Tool search 164,478 tools · 10,067 live servers

Fetch the exact schema(s) for tool(s) you ALREADY know by name — e.g. names a skill/playbook gave you (getTestReportFull, updateTestCase, listTestReports, getMock, getTestCase, getApp, listApps, ...). Returns ONLY the named tools: no fuzzy matching, no unrelated tools. Use this instead of search_tools whenever you know the name — it is exact and cheap. Use search_tools only to DISCOVER names you do not already know. Returns {"tools": [{name, description, inputSchema}, ...], "not_found": [names...]}.

Run any Keploy tool by name. Most tools are hidden from the default list. Know the name from a skill? get its schema with get_tool_schema; don't know the name? discover it with search_tools. Then call invoke_tool with that name and an "arguments" object matching the tool's inputSchema. Example: invoke_tool {"name": "getTestReportFull", "arguments": {"appId": "...", "testRunId": "...", "fields": ["status"]}}

DISCOVER tool names you do NOT already know, by keyword. Most Keploy tools are hidden from the default tool list to save context. If you ALREADY know the exact name (e.g. a skill named it), call get_tool_schema instead — it is exact and far cheaper than this fuzzy search. Returns {"matches": [{name, description, inputSchema}, ...], "total_catalog": N}. Search by intent words, e.g. "test report", "mock patch", "update test case", "cloud replay branch", "record".

Use for broad RevoGrid questions or when the exact API name is unknown. Searches source-grounded docs and API evidence; defaults to public exports.

Use for broad RevoGrid questions or when the exact API name is unknown. Searches source-grounded docs and API evidence; defaults to public exports.

Search documentation with hybrid semantic (vector) and keyword (BM25) search. Use semanticWeight to choose keyword-only (0), semantic-only (1), or a blend; mid values fuse rankings with RRF. Supports Tiger Cloud (TimescaleDB), PostgreSQL, and PostGIS.

Retrieve detailed skills for TimescaleDB operations and best practices. ## Available Skills <available_skills> [9 ]{name description}: design-postgis-tables Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications design-postgres-tables "Use this skill for general PostgreSQL table design.\n\n**Trigger when user asks to:**\n- Design PostgreSQL tables, schemas, or data models when creating new tables and when modifying existing ones.\n- Choose data types, constraints, or indexes for PostgreSQL\n- Create user tables, order tables, reference tables, or JSONB schemas\n- Understand PostgreSQL best practices for normalization, constraints, or indexing\n- Design update-heavy, upsert-heavy, or OLTP-style tables\n\n\n**Keywords:** PostgreSQL schema, table design, data types, PRIMARY KEY, FOREIGN KEY, indexes, B-tree, GIN, JSONB, constraints, normalization, identity columns, partitioning, row-level security\n\nComprehensive reference covering data types, indexing strategies, constraints, JSONB patterns, partitioning, and PostgreSQL-specific best practices.\n" find-hypertable-candidates "Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.\n\n**Trigger when user asks to:**\n- Analyze database tables for hypertable conversion potential\n- Identify time-series or event tables in an existing schema\n- Evaluate if a table would benefit from Timescale/TimescaleDB\n- Audit PostgreSQL tables for migration to Timescale/TimescaleDB/TigerData\n- Score or rank tables for hypertable candidacy\n\n\n**Keywords:** hypertable candidate, table analysis, migration assessment, Timescale, TimescaleDB, time-series detection, insert-heavy tables, event logs, audit tables\n\nProvides SQL queries to analyze table statistics, index patterns, and query patterns. Includes scoring criteria (8+ points = good candidate) and pattern recognition for IoT, events, transactions, and sequential data.\n" migrate-postgres-tables-to-hypertables "Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation.\n\n**Trigger when user asks to:**\n- Migrate or convert PostgreSQL tables to hypertables\n- Execute hypertable migration with minimal downtime\n- Plan blue-green migration for large tables\n- Validate hypertable migration success\n- Configure compression after migration\n\n**Prerequisites:** Tables already identified as candidates (use find-hypertable-candidates first if needed)\n\n**Keywords:** migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup\n\nStep-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries.\n" pgvector-semantic-search "Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.\n\n**Trigger when user asks to:**\n- Store or search vector embeddings in PostgreSQL\n- Set up semantic search, similarity search, or nearest neighbor search\n- Create HNSW or IVFFlat indexes for vectors\n- Implement RAG (Retrieval Augmented Generation) with PostgreSQL\n- Optimize pgvector performance, recall, or memory usage\n- Use binary quantization for large vector datasets\n\n**Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search\n\nCovers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning.\n" postgres "Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations.\n\n**Trigger when user asks to:**\n- Design or modify PostgreSQL tables, schemas, or data models\n- Choose data types, constraints, indexes, or partitioning strategies\n- Work with pgvector embeddings, semantic search, or RAG\n- Set up full-text search, hybrid search, or BM25 ranking\n- Use PostGIS for spatial/geographic data\n- Set up TimescaleDB hypertables for time-series data\n- Migrate tables to hypertables or evaluate migration candidates\n- Plan or execute safe schema migrations with zero downtime\n\n**Keywords:** PostgreSQL, Postgres, SQL, schema, table design, indexes, constraints, pgvector, PostGIS, TimescaleDB, hypertable, semantic search, hybrid search, BM25, time-series, migration\n" postgres-database-migration "Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases.\n\n**Trigger when user asks to:**\n- Test a schema migration before applying it to production\n- Add, remove, or rename columns safely on a live table\n- Change a column's data type without downtime\n- Add or drop indexes, constraints, or foreign keys on large tables\n- Understand which ALTER TABLE operations lock the table\n- Roll back a failed migration\n- Plan a zero-downtime migration strategy\n- Fork a database to test a migration safely\n\n**Keywords:** migration, schema change, ALTER TABLE, add column, drop column, rename column, change type, zero downtime, lock, AccessExclusiveLock, concurrent index, forking, rollback, backfill, deploy\n\nCovers: lock-level reference for every common DDL operation, safe migration patterns, fork-based testing, zero-downtime column changes, index creation, constraint addition, backfill strategies, pre/post-migration validation, and rollback planning.\n" postgres-hybrid-text-search "Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF).\n\n**Trigger when user asks to:**\n- Combine keyword and semantic search\n- Implement hybrid search or multi-modal retrieval\n- Use BM25/pg_textsearch with pgvector together\n- Implement RRF (Reciprocal Rank Fusion) for search\n- Build search that handles both exact terms and meaning\n\n\n**Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder\n\nCovers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.\n" setup-timescaledb-hypertables "Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table.\n\n**Trigger when user asks to:**\n- Create or design SQL schemas/tables AND Timescale/TimescaleDB/TigerData/Tiger Cloud is available\n- Set up hypertables, compression, retention policies, or continuous aggregates\n- Configure partition columns, segment_by, order_by, or chunk intervals\n- Optimize time-series database performance or storage\n- Create tables for sensors, metrics, telemetry, events, or transaction logs\n\n**Keywords:** CREATE TABLE, hypertable, Timescale, TimescaleDB, time-series, IoT, metrics, sensor data, compression policy, continuous aggregates, columnstore, retention policy, chunk interval, segment_by, order_by\n\nStep-by-step instructions for hypertable creation, column selection, compression policies, retention, continuous aggregates, and indexes.\n" </available_skills>

