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

List the open-source AI applications hosted and ready to run at AI NetCafé (ainetcafe.com). Each one normally requires local setup (Docker/Python + your own model API key); here they run pre-configured. Use this to find a tool for a task like translating a PDF with formulas intact, generating a PowerPoint file, polishing an academic paper, or running an autonomous research report. Do not call this first when the request already clearly matches compare_models, translate_pdf, deep_research, or make_slides; call that task tool directly. Example — GET https://ainetcafe.com/t/list_apps

Converts JSON to YAML or YAML to JSON. It works out which one you gave it, so you do not have to say. A parse failure comes back with the parser message instead of silently producing something that looks fine and is not. Use when a config, a CI file, or a Kubernetes manifest needs to be in the other format.

Combines up to 20 CSVs into a single table. Headers do not have to match: columns are unioned and a file missing a column contributes blanks for it, so rows never shift silently — the failure mode that makes hand-merged spreadsheets untrustworthy. Reports each source file row count and checks in code that they sum to the merged total. Use for monthly exports, per-store sheets, or any set of files with the same subject but drifting headers.

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.

Fetch and convert a Microsoft Learn documentation webpage to markdown format. This tool retrieves the latest complete content of Microsoft documentation webpages including Azure, .NET, Microsoft 365, and other Microsoft technologies. ## When to Use This Tool - When search results provide incomplete information or truncated content - When you need complete step-by-step procedures or tutorials - When you need troubleshooting sections, prerequisites, or detailed explanations - When search results reference a specific page that seems highly relevant - For comprehensive guides that require full context ## Usage Pattern Use this tool AFTER microsoft_docs_search when you identify specific high-value pages that need complete content. The search tool gives you an overview; this tool gives you the complete picture. ## URL Requirements - The URL must be a valid HTML documentation webpage from the microsoft.com domain - Binary files (PDF, DOCX, images, etc.) are not supported ## Output Format markdown with headings, code blocks, tables, and links preserved.

Call this first. Returns example prompts that define what a good prompt looks like. Do NOT call plan_create yet. Optional before plan_create: call model_profiles to choose model_profile. Next is a non-tool step: formulate a detailed prompt (typically ~300-800 words; use examples as a baseline, similar structure) and get user approval. Good prompt shape: objective, scope, constraints, timeline, stakeholders, budget/resources, and success criteria. Write the prompt as flowing prose, not structured markdown with headers or bullet lists. Weave technical specs, constraints, and targets naturally into sentences. Include banned words/approaches and governance preferences inline. The examples demonstrate this prose style — match their tone and density. Then call plan_create. PlanExe is not for tiny one-shot outputs like a 5-point checklist; and it does not support selecting only some internal pipeline steps.

Optional helper before plan_create. Returns model_profile options with plain-language guidance and currently available models in each profile. If no models are available, returns error code MODEL_PROFILES_UNAVAILABLE.

Call only after example_prompts and after you have completed prompt drafting/approval (non-tool step). PlanExe turns the approved prompt into a strategic project-plan draft (20+ sections) in ~10-20 min. Sections include: executive summary, interactive Gantt charts, investor pitch, project plan with SMART criteria, strategic decision analysis, scenario comparison, assumptions with expert review, governance structure, SWOT analysis, team role profiles, simulated expert criticism, work breakdown structure, plan review (critical issues, KPIs, financial strategy, automation opportunities), Q&A, premortem with failure scenarios, self-audit checklist, and adversarial premise attacks that argue against the project. The adversarial sections (premortem, self-audit, premise attacks) surface risks and questions the prompter may not have considered. Returns plan_id (UUID); use it for plan_status, plan_stop, plan_retry, and plan_file_info. To track progress, poll plan_status at reasonable intervals (e.g. every 5 minutes). Optionally, run `curl -N <sse_url>` in a background shell as a completion detector — the stream auto-closes on terminal state (completed/failed/stopped). If you lose a plan_id, call plan_list to recover it. If the same prompt + model_profile is submitted by the same user within a short window, the existing plan is returned (with deduplicated=true) instead of creating a new one. If you are unsure which model_profile to choose, call model_profiles first. If your deployment uses credits, include user_api_key to charge the correct account. Common error codes: INVALID_USER_API_KEY, USER_API_KEY_REQUIRED, INSUFFICIENT_CREDITS.

