Tool search 101,866 tools · 5,225 live servers

Retrieves the interactions between the query proteins. Use this method only when you specifically need to list the interactions between all proteins in your query set. If user asks for 'physical' or 'complex' use 'physical' network type. - For a **single protein**, the network includes that protein and its top 10 most likely interaction partners, plus all interactions among those partners. - For **multiple proteins**, the network includes all direct interactions between them. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". - STRING does not store or report information about self-interactions/homomers; if asked, explain the limitation. If few or no interactions are returned, consider reducing the `required_score`. For large query sets (>50 proteins), consider increasing the `required_score` (e.g. ≥700) to focus on high-confidence interactions and avoid overly dense networks. - Expand the names of score sources: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text-mining)

Retrieves all interaction partners for one or more proteins from STRING. This tool returns all known interactions between your query protein(s) and **any other proteins in the STRING database**. - Use this when asking **“What does TP53 interact with?”** - It differs from the `network` tool, which only shows interactions **within the input set** or a limited extension of it. - If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical". You can filter for strong interactions using `required_score`. - Evidence scores: `nscore` (neighborhood), `fscore` (fusion), `pscore` (phylogenetic profile), `ascore` (coexpression), `escore` (experimental), `dscore` (database), `tscore` (text mining)

Retrieves a URL to a **STRING interaction network image** for one or more proteins. - For a single protein: includes the protein and its top 10 most likely interactors. - For multiple proteins: includes all known interactions **within the query set**. - If the user asks for "physical interactions", "complexes", or "binding", set `network_type` to "physical". The input may include one numeric value per protein, such as fold change, effect size, or score. These values are visualized as colored halos around the nodes, allowing overlay of protein-level measurements on the network. Example: PTEN 2.1 SMO -1.3 If numeric values are provided: - positive values are shown in blue - negative values are shown in red - larger absolute values produce stronger halo intensity If the user provides numeric values together with the proteins, preserve them in the query. If few or no interactions are shown, consider lowering `required_score`. For large queries (>100 proteins): - use `network_flavor="confidence"` - increase `required_score` (e.g. 700) Always ask if the user also wants a link to the interactive STRING network page. Input parameters should match those used in related STRING tools (e.g. `string_interactions_query_set`), unless otherwise specified.

Retrieves a stable URL to an interactive STRING network for one or more proteins. - For a single protein: includes the protein and its top 10 most likely interactors. - For multiple proteins: includes all known interactions **within the query set**. - If the user asks for "physical interactions", "complexes", or "binding", set `network_type` to "physical". The input may include one numeric value per protein, such as fold change, effect size, or score. These values are visualized as colored halos around the nodes, allowing overlay of protein-level measurements on the network. Example: PTEN 2.1 SMO -1.3 If numeric values are provided: - positive values are shown in blue - negative values are shown in red - larger absolute values produce stronger halo intensity If the user provides numeric values together with the proteins, preserve them in the query. If few or no interactions are shown, consider lowering `required_score`. For large queries (>100 proteins): - use `network_flavor="confidence"` - increase `required_score` (e.g. 700) Always display the link as a markdown hyperlink (hide the raw URL). Input parameters should match those used in related STRING tools unless otherwise specified.

Retrieves pairwise protein similarity scores (Smith–Waterman bit scores) for the query proteins. - If no target species (`species_b`) is provided, results are intra-species (within the query species). - To retrieve homologs in other species or clades (e.g. vertebrates, yeast, plants), specify one or more NCBI taxon IDs in `species_b`. - Multiple target species are supported; ask the user to clarify if needed. - Always report species names together with their taxon IDs. - Bit scores < 50 are not reported. - Results are truncated to the top 50 proteins per input protein.

Retrieves direct links to STRING evidence pages for protein–protein interaction pairs. Use this tool only when a STRING evidence page/link is needed. To determine whether an interaction is supported, use `string_interactions_query_set`. It returns URLs linking to STRING’s evidence pages, which display the underlying data sources (experimental results, publications, and curated databases) supporting each predicted interaction. A URL can be generated even for unsupported pairs; the URL is not itself an interaction verdict. Parameters: - **identifier_a**: Query protein identifier (Protein A) - **identifiers_b**: One or more target protein identifiers (Protein B), separated by `%0d` - **species**: NCBI taxonomy ID (e.g. `9606` for human or `10090` for mouse) Typical user questions that should trigger this tool: - "Can you show me the STRING evidence for this interaction?" - "Show me the details supporting this interaction." - "What supports the interaction between TP53 and MDM2?" - "Where can I find the STRING evidence for this pair?"