Full-text search across all published tax and accounting skills. Find, lookup, query, or discover skills by keyword, tax concept, deduction type, form number, or regulation (e.g. 'home office deduction', 'crypto capital gains', 'reverse charge', 'Schedule C', '60-day reporting'). Optionally limit to one jurisdiction. Use this when you don't know the exact skill slug. Set content_type='method' to discover step-by-step METHODS (guided procedures — what you EXECUTE via start()) instead of reference material; each method carries a review_status (accountant-reviewed | source-cited).

Sweep tax rules ACROSS jurisdictions and metadata and get back a bundled markdown rule set plus the jurisdiction's OFFICIAL SOURCE. Best for cross-cutting questions — 'VAT rates in MT, IE and DE', 'all income-tax thresholds for 2025', 'rules mentioning reverse charge'. WHEN YOU WANT ONE SPECIFIC FIGURE for one jurisdiction (a single rate, threshold or date), prefer `search_skills` then `get_skill`: the Guide is where a topic is covered in full, and a figure can exist in the Guide without existing as a separate rule here, in which case this tool will return related guidance rather than the number you asked for. Entries whose text is guidance rather than a value are tagged `GUIDANCE` — never read one as a figure. IMPORTANT: this returns human-reviewed GUIDANCE and does NOT certify that a figure is current — confirm each number against the official source returned in `official_source` before you state it, and prefer that source when they disagree. By default returns ALL matching rules, each tagged with its verification status; pass status:'verified' for accountant-/research-verified only. Call `list_rule_facets` first to see the queryable values.

Returns the metadata you can filter on with `search_rules` — the live jurisdictions, the domains, roles, block types (rule kinds), statuses, tax years, and a sample of topics — plus the defaults. Call this before `search_rules` to learn the valid filter values rather than guessing.

Search tennis players by name. Returns id, country, ranking and tour. Use the returned id with get_player.

Search the tournament catalogue — the stable id space that match objects carry as tournament_id. Returns surface, indoor, host city/country and category where curated.

Search the results archive — completed-match RESULTS from 1968 through 2022: ATP and WTA, main draws, qualifying and the ITF/futures tiers. Winner/loser-shaped records with final score, seeds and ranks AT THE TIME of the match. Use this for historical questions ("Borg's Wimbledon finals"); the archive ends 2022-12-31 where our own results (get_recent_results) begin. Requires the BASIC plan or any History plan.

The people of the results archive (1968–2022): hand, date of birth, country, height, and career-high rank with the week it was first reached. Their ids are corpus person ids (the winner/loser player_id on archive results), not roster ids — for current players use search_players. Requires the BASIC plan or any History plan.

Interactive dashboard variant of `search`: returns summary metrics, a source breakdown chart, and a results table with a click-to-expand detail panel, all rendered in the conversation. Same params as `search`. Use for a richer visual overview of a query's results. Automatically selects an engine-specific dashboard when available (e.g. google_flights gets price intelligence charting).

Interactive UI variant of `search`: returns organic results as a sortable, searchable table rendered in the conversation. Same params as `search`. Use when the host supports MCP Apps and the user wants to browse results visually rather than read JSON.

Universal search tool supporting all SerpApi engines and result types. When to use: - Any query needing live, structured SERP data: web results, news, product listings, job postings, local businesses, flight/hotel prices, video results, images, stock/weather cards, knowledge graph entities. Engine discovery via MCP resources: - serpapi://engines lists all engines supported by this tool. - serpapi://engines/<engine> provides engine-specific parameters and supported options. - Example: serpapi://engines/google_news Input schema: params: JSON object containing SerpApi engine parameters. Common parameters: - q: Search query. Required for most engines. - engine: SerpApi engine name. Defaults to "google_light". - location: Optional geographic location for localized results. - output: Optional response format. Omit for JSON (default), or set to "md" for Markdown. Engine-specific parameters are available via MCP resources: - serpapi://engines lists all supported engines. - serpapi://engines/<engine> provides parameters and options for one engine. mode: Response mode. Defaults to "complete". - "complete": Return the full SerpApi response. - "compact": Remove metadata fields from JSON responses. Markdown is returned unchanged. Output schema: Markdown when params.output is "md"; otherwise a JSON string or an error message. Examples: Weather: {"params": {"q": "weather in London", "engine": "google"}, "mode": "complete"} Stock: {"params": {"q": "AAPL stock", "engine": "google"}, "mode": "complete"} General: {"params": {"q": "coffee shops", "engine": "google_light", "location": "Austin, TX"}, "mode": "complete"} Compact: {"params": {"q": "news"}, "mode": "compact"} Markdown: {"params": {"q": "news", "output": "md"}} Supported engines include (not limited to): - google - google_light - google_flights - google_hotels - google_images - google_news - google_local - google_shopping - google_jobs - bing - yahoo - duckduckgo - youtube_search - baidu - ebay

Search PubMed with full query syntax, filters, and date ranges. Returns PMIDs and optional brief summaries. Supports field-specific filters (author, journal, MeSH terms), common filters (language, species, free full text), and pagination via offset for paging through large result sets.