Returns status and progress of the plan currently being created. This is the primary way to check progress — it returns structured JSON with all progress fields. Poll at reasonable intervals (e.g. every 5 minutes): plan generation typically takes 10-20 minutes (baseline profile) and may take longer on higher-quality profiles. State contract: pending/processing => keep polling; completed => download is ready; failed => terminal error; stopped => user called plan_stop (consider plan_resume). progress_percentage is 0-100 (integer-like float); 100 when completed. Note: steps vary in duration — early steps complete quickly while later steps (review, report generation) take longer. Do not use progress_percentage to estimate time remaining. steps_completed and steps_total give the number of plan generation steps completed and expected (both nullable). current_step is the human-readable label of the most recently completed step (e.g. 'SWOT Analysis'). timing.last_progress_at is an ISO 8601 timestamp of the last progress update (null until the first worker update); use it to compute time-since-last-progress and detect stalls — a gap > 10 minutes with no progress change is a strong stall signal. files lists the most recent 10 intermediate outputs produced so far (files_count gives the total); use their updated_at timestamps as a secondary stall signal. When state is 'failed', the response includes an error dict with failure diagnostics: error.failure_reason (category: generation_error, worker_error, inactivity_timeout, internal_error, version_mismatch), error.failed_step (pipeline step active at failure), error.message (human-readable message), and error.recoverable (true => plan_resume may work, false => use plan_retry). The error dict is absent for non-failed states. Unknown plan_id returns error code PLAN_NOT_FOUND. Troubleshooting: pending for >5 minutes likely means queued but not picked up by a worker. processing with timing.last_progress_at unchanged for >10 minutes likely means stalled — call plan_stop then plan_retry. Fall back to file updated_at timestamps if last_progress_at is null. Report these issues to https://github.com/PlanExeOrg/PlanExe/issues .

Retry a plan that is currently in failed or stopped state. Pass the plan_id and optionally model_profile (defaults to baseline). The plan is reset to pending, prior artifacts are cleared, and the same plan_id is requeued for processing. Returns PLAN_NOT_FOUND when plan_id is unknown and PLAN_NOT_FAILED when the plan is not in failed or stopped state.

Resume a failed or stopped plan without discarding completed intermediary files. Plan generation restarts from the first incomplete step, skipping all steps that already produced output files. Use plan_resume when plan_status shows 'failed' or 'stopped' and plan generation was interrupted before completing all steps (network drop, timeout, plan_stop, worker crash). For a full restart or to change model_profile, use plan_retry instead. Only failed or stopped plans can be resumed. Returns PLAN_NOT_FOUND when plan_id is unknown and PLAN_NOT_RESUMABLE when the plan is not in failed or stopped state. Returns PIPELINE_VERSION_MISMATCH when the snapshot was created by a different pipeline version; use plan_retry instead.

Publish a post to the caller's blog. For anything meant to be read later by other people — notes, write-ups, announcements. For a private note to yourself, prefer files or memory

Delete a file you own

Read a stored file back by its id

List the caller's stored files, newest first

Store a file and get a URL for it — a report, a CSV, a transcript

Make a file readable by anyone with its URL, or private again

Upcoming filing/payment deadlines and recurring filing rhythms (monthly VAT, quarterly instalments) for a country or US state, from the OpenAccountants tax calendar. Use it whenever the user asks 'when is X due', mentions a filing date, or when a heads-up about an imminent deadline would help. Signed-in users with a saved home jurisdiction can omit `jurisdiction` — it fills from their profile (the response marks jurisdiction_source accordingly).

Retrieves full documentation content for Svelte 5 or SvelteKit sections. Supports flexible search by title (e.g., "$state", "routing") or file path (e.g., "cli/overview"). Can accept a single section name or an array of sections. Before running this, make sure to analyze the users query, as well as the output from list-sections (which should be called first). Then ask for ALL relevant sections the user might require. For example, if the user asks to build anything interactive, you will need to fetch all relevant runes, and so on. Before calling this tool, try to implement Svelte components using your own knowledge and the `svelte-autofixer` tool, since calling this tool is token intensive.