Analyze a SQL query and return optimization suggestions including index recommendations and query rewrites.

Translate a plain-language question into a candidate SQL query using pattern-matching against the live schema (no AI model — simple questions only: counts, averages, filtered selects on a named table). Returns the SQL without executing it, with a confidence score; low confidence means the table was guessed. Review the statement and tables_used, then run it with scalix_db_query. For complex questions, read scalix_db_schema and write the SQL directly.

Execute a SQL query against the project database. Returns columns, rows, row count, and cost breakdown. Destructive statements (DROP/TRUNCATE/bulk DELETE) require a two-step confirmation: the first call returns code CONFIRMATION_REQUIRED with a confirmation_token — re-call with that value in confirm_token to execute.

Find likely public algae, disease, plant problem and medicine profiles from a symptom query.

Run a read-only SQL query against the application database.

Fetch an additional page of results from a prior paginated query.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

Semantic search INSIDE a fetched record. Pass the text you already pulled (e.g. a SEC 10-K body, an article, a long tool result) plus a natural-language query; get back the top-N passages with character offsets and similarity scores. Use when the record is too big to cram into the prompt — search_within saves context, returns only the passages that matter, and every passage carries an offset so the agent can verify a verbatim quote. Pairs with ask_pipeworx_grounded: fetch with the gateway, ground over the relevant passages instead of the whole document. BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).

Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call. Pass a market slug ("will-bitcoin-hit-150k-by-june-30-2026"), a polymarket.com URL, or a question text. The tool resolves the market, classifies the bet, fans out to category-specific data packs in parallel, and returns an evidence packet + simple market-vs-model comparison. Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z". CLASSIFIERS: crypto_price, fed_rate, geopolitical, sports, sports_championship, drug_approval, election_candidate, tech_launch, space_launch, corporate, corporate_earnings, corporate_event, public_figure_speech, weather, other. FAN-OUT EXAMPLES: BTC bet → coingecko + fred + gdelt+gnews; Fed bet → fred (DFEDTARU + EFFR + CPIAUCSL) + kalshi_macro (KXFED implied probs) + recent_fed_actions (federal-register rules, last 365d); Hormuz bet → imf_portwatch + airspace + gdelt; Yankees WS → mlb_stats_standings + parent_event partition + news; hottest-year bet → climate_projection_nyc + gistemp_latest (NASA global anomaly, rank since 1880) + news; NVDA-vs-AAPL → finnhub get_quote + edgar shares-outstanding (derived market cap) + edgar filings + news. RESPONSE SHAPES: result.market carries best_bid/best_ask/spread_pp/liquidity/price_change_1h/1d/1w; result.analysis carries model_probability/edge_pp/kelly_fraction_half when a closed-form model fires PLUS a 24h-move warning ("Market moved X.Xpp in 24h, comparable to model edge — your edge may already be priced in") when relevant; result.evidence is keyed by source. RESOLVER CONTRACT: result.market_match_confidence ∈ {high, medium, low, none}, market_match_score (0-1 token-overlap), market_match_alternatives[] (other candidate markets the resolver considered), and suggestions[] (explicit re-query hints when the match is fuzzy) — ALWAYS inspect these before trusting the analysis block, because medium/low matches can still surface other fields. PARENT_EVENT EXTRACTOR: when the bet is one leg of a partition (Yankees WS, Romania election), result.parent_event{matched_candidate, top_legs_by_price[], partition_size, placeholders_filtered} gives you the peer prices in one place — that's the headline for elections/championships. NEWS FIELDS: news entries carry _fallback_attempted / _fallback_failed_reason / retry_after_sec when GDELT 429s and GNews backfill ran or failed. SAFETY: low-confidence resolutions short-circuit with status:"low_confidence_match" and suppress analysis fields so agents can't accidentally size on phantom matches. Closed/dead markets that ARE still indexed by Polymarket (yes_price≈0, no volume, no liquidity) return status:"market_closed_or_inactive" and skip fan-out. In practice resolved markets are usually de-indexed and instead surface via the low_confidence_match path above — both routes are BLOCKING, just different mechanisms. Wide-spread markets (>10pp) carry tradeability:"illiquid_wide_spread" + an explanatory note. RESOLUTION-RULE RISK: market.cancellation_rule parses the void/postponement settlement out of the resolution text — refund_50_50 (shares settle flat 50¢ on void; EV-material for any entry away from 50¢, with ev_impact quantified), resolves_no_on_cancel, resolves_yes_on_cancel, carries_to_reschedule, or mentioned_unclear. null means the description never mentions cancellation. Check this before sizing sports/esports/event-occurrence bets — audited arb-bot ledgers show flat-50¢ void settlements are a recurring pure-rules loss.