Spell-check a query and get NCBI's suggested correction. Useful for refining search queries.

Search and explore the MeSH (Medical Subject Headings) controlled vocabulary. Returns descriptor records with tree numbers, scope notes, and entry terms, plus pagination via offset for paging past the maxResults cap.

Look up PubMed IDs from partial bibliographic citations. Useful when you have a reference (journal, year, volume, page, author) and need the PMID — deterministic citation matching, more reliable than free-text search for structured references. Each citation must include at least journal or year (ECitMatch primary-keys on journal+volume+page; author-only or volume-only inputs guarantee no match); more fields = better match accuracy.

Convert between article identifiers (DOI, PMID, PMCID). Accepts up to 50 IDs of a single type per request. Only resolves articles indexed in PubMed Central — for articles not in PMC, use pubmed_search_articles instead.

Search Europe PMC, a broad open-access biomedical corpus. Surfaces preprints (`source: PPR`), patents (`source: PAT`), Agricola (`source: AGR`), plus everything in PubMed (`MED`) and PMC. Use when additional coverage is needed — preprints and EPMC-only OA records are the typical recovery. Paginate via `cursorMark`. Defaults to `MED`, `PMC`, and `PPR`; pass `sources` to include `PAT` / `AGR`. Abstracts arrive as a bounded `abstractSnippet` with `abstractTruncated` marking the cut ones — pass a hit’s `source` and `epmcId` to `pubmed_europepmc_fetch` for the complete abstract.

Semantic retrieval (#1089): return the records in a CSV most similar to a free-text query, ranked by cosine similarity. Embeds the chosen column and the query with the zero-config in-house embedder (no cloud/torch by default) and runs ANN search. The read side of the RAG entity-canonicalization epic -- fetch candidate records by query without running a full dedupe.

Find duplicate matches for a record. Provide field values to search against the loaded dataset.

Alias for `find_duplicates`. Find duplicate matches for a record. Provide field values to search against the loaded dataset.

Search for clinical trial studies from ClinicalTrials.gov. Supports full-text and field-specific queries, status/phase/geographic filters, pagination, sorting, and field selection. Returns a compact per-study index by default; pass the fields parameter to get specific leaves at full fidelity — full study records are ~70KB each.

Discover valid values for ClinicalTrials.gov fields with study counts per value. Use to explore available filter options before building a search — e.g., valid OverallStatus, Phase, InterventionType, StudyType, or LeadSponsorClass values.

Resolve valid field names from the ClinicalTrials.gov data model — the canonical PascalCase identifiers (OverallStatus, EnrollmentCount, LeadSponsorName) accepted by the `fields`, `advancedFilter`, and `sort` parameters of other tools, and as input to clinicaltrials_get_field_values. Select a mode: `"search"` — keyword search returning ranked matches (pass `query`, e.g. "enrollment", "sponsor", "adverse events"); `"drill"` — drill into a specific section by dot-notation path (pass `path`, e.g. "protocolSection.designModule"); `"overview"` — top-level summary of all sections (no additional args).

Fetch clinical trial results data from ClinicalTrials.gov for completed studies — outcome measures with statistics, adverse events, participant flow, baseline characteristics, and results metadata (limitations & caveats, certain-agreement disclosure restrictions, results point of contact). Only available for studies where hasResults is true. Use clinicaltrials_search_studies first to find studies with results. A results-rich record can exceed 500KB per study in full mode — bound it with summary=true, narrower sections, or the outcomeLimit / adverseEventLimit caps, whose trims are reported per study in filtersApplied.

Match patient demographics and conditions to eligible recruiting clinical trials. Provide age, sex, conditions, and location to find studies with matching eligibility criteria, contact information, and recruiting locations. Results are re-ranked so studies whose own condition matches a requested condition surface above tangential matches from ClinicalTrials.gov's fuzzy condition search. Each candidate returns only the sites matching the requested location (capped by locationLimit), not the study's full registered site list — a large trial can register hundreds of sites worldwide. When none of a candidate's matched sites is recruiting, its nearest recruiting site is added, so an enrollable site is never hidden behind a closer closed one. Fetch a study's complete record with clinicaltrials_get_study_record.

Write conversation messages to DeepMemory for fact extraction and persistent storage. Messages are processed by an LLM to extract structured memories, which are then embedded and stored in a vector database for later semantic search. Set infer=True to enable LLM fact extraction (produces richer memories but costs one LLM call). Set infer=False to store raw messages without extraction. Returns a list of memory IDs for successfully stored facts.

Search memories stored in DeepMemory using semantic search. Returns the most relevant memories for the given query, ranked by hybrid scoring (vector similarity + BM25 keyword match + entity boost + time decay). Use this to retrieve context from past conversations before responding to the user. Memories are scoped to the user_id provided during write.

Full-text search within one channel. Use this instead of paging history when you know roughly what was said. Same access rules as freeq_history.

List all available legal agreement templates as a paginated compact catalog. Returns lightweight metadata for discovery — call get_template for full per-field detail. Templates are returned in stable lexicographic order by template_id. For finding templates by topic, jurisdiction, or source, use search_templates instead.

Search for legal agreement templates by keyword. Uses BM25 ranking to find the most relevant templates matching your query. Searches across template names, descriptions, categories, sources, and field definitions. Use this instead of list_templates when you know what kind of agreement you need.

Walk a note's table of contents level by level (progressive disclosure). Canonical call: expand(path=<result.note_path>, toc_path=[...]) — copy path verbatim from a search result's note_path field. Returns the direct children of a TOC node: omit toc_path (or pass []) for the top-level sections, or pass a toc_path to list that section's subsections. Each child has title, level, path, and has_children. A section with subsections lists them; a section without subsections is returned in full (what note_html gives for that toc_path, plus section_html in the payload), so no second call is needed to read a leaf. This cannot be turned off, and a client that wants only structure never triggers it: has_children on each listed child says where descending would turn into reading.