Lists all available Svelte 5 and SvelteKit documentation sections in a structured format. Each section includes a "use_cases" field that describes WHEN this documentation would be useful. You should carefully analyze the use_cases field to determine which sections are relevant for the user's query. The use_cases contain comma-separated keywords describing project types (e.g., "e-commerce", "blog"), features (e.g., "authentication", "forms"), components (e.g., "slider", "modal"), development stages (e.g., "deployment", "testing"), or "always" for fundamental concepts. Match these use_cases against the user's intent - for example, if building an e-commerce site, fetch sections with use_cases containing "e-commerce", "product listings", "shopping cart", etc. If building a slider, look for "slider", "carousel", "animation", etc. Returns sections as "* title: [section_title], use_cases: [use_cases], path: [file_path]". Always run list-sections FIRST for any Svelte query, then analyze ALL use_cases to identify relevant sections, and finally use get_documentation to fetch ALL relevant sections at once.

Generates a Playground link given a Svelte code snippet. Once you have the final version of the code you want to send to the user, ALWAYS ask the user if it wants a playground link to allow it to quickly check the code in the playground before calling this tool. NEVER use this tool if you have written the component to a file in the user project. The playground accept multiple files so if are importing from other files just include them all at the root level.

Return the Pack-declared hosted skills, ephemeral attachment policy, and user-controlled MCP/API extensions before a run.

Run a Tetrees AI Pack. Before acquisition, Points fund a stateless base preview. Ownership unlocks BYOK, saved growth and download; local files remain request-scoped.

Store a product on the account. Before asking the maker anything, use what you can already see: a README, package metadata, the site's own copy and title, an assets or public folder. A maker working in their product's repository should be able to say 'add my product to SubmitMap' and get a filled-in project back, with questions only about what is genuinely not there. Fill in as much as you can, leave the rest, and come back with update_project. Facts drive what it qualifies for; the pack is what you will paste into forms later. Ask about images early: most platforms want a square logo and many want a cover, and every asset in the pack is two fields, the public address (logoUrl) and the file on the maker's machine (logoFile), because a form uploads the file and only the address can be shown back to them.

Fetch the category-aware copy/install asset for a HeyClaude entry without writing local files. Pass assetType (e.g. 'install_command', 'config_snippet') to return only that asset and avoid the full_content/script payloads when you do not need them.

Files feedback (bug, idea, friction, praise, other) with the COTAL team on behalf of the user. The same log the site's feedback widget writes to. Requires the user's email so the team can follow up.

One player's profile: ranking, country, handedness, date of birth and cached stats.

Career shot-level profile from the Match Charting Project: serve placement (deuce/ad × wide/body/T), return depth and outcomes, net play, clutch break/game/set-point serving, winners and errors by wing, rally-length tendencies — summed over the player's charted matches. COVERAGE IS CURATED (11,646 charted matches back to the 1960s, concentrated on the majors), not full-slate. An ambiguous name returns the candidates to choose from. Requires the ULTRA plan.

Profile data, detect domain, recommend ER strategy

Match two files with intelligent strategy selection

Run GoldenCheck data quality scan on a CSV file. Returns issues found (encoding errors, Unicode problems, format violations) without applying fixes. Requires goldencheck: pip install goldenmatch[quality]

Run GoldenCheck scan and apply fixes to a CSV file. Returns the fixed data summary and a manifest of all fixes applied. Requires goldencheck: pip install goldenmatch[quality]

Run GoldenFlow data transforms on a CSV file. Normalizes phone numbers (E.164), dates (ISO), categorical spelling, and Unicode issues. Returns a manifest of transforms applied. Requires goldenflow: pip install goldenmatch[transform]

Parameter-sensitivity analysis: sweep one or more config parameters across a range and report how stable the clustering is at each value (CCMS unchanged %). Use it to find robust thresholds. Auto-configures the file if no config is given.

Read a future adoption profile without inventing unavailable data.

Create or resume an Assembly, optionally uploading files and waiting for completion.

Compress a PDF to reduce its file size and return a new versioned file. MANDATORY: Before calling this tool, call 'check_