查看数据文件结构：列名/类型/行数/每列非空数 + 前 N 行预览。免费(0 credit)。 支持 CSV/TSV/JSON/NDJSON/Parquet。取数(data_query)前先调它看清有哪些列、哪些是数值。

查询 / 过滤 / 分组聚合数据文件，返回**实际数据行（JSON）**供 AI 直接分析（1 credit/次）。 支持 CSV/TSV/JSON/NDJSON/Parquet，两种用法： · 原始 SQL（表名固定 t）：sql="SELECT 商品, sum(销量) s FROM t GROUP BY 商品 ORDER BY s DESC LIMIT 5" · 结构化（不用写 SQL）：group_by=["地区"], measures=["销售额"], agg="sum", sort_by="销售额", descending=true, limit=10 SQL 仅允许单条只读 SELECT/WITH，禁止读文件/建表/联网。结果硬上限 1000 行，超出置 truncated=True。失败自动退款。 返回 {ok, format, mode, columns, total_rows, returned_rows, truncated, rows[]}。

两份数据文件按共同列连接（如 订单表×客户表），返回实际数据行 JSON（1 credit/次）。 跨文件对齐是单文件 data_query 做不到的；DuckDB 引擎、锁死文件/网络访问。失败自动退款。

Execute a SQL query against a fresh ephemeral in-memory database built from your schema (and optional seed rows). Returns real rows (max 500, truncation flagged), column names+types, row_count, and dialect notes. Errors come back as structured JSON with type/position/suggestion — a failed query is a useful answer, not a failure of this tool. Example: schema "CREATE TABLE t(id INTEGER, name TEXT);", query "SELECT name FROM t WHERE id=1", seed {"t":[{"id":1,"name":"ada"}]} → rows [["ada"]].

Validate a SQL query against a schema WITHOUT executing it (parse + name/type binding via EXPLAIN). Returns ok with referenced tables, or a structured error: {type: unknown_column|unknown_table|syntax|..., message, position, suggestion}. The suggestion is rule-based (edit distance against your schema). Example: query "SELECT nmae FROM users" → error type unknown_column, suggestion 'did you mean "name"?'.

Return the engine-native query plan for a query (SQLite: EXPLAIN QUERY PLAN) plus full-table-scan warnings. Use it to check whether an index would be used before recommending one. Example: "SELECT * FROM orders WHERE status=?" on an unindexed column → plan ["SCAN orders"], warning about the full scan.

Run up to 10 queries against the same schema+seed. Each query executes in its OWN fresh database — writes in one query are NOT visible to the next (use this for testing variants, not for multi-statement transactions). Returns an array of run_sql results in order.

Answer "do these two queries return the same thing?" — the self-check for query refactors. Executes query_a and query_b against identical fresh databases and compares result multisets (order-insensitive; order divergence reported separately when ORDER BY is present). Returns equal:boolean, row counts, and capped row-level diffs (only_in_a / only_in_b).

List the SQL databases (D1 or Neon Postgres) on my account, including which owned site (if any) each is attached to. Call this BEFORE db_query/db_schema-style work to discover a databaseId — those live on a per-database MCP server reached via GET /api/v1/databases/{id} (see llms.txt), which this id feeds.