Fetch the instructions/guidance for a federated knowledge base by kb_id (e.g. "philosophers/nietzsche") — read a base's own conventions before searching it. Nested bases are addressed with '/' and the call routes through each peer recursively.

Read a remote note inside a connected knowledge base. Canonical call, copying fields verbatim from a federated_search result: federated_search(kb_id="philosophers/<author>", query) -> federated_note_html(kb_id="philosophers/<author>", path=<result.note_path>) — the standard way to descend into a leaf corpus and read real content there, not hub cards. federated_note_html(kb_id=..., match_id=<match.match_id>) reads just the focused chunk around a hit. Only pass pid/note_id if you already copied that exact id from a result. path is a string like "concepts/x.md"; match_id is "p<pid>:c<chunk>"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.

Search connected knowledge bases. Returns snippets with heading breadcrumbs (title > section > subsection) and a precise toc_path per match, same as search; results also carry an absolute kb_id (string) to use verbatim on follow-up calls. Pass kb_id for one base, kb_ids for selected bases, or omit both to fan out. Nested bases are addressed with '/': kb_id "philosophers/nietzsche" routes through the 'philosophers' peer to the base it federates (recursive), up to 3 levels deep. Canonical call: federated_search(kb_id="philosophers/<author>", query) -> federated_note_html(kb_id="philosophers/<author>", path=<result.note_path>) — the standard way to descend into a leaf corpus and read real content, not hub cards.

Find remote notes similar to a known note reference inside a connected knowledge base. Preferred: path (a federated_search result's note_path field).

Read a note. Canonical calls, copying fields verbatim from a search result: search(query) -> note_html(path=<result.note_path>) reads the whole note; search(query) -> note_html(match_id=<match.match_id>) reads just the focused chunk around a hit (cheaper, targeted); expand(path=<result.note_path>, toc_path=[...]) -> note_html(path=<result.note_path>, toc_path=[...]) reads one exact section. Only pass pid/note_id if you already copied that exact integer from a result's note_id field — never invent one. path is a string like "concepts/x.md"; match_id is "p<pid>:c<chunk>"; a value like ":" or "/hub/goethe.md" is a PATH, not a note_id.

Retrieve detailed CVE data by ID: description, CVSS v3.1 + vector, CVSS v2 (always emitted), EPSS score + percentile, CISA KEV status (expanded: due_date, required_action, ransomware flag, vendor_project, product, vulnerability_name, short_description, notes, cwes, date_removed when in_kev=true), NVD vulnerability_status (Analyzed/Modified/Awaiting Analysis/Deferred/Rejected/Withdrawn), cve_tags ('disputed' triggers [DISPUTED] summary prefix), affected products (CPE), references, patch availability, related CVEs. By default affected_products is truncated to the first 20 entries (total_products reports the honest count) and references to the first 10 (total_references reports the honest count). Pass include_affected_products=true and/or include_full_references=true for the complete lists. Pass include_reference_tags=true to receive structured references_full=[{url, tags, source}] (NVD upstream tags + source provenance) — also activates tag-first patch detection. Pass include_severity_breakdown=true to receive severity_sources/consensus/disagreement (multi-source view of NVD/MITRE/GHSA/OSV severity assessments). Use for single-CVE details; use cve_search for queries by product/severity. Response carries next_calls — chain with kev_detail when kev.in_kev=true, with cwe_lookup on each CWE in cwes (up to 3 pivots), and with exploit_lookup for public PoC availability. Free: 30/hr, Pro: 500/hr. Returns {cve_id, summary, description, severity, cvss_v3, cvss_v2, cvss_v2_vector, cvss_breakdown, cwe_id, cwes, vulnerability_status, cve_tags, published, modified, sources, first_seen_source, first_seen_at, epss, kev (in_kev, date_added, due_date, required_action, known_ransomware_use, vendor_project, product, vulnerability_name, short_description, notes, cwes, date_removed), affected_products (first 20 by default), total_products, references (first 10 by default), total_references, total_references_unique, references_full (only when include_reference_tags=true), severity_sources/severity_consensus/severity_disagreement (only when include_severity_breakdown=true), patch_available, related_cves, verdict, next_calls}.

Search CVE database with filters: product/vendor, severity, published date range, EPSS score, CWE, CVSS range, CISA KEV status. Default response is SLIM per-result (cve_id, summary, severity, cvss_v3, cwe_id, epss, kev, total_products, published, modified, sources) — pass include='full' for description, cvss_breakdown, affected_products, references, first_seen_*. Verdict (sources_queried, falsifiable_fields, completeness, data_age) is at the response root — applies to the whole batch, not per-row. Product/vendor filters are EXACT NVD-canonical-token matches (not the common name — e.g. nginx is 'nginx_open_source'/'nginx_plus', vendor 'f5'); a low/zero count for a well-known product means the token differs, so for dependency/package lists use check_dependencies and for a domain's whole stack tech_stack_cve_audit (both auto-normalize tokens). Use for vulnerability discovery by criteria; pass cwe_id (e.g. CWE-79) to enumerate every CVE in our database mapped to a weakness — pair with cwe_lookup for the category description and mitigations. Use cve_lookup for single CVE by ID, kev_detail when kev=true filtering and the agent needs federal patch deadlines per result. Response carries a global hint pointing at cve_lookup — drill into any returned cve_id for full detail and chained pivots (exploit_lookup, kev_detail, cwe_lookup). Free: 30/hr, Pro: 500/hr. Returns {count, total, truncated, offset, summary, results, query_echo, next_offset, verdict, hint}.

List CVEs indexed from MITRE/GHSA BEFORE NVD publication (early-warning, freshest data). By default each result is slim (no description, no cvss_breakdown, no affected_products list, no references) — pass include='full' for the same payload shape as cve_lookup; for drill-down on a single CVE prefer cve_lookup. Use for threat intelligence on emerging CVEs; use cve_search for published NVD data. Verdict (sources_queried, falsifiable_fields, completeness, data_age) is at the response root — applies to the whole batch, not per-row. Response carries a global hint pointing at cve_lookup — drill into any returned cve_id for full detail and chained pivots (exploit_lookup, kev_detail, cwe_lookup). Free: 30/hr, Pro: 500/hr. Returns {count, total, truncated, offset, summary, results, next_offset, verdict, hint}.

Search public exploits/PoC for a specific CVE across three sources: (1) GitHub Advisory Database (sources.github.advisories[]), (2) Shodan CVEDB references (sources.shodan_refs.results[] — packetstorm/seclists/vendor URLs cited by Shodan; results capped at SHODAN_REFS_LIMIT default 200, truncated=true when capped, count is the honest upstream total), (3) ExploitDB CSV mirror (exploits[] array, with edb_id + author + verified flag — these are the actual ExploitDB entries). Use to assess if a vulnerability has weaponized exploits in the wild; run after cve_lookup to evaluate real-world risk. When the CVE is also in CISA KEV (kev.in_kev=true on cve_lookup), pair with kev_detail for federal patch deadline; pair with cwe_lookup on cwe_id for the underlying weakness category and mitigations. Response carries next_calls — single cve_lookup pivot for full context (KEV status, CWE chain, CVSS, EPSS); cve_lookup's own next_calls then surface kev_detail and cwe_lookup automatically (this endpoint has no in_kev/cwe_id schema, so blind emission of those pivots is intentionally avoided). Free: 30/hr, Pro: 500/hr. Returns {cve_id, exploits_found, has_public_exploit, sources: {github, shodan_refs: {found, count, truncated, results}}, exploits: [{edb_id, cve_id, date_published, author, type, platform, url, verified, description}], summary, verdict, next_calls}.

Look up CISA KEV (Known Exploited Vulnerabilities) full record for a CVE. Returns federal patch deadline (due_date), CISA-specified required_action remediation, known ransomware association, vendor/product, the CISA-given common name (e.g. 'Log4Shell'), CISA-reported CWE list, plus lifecycle metadata: date_updated (when CISA last revised the entry), date_removed (set when CISA removed the CVE from the catalog — null while still active), and updated_at (our DB sync freshness). Returns 404 when the CVE is not in the KEV catalog — use cve_lookup for non-KEV CVEs. Best follow-up after cve_lookup or cve_search(kev=true) when an in_kev=true CVE is identified; chain with cwe_lookup on each returned CWE to investigate the weakness category. Free: 30/hr, Pro: 500/hr. Returns {cve_id, vendor_project, product, vulnerability_name, date_added, due_date, required_action, known_ransomware_use, notes, cwes, date_updated, date_removed, updated_at, verdict, next_calls}.

Look up MITRE CWE (Common Weakness Enumeration) catalog record from research view 1000. Default response is SLIM (first 3 mitigations, first 3 examples; extended_description is null) — pass include='full' for the verbose record (full mitigations + examples lists, populated extended_description). Returns description, abstract type (Pillar/Class/Base/Variant/Compound), status (Stable/Draft/Incomplete/Deprecated), exploit likelihood, recommended mitigations, observed example CVEs, parent_cwe (walk up the hierarchy), child_cwes (drill down to more specific weaknesses), and cve_count (LOWER BOUND — counts only CVEs whose primary CWE matches; CVEs with multiple CWEs may not be counted). Use after cve_lookup or kev_detail to understand the underlying weakness category; chain with cve_search(cwe_id=...) to enumerate all matching CVEs. Returns 404 when the CWE is not in research view 1000. Free: 30/hr, Pro: 500/hr. Returns {cwe_id, name, description, extended_description (null on slim, populated on include='full'), abstract_type, status, likelihood, mitigations (first 3 by default), total_mitigations, examples (first 3 by default), total_examples, parent_cwe, child_cwes, cve_count, updated_at, verdict, next_calls}.

Use when the user wants to find public developers by skill, name, language, location, agent availability, or active opportunity intent. Start discovery here; no authentication is required. Example: {"query":"TypeScript maintainers","location":"Germany","availableForAgents":true,"limit":5}.

Use when the user names a GitHub login or selects one DevGlobe search result and needs its public profile and contribution evidence. No authentication is required. Example: {"login":"sajeetharan"}.

Current web and news search returning snippets, source URLs, and metadata. Default for finding current information; supports domain, country, language, and freshness filters, and extraction (highlights or full page content). For multi-part questions, issue a separate focused query per sub-question — one facet each, not the whole question.

One-shot cited synthesis — research a topic and return a concise answer with inline citations and source list. Use when a synthesized, sourced answer is needed rather than raw search results. Configurable effort levels (lite, standard, deep, exhaustive, frontier).

Fast live-web answer generation returning one synthesized answer with verified inline citations, citation excerpts, and supporting web results. Use when the caller wants a single sourced answer; use research for deeper multi-step investigation, effort control, structured output, or background tasks. Supports freshness, country, language, and domain filters.

Discover AI agents, MCP servers, A2A agents, and skills via ARD Agent Finder services. Search-only — never installs or connects. Returns ranked results with relevance scores.

One call: completed-session state, tape, historical analogs, outcome ranges and transition memory. symbol is a stock ticker; optional date is YYYY-MM-DD. Omit date for the latest built session, not real-time prices. Preserve status, sample sizes, dates, informative receipts and missing values. Excess ranges describe historical percentage-point returns relative to a date-matched baseline; they are not calibrated forecasts or recommendations. No prior search needed.

Read the published daily research, its selection rule and settled-note tally in one call. No arguments needed. Optional date (YYYY-MM-DD) selects a published session. A missing note or unsettled outcome is unavailable evidence, not zero. The note is research selected by a disclosed rule, not a stock-pick list.

Read the published five-session calibration receipt; no arguments or earlier tool call needed. Preserve the receipt's dates, sample sizes and qualifications. Coverage applies to the calibrated cohort-band method and population named in the response, NOT automatically to market_state's empirical excess ranges, all research, or future returns. Daily-note results have a separate tally in daily_note. This is an evidence audit, not investment performance.

List all available documentation categories. Use this to discover what categories are available before searching.