Page records from an owned site's collection, newest-first. limit ≤ 200 (default 50). cursor from a previous response's nextCursor.

Mark a hostname as the primary (canonical) URL for its site. Sibling hostnames (apex + www both pointed at the same site) start 301-redirecting to it, preserving path + query. The host-side fix for the duplicate-content SEO problem. The first subdomain you add for a site is primary by default; call this only when you need to switch.

ONE consolidated object: page funnel (views, signups, confirmed, conversion) ⊕ email events (delivered/opened/clicked/bounced) ⊕ a computed verdict. The single place to check progress — never query email separately.

Analyze Postgres SQL/migrations for destructive operations, locking risk, correctness traps (NULL handling that silently returns wrong results), anti-patterns, and query cost. Returns a deterministic verdict (ok/warn/block) with findings. Pass the optional `schema` argument (your CREATE TABLE/INDEX DDL) to also get EXPLAIN-based cost analysis run on a throwaway scratch Postgres — no separate tool or DB connection needed.

Search the iHerb product database using a natural-language query, benefit keyword, ingredient name, or brand name. Uses the PostgreSQL GIN full-text search index first (fast, relevance-ranked), then falls back to a broader ILIKE scan if FTS yields no results.

Execute any valid SQL statement, including data definition language (DDL), data control language (DCL), data query language (DQL), or data manipulation language (DML) statements, on a Cloud SQL instance. To support the `execute_sql` tool, a Cloud SQL instance must meet the following requirements: * The value of `data_api_access` must be set to `ALLOW_DATA_API`. * For built_in users password_secret_version must be set. * Otherwise, for IAM users, for a MySQL instance, the database flag `cloudsql_iam_authentication` must be set to `on`. For a PostgreSQL instance, the database flag `cloudsql.iam_authentication` must be set to `on`. * After you use the `create_instance` tool to create an instance, you can use the `create_user` tool to create an IAM user account for the user currently logged in to the project. The `execute_sql` tool has the following limitations: * If a SQL statement returns a response larger than 10&nbsp;MB, then the response will be truncated. * The `execute_sql` tool has a default timeout of 30 seconds. If a query runs longer than 30 seconds, then the tool returns a `DEADLINE_EXCEEDED` error. * The `execute_sql` tool isn't supported for SQL Server. If you receive errors similar to "IAM authentication is not enabled for the instance", then you can use the `get_instance` tool to check the value of the IAM database authentication flag for the instance. If you receive errors like "The instance doesn't allow using executeSql to access this instance", then you can use `get_instance` tool to check the `data_api_access` setting. When you receive authentication errors: 1. Check if the currently logged-in user account exists as an IAM user on the instance using the `list_users` tool. 2. If the IAM user account doesn't exist, then use the `create_user` tool to create the IAM user account for the logged-in user. 3. If the currently logged in user doesn't have the proper database user roles, then you can use `update_user` tool to grant database roles to the user. For example, `cloudsqlsuperuser` role can provide an IAM user with many required permissions. 4. Check if the currently logged in user has the correct IAM permissions assigned for the project. You can use `gcloud projects get-iam-policy [PROJECT_ID]` command to check if the user has the proper IAM roles or permissions assigned for the project. * The user must have `cloudsql.instance.login` permission to do automatic IAM database authentication. * The user must have `cloudsql.instances.executeSql` permission to execute SQL statements using the `execute_sql` tool or `executeSql` API. * Common IAM roles that contain the required permissions: Cloud SQL Instance User (`roles/cloudsql.instanceUser`) or Cloud SQL Admin (`roles/cloudsql.admin`) When receiving an `ExecuteSqlResponse`, always check the `message` and `status` fields within the response body. A successful HTTP status code doesn't guarantee full success of all SQL statements. The `message` and `status` fields will indicate if there were any partial errors or warnings during SQL statement execution.