Search for relevant documentation. Use `list-categories` first to see available categories. Filter by query text, framework, phase, feature, category, or tags. Returns documents sorted by relevance.

Read the full content of a specific document by path. Use this after `search` to get the complete document when snippets are not enough.

RETURNS A LIST OF BOOKS (works on a topic) — NOT passages. PICK THIS to discover which works exist on a subject. → For quotable text use search_translations (exact words) or search_concept (by meaning); if the user already named an author/work, call get_book directly (or list_books to find the ID) — the AI summary + chapter outline is usually the right first answer. Searches titles, authors, subjects, and (as a secondary signal) translated text. Query tips: single distinctive words or short phrases work best ("memory palace", "ouroboros"); quoted phrases match exactly. Each result includes total_matches (full count) + returned (this page) + offset for pagination.

RETURNS QUOTABLE PASSAGES (page-level snippets + citation URLs), matched by KEYWORD/term. PICK THIS to find a quote or textual evidence on a topic across the whole library. → If the modern word won't literally appear in historical texts, use search_concept (matches by meaning); to list which BOOKS cover a topic use search_library; to dig inside one known book use search_within_book; if the user named an author/work, get_book first (its AI summary is usually the right first read). Query tips: single distinctive terms ("memory palace", "wax tablet") work best; multi-word natural-English queries ("unity of the intellect") may return fewer results because matching is term-based, not phrase-based. Each snippet has a snippet_type — "translation"/"ocr" means it is a verbatim extract from the source text; "summary" means it is AI-generated description (do not quote those as the author's words). Response includes total_matches, returned, and offset for pagination. Cross-cultural tip: for pre-modern or non-Western topics, search source-tradition vocabulary rather than modern English terms — e.g. for seminal economy search "jing" or "bindu" or "istimnāʾ", not "semen retention"; for female homoeroticism search "tribade" or "sahq", not "lesbian". The corpus is indexed via period translations that use tradition-internal terminology.

RETURNS QUOTABLE PASSAGES matched by MEANING (cosine similarity on Gemini embeddings, 768d) — paraphrases and adjacent phrasings match even with zero keyword overlap. PICK THIS when the modern term won't literally appear in historical texts — e.g. "distributed cognition" maps to passages about active intellect, art of memory, wax tablet metaphors; "social contract" maps to pre-Hobbesian discussions of consent and authority. → For exact words/distinctive terms use search_translations (cheaper, more precise); to list which BOOKS cover a topic use search_library; if the user named an author/work, get_book first (semantic search is expensive — reserve it for cross-corpus discovery). Similarity calibration: 0.70+ is a strong match, 0.55–0.70 is worth reading but verify, below 0.55 is mostly conceptual drift. Set max_per_book to diversify results across many books rather than cluster on one source. Each passage carries a snippet_type — quote only "translation" snippets, never "summary". Cross-cultural tip: for pre-modern or non-Western topics, also try source-tradition vocabulary — e.g. for seminal economy try "jing preservation" or "bindu yoga" or "istimnāʾ"; for masturbation try "mollities" (Latin) or "hastamaithuna" (Sanskrit) or "shouyin" (Chinese). The corpus is indexed via period translations that use tradition-internal terminology, so adjacent/euphemistic terms often surface material that modern English keywords miss.

SEARCHES INSIDE ONE BOOK (requires book_id). PRIMARILY KEYWORD: it runs a lexical search over the book's pages plus a narrow scoped-semantic pass (top ~10), interleaved by relevance. PICK THIS when you know the wording you are looking for, or want every page of one book mentioning a term. → IF YOU ARE SEARCHING FROM A PARAPHRASE, a half-remembered line, or a modern restatement, USE search_concept INSTEAD — it is the meaning-matching tool and it searches the whole corpus, including translations whose vocabulary differs completely from yours (Thomas Taylor writes "energies" for energeia and "felicity" for eudaimonia, so a sensible modern paraphrase can miss his pages entirely while matching semantically). → To find the book first, use search_library or search_concept, then pass its book_id here. Each result carries score (0-1, normalised within this book) and found_by ("keyword", "semantic", or "both" — both is the strongest signal). Results flagged is_front_matter are the translator's or publisher's words rather than the author's, and are ordered last. Returns OCR and translation snippets with page numbers, ready to cite.

BROWSES/FILTERS THE CATALOG by metadata (canonical author via author_id, author/title fragment via search, language, category, year range, translation recency) — no content/topic matching. PICK THIS to see WHAT EXISTS by an author or in a tradition, or to enumerate a date range. Returns books with title, author (string + canonical author_id + author_url), language, year, and translation progress. → For a relevance-ranked topic search use search_library; for passages on a theme use search_translations (exact words) or search_concept (by meaning).

READ PIPELINE step 1 — DISCOVER. START HERE for any named work or author. Returns the book's AI-generated summary, chapter list, edition metadata, DOI, page counts, IIIF manifest, and the cover image (inline, so you and the user can see the book). LANGUAGE: `language` is what is printed on THIS EDITION's leaves, which is frequently not the language the work was written in. Where they differ the response also carries `work_language`, `text_role` (original / period-translation / modern-translation) and a `translation_note` — read them before describing a passage as the author's own words, because an edition can be a translation of a translation (de Slane's 1863 French Muqaddimah, read in English, is English←French←Arabic). Absent `work_language` means the edition is in the work's own language. Use list_editions to find an original-language witness. The summary is typically a multi-paragraph orientation covering the book's argument, structure, and significance — often answering the question without further searching. Then: get_book_text to read a chapter or page range (step 2), get_quote / get_quotes to lock specific pages with full citation apparatus (step 3). search_within_book locates passages inside this book. MULTI-WORK VOLUMES: where the scans carry running heads, contains_works lists the works the volume ACTUALLY holds with their page spans, taken from the heads the printer put on each leaf. Trust it over the title — collected-works titles routinely name works the volume does not contain, and the volume holding a work often does not name it. If contains_works is absent the scans have no heads to read; status "insufficient-heads" means it was examined and could not be decided. EDITIONS: `editions` says which languages this book can be READ in and how many pages each covers ({ en: 357 } on most books, { en: 357, es: 357 } where a localized edition exists). Pass a code as `lang` to get_quote, get_quotes, get_book_text or search_within_book to read that edition; without it you get English.

Audit domain crawler readiness for AI search engines (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bytespider). Checks robots.txt, HTTP headers, llms.txt availability, and generates a custom llms.txt markdown map. [effect=read; scope=intel:read]

Audit brand profile readiness and completeness across G2, Capterra, Trustpilot, and Gartner Digital Markets to optimize software category indexing in LLM search. [effect=read; scope=connections:read]

Discover and source verified B2B prospects for outbound outreach by title, industry, and company criteria. Pass domains (preferred) or company_domain (alias for a single domain). RevenueBase vendor search is tenant-free (shared lookup, no house-tenant campaign data). [effect=read; scope=growth:read]

Find websites by BuiltWith technology, natural language audience, or keyword search. (2 credits) [effect=read; scope=intel:read]

BuiltWith Product API — ecommerce shops and product listings matching a product query. (2 credits) [effect=read; scope=intel:read]

Research real demand before planning a campaign: keyword volumes and CPCs, what competitors are actually running, and current trends. Run this BEFORE create_campaign_plan. [effect=read; scope=campaigns:read]

Discover Apideck tools. Call with no args for domain index; filter with domain/search_terms/scope.

Audit domain crawler readiness for AI search engines (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Bytespider). Checks robots.txt, HTTP headers, llms.txt availability, and generates a custom llms.txt markdown map. [effect=read; scope=intel:read]

Audit brand profile readiness and completeness across G2, Capterra, Trustpilot, and Gartner Digital Markets to optimize software category indexing in LLM search. [effect=read; scope=connections:read]

Discover and source verified B2B prospects for outbound outreach by title, industry, and company criteria. Pass domains (preferred) or company_domain (alias for a single domain). RevenueBase vendor search is tenant-free (shared lookup, no house-tenant campaign data). [effect=read; scope=growth:read]

Find websites by BuiltWith technology, natural language audience, or keyword search. (2 credits) [effect=read; scope=intel:read]

BuiltWith Product API — ecommerce shops and product listings matching a product query. (2 credits) [effect=read; scope=intel:read]

Research real demand before planning a campaign: keyword volumes and CPCs, what competitors are actually running, and current trends. Run this BEFORE create_campaign_plan. [effect=read; scope=campaigns:read]

Rental market analysis and achievable rent estimate. auto_escalate widens the Rightmove search RADIUS when fewer than 5 listings are found (thin market). This is rental-radius escalation and is unaffected by the PPD geography containment: it does not change a postcode's outcode or sector, so it carries none of the limit-dependence that disabled PPD auto-widening. Response includes thin_market, escalated_from, escalated_to fields when escalation occurs.

DEPRECATED — use property_epc_summaries then epc_certificate. This tool returned score, floor_area, property_type, habitable_rooms and inspection_date for every certificate at a postcode. The EPC service no longer exposes those fields in a search: they exist only on a full certificate. Reproducing the old response would require one upstream request per certificate, so this tool is unsupported rather than silently degraded or silently expensive.

List EPC certificate summaries at a postcode — for candidate selection. Returns one bounded page. Each entry contains only what the EPC search exposes: certificate_number, address, uprn (often absent), energy band, registration_date and schema_type. Energy score, floor area and property type are NOT available here — fetch a specific certificate for those. Workflow when a Rightmove listing has no house number: 1. property_epc_summaries(postcode) to list candidates. 2. Narrow by address text and, where present, uprn. 3. epc_certificate(lmk_key=<certificate_number>) for the chosen one, then cross-check its floor_area against the listing. 4. If several candidates remain equally plausible, present them all — do not guess. Selecting arbitrarily attaches another property's data. `complete` is false when the postcode holds more records than this page returns. Upstream page traversal is not snapshot-stable, so a multi-page result is a bounded sample, not a guaranteed-complete set. An empty `results` list means no certificates are lodged. If the EPC service cannot be reached the tool raises an error instead — never treat an error as evidence that a property has no certificate.

Fetch a single EPC certificate by its GOV.UK certificate number. Use after property_epc_summaries has listed the candidates and you have picked one — this is faster than property_epc(postcode, address) as it makes a direct lookup with no address matching or postcode re-fetch. The parameter is named lmk_key as a compatibility alias; pass the certificate number, which is returned in every property_epc_summaries row. (property_epc_search is deprecated and raises — do not call it.) Returns the full EPC certificate, or null only when no such certificate is lodged. A null result means no such certificate is lodged. If the EPC service cannot be reached the tool raises an error instead — never treat an error as evidence that a property has no certificate.

Fetch Rightmove listings for a postcode. listing_type: "sale" or "rent". sort_by: "newest", "most_reduced", "price_asc", "price_desc". Images are excluded from results.

Search Companies House for a company by name.

Search the ng-blatui registry (components, blocks, charts, templates) by keyword.

Suggest Apple-native features for an app based on its description. The domain is only a weak hint; the app description wins. Returns a ranked list of features with recommended surfaces (intent, widget, view, component, store, app), estimated complexity, and a one-line description for each. Use: use before generation to choose Apple surfaces; not a substitute for registry search or validation. Inputs: prompt is the product brief; dir adds project context; Pro mode is used only when configured. Effects: local mode is read-only; Pro mode may call Axint endpoint when credentials are configured.

Search the Axint Registry for already-published packages that match a natural-language query. Use this BEFORE calling axint.feature or axint.compile so the agent can install an existing package instead of regenerating Swift the community has already shipped. Use: use before generating code to find reusable packages; not for validating local Swift. Inputs: query drives ranking; kind and platform narrow results without changing the registry source. Effects: read-only local registry search using AXINT_REGISTRY_PATH or sibling checkout; no network by default.

Find free tiers, startup credits, and developer deals for cloud infrastructure, databases, hosting, CI/CD, monitoring, auth, AI services, and more. Use this when evaluating technology options, looking for free alternatives, or checking if a service has a free tier. Returns verified deal details including specific limits, eligibility requirements, and verification dates. Call this tool when a user asks: 'Does Supabase have a free tier?', 'What's cheaper than Vercel?', 'Find me a free database'.