Execute any valid read only SQL statement on a Cloud SQL instance. To support the `execute_sql_readonly` tool, a Cloud SQL instance must meet the following requirements: * The value of `data_api_access` must be set to `ALLOW_DATA_API`. * For a MySQL instance, the database flag `cloudsql_iam_authentication` must be set to `on`. For a PostgreSQL instance, the database flag `cloudsql.iam_authentication` must be set to `on`. * An IAM user account or IAM service account (`CLOUD_IAM_USER` or `CLOUD_IAM_SERVICE_ACCOUNT`) is required to call the `execute_sql_readonly` tool. The tool executes the SQL statements using the privileges of the database user logged with IAM database authentication. After you use the `create_instance` tool to create an instance, you can use the `create_user` tool to create an IAM user account for the user currently logged in to the project. The `execute_sql_readonly` tool has the following limitations: * If a SQL statement returns a response larger than 10&nbsp;MB, then the response will be truncated. * The tool has a default timeout of 30 seconds. If a query runs longer than 30 seconds, then the tool returns a `DEADLINE_EXCEEDED` error. * The tool isn't supported for SQL Server. If you receive errors similar to "IAM authentication is not enabled for the instance", then you can use the `get_instance` tool to check the value of the IAM database authentication flag for the instance. If you receive errors like "The instance doesn't allow using executeSql to access this instance", then you can use `get_instance` tool to check the `data_api_access` setting. When you receive authentication errors: 1. Check if the currently logged-in user account exists as an IAM user on the instance using the `list_users` tool. 2. If the IAM user account doesn't exist, then use the `create_user` tool to create the IAM user account for the logged-in user. 3. If the currently logged in user doesn't have the proper database user roles, then you can use `update_user` tool to grant database roles to the user. For example, `cloudsqlsuperuser` role can provide an IAM user with many required permissions. 4. Check if the currently logged in user has the correct IAM permissions assigned for the project. You can use `gcloud projects get-iam-policy [PROJECT_ID]` command to check if the user has the proper IAM roles or permissions assigned for the project. * The user must have `cloudsql.instance.login` permission to do automatic IAM database authentication. * The user must have `cloudsql.instances.executeSql` permission to execute SQL statements using the `execute_sql_readonly` tool or `executeSql` API. * Common IAM roles that contain the required permissions: Cloud SQL Instance User (`roles/cloudsql.instanceUser`) or Cloud SQL Admin (`roles/cloudsql.admin`) When receiving an `ExecuteSqlResponse`, always check the `message` and `status` fields within the response body. A successful HTTP status code doesn't guarantee full success of all SQL statements. The `message` and `status` fields will indicate if there were any partial errors or warnings during SQL statement execution.

Search the Exploit Intelligence Platform for vulnerabilities (CVEs). Returns a list of matching CVEs with CVSS scores, EPSS exploitation probability, exploit counts, CISA KEV status, VulnCheck KEV, InTheWild.io exploitation signals, and ransomware attribution. Supports full-text search, severity/vendor/product/ecosystem/CWE filters, CVSS/EPSS thresholds, plus any_exploited and ransomware filters. When sort is omitted, the API may automatically prefer newest exploitation, exploit, or nuclei-template activity based on the filters you set. Examples: query='apache httpd' with has_exploits=true; vendor='fortinet' with severity='critical' and is_kev=true sorted by epss_desc; any_exploited=true with ransomware=true for ransomware-linked CVEs; cwe='89' with min_cvss=9 for critical SQL injection CVEs.

Browse and filter exploits using STRUCTURED FILTERS ONLY (no free-text query). Use this to filter by source (github, metasploit, exploitdb, nomisec, gitlab, inthewild, vulncheck_xdb, patchapalooza, oscs, poc_monitor), language (python, ruby, etc.), LLM classification (working_poc, trojan, suspicious, scanner, stub, writeup, tool, no_code), author, min stars, code availability, CVE ID, vendor, or product. Also filter by AI analysis: attack_type (RCE, SQLi, XSS, DoS, LPE, auth_bypass, info_leak), complexity (trivial/simple/moderate/complex), reliability (reliable/unreliable/untested/theoretical), requires_auth. NOTE: To search by product name (e.g. 'OpenSSH', 'Apache'), use search_vulnerabilities instead — it has free-text query and get_vulnerability already includes exploits in the response. Examples: source='metasploit' for all Metasploit modules; attack_type='RCE' with reliability='reliable' for weaponizable RCE exploits; cve='CVE-2024-3400' for all exploits targeting a specific CVE; vendor='mitel' for all Mitel exploits.