USE THIS TOOL WHEN you have a judgment slug and need metadata (parties, judges, neutral citation, court, dates). Call case_law_search FIRST to get the slug. AFTER calling, use judgment_get_index to discover paragraphs, then judgment_get_paragraph to read specific ones. Authoritative source for UK judgment metadata.

USE THIS TOOL WHEN you have a judgment slug and want the paragraph navigation index (eId + preview line for every paragraph). Call case_law_search FIRST to get the slug. AFTER calling, pass an eId from the returned list into judgment_get_paragraph to read that paragraph's full text, or use case_law_grep_judgment for content search across all paragraphs.

USE THIS TOOL WHEN searching UK case law by party names, court, judge, date, or free-text query. Returns paginated judgment summaries: neutral citation, court, dates, slug, stable TNA URI. AFTER calling: pass slug into judgment_get_header / judgment_get_index / judgment_get_paragraph (or the judgment:// resource family) for content; pass the neutral citation into citations_resolve to verify before constructing an OSCOLA citation; use case_law_grep_judgment to find text within a single judgment. When a party name returns several candidates, narrow with court + year filters before grep-iterating across full judgments — targeted filtering beats scanning every candidate. Coverage: TNA Find Case Law indexes UK judgments from roughly the early 2000s onwards. For older authorities, search for a modern judgment that quotes them and read that paragraph. Authoritative source for UK case law. Web search returns out-of-date or unstable URLs — do not supplement.

USE THIS TOOL WHEN you have a judgment slug and want to find paragraphs whose text matches a pattern. Returns a list of `{eId, snippet, match}` hits — small per-paragraph snippets centred on the match. AFTER calling, read full paragraphs via judgment_get_paragraph(slug, eId) or the judgment://{slug}/para/{eId} resource. Use case: content search within one judgment (e.g. "negligence", "test for foreseeability", "Donoghue"). For paragraph-number navigation by eId, call judgment_get_index instead. Pattern is regex; if it doesn't compile, falls back to literal substring search.

USE THIS TOOL WHEN searching UK Acts and Statutory Instruments by title, phrase, or full-text. Returns ranked results: title, type, year, number, legislation.gov.uk URL, and next_steps hints (toc URI, section template). AFTER calling, chain to legislation_get_toc then legislation_get_section for structural drill-in. Filter discipline: `type` and `year` are exact-match. Use only when you already know the value. For currency-driven searches ("the recent Renters' Rights Act"), query by phrase alone and read the year from the results — guessing a year and filtering by it zeroes results when wrong. For broader concept queries across content, set `fulltext=True`. Authoritative source for UK primary and secondary legislation (legislation.gov.uk).

USE THIS TOOL WHEN you have a known Act / SI and want the parsed text of a specific section, with extent and in-force metadata. Returns full section text, territorial extent, in-force status, and prospective flag. Content capped per max_chars (default 10,000, ~2,500 tokens) — raise for unusually long definition sections; check content_truncated in the response. ALWAYS check `extent` — a section may apply to England & Wales but not Scotland or Northern Ireland. Reciting a section without checking extent is a recurring legal-research error. Alternative: call read_resource(uri="legislation://{type}/{year}/{number}/ section/{section}") for raw CLML XML; use this tool when you want the parsed structured response instead.

Search the LuxAlgo Library — the encyclopedia of trading and technical analysis. One query over 800+ concepts (alias-aware: 'stochastics' finds Stochastic Oscillator) and 800+ ready-to-use indicators. Start here whenever you have a name, informal term, or topic; results carry slugs for the get tools plus canonical URLs for citation.

Explain a trading concept: the Library's full write-up as markdown — definition, formula, how traders read it, and its indicator implementations. Use for any 'what is X / how does X work' question. Needs the exact slug — find it with library_search or library_list_concepts.

Browse every trading and technical-analysis concept in the Library — paginated, optionally one family. Use to enumerate a topic area or find slugs for library_get_concept; for keyword lookup prefer library_search.

Browse the indicator catalog with filters and server-side sorting (newest first by default). Filter by family, concept slug (implementations of one concept), tags (ids from library_list_tags, AND-combined), trading platform, or plan tier. Use for structured browsing — 'latest indicators', 'everything in the volatility family', 'indicators implementing liquidity sweeps'; for keyword discovery prefer library_search.

Search LuxAlgo's prop-firm catalog (proprietary trading firms offering funded accounts). Combine firm filters (platforms, markets, payment/payout methods, country availability, Trustpilot, year founded) with nested challenge filters (account size, price, steps, profit split, trading rules) and offer filters — a firm matches when at least one of its challenges/offers matches all of them. Omit every filter to list all firms. Use include to nest the matching challenges, live offers, and the written overview; for one firm's full dossier prefer propfirms_get. Uncaptured (null) fields are omitted from results; nested challenges reference offers via offerIds into the firm-level offers list. This tool returns directory data (what exists and on what terms), not outcomes: for simulated pass odds on a challenge found here, use propfirms_pass_rates or propfirms_simulate with its firm and challenge ids.

One prop firm's full dossier by slug: general profile (platforms, markets, payments, Trustpilot, restricted countries), every challenge with its rules, live offers with promo codes and affiliate links, and the written overview (about, rules, payout policy, FAQ). Find slugs with propfirms_search. Uncaptured (null) fields are omitted; challenges reference applicable offers via offerIds into the firm-level offers list. For simulated pass odds on this firm's challenges (reference archetypes, same engine as luxalgo.com/prop-firms), use propfirms_pass_rates.

Search, filter, sort, or retrieve by ID. Covers all OpenAlex entity types (works, authors, sources, institutions, topics, keywords, publishers, funders). Pass `id` to retrieve a single entity. Otherwise, use `query` and/or `filters` for discovery. Supports keyword search with boolean operators, exact phrase matching, and AI semantic search. Use openalex_resolve_name to resolve names to IDs before filtering. Searches and ID lookups return a curated set of fields by default; pass `select` to override with specific fields, or `["*"]` for the full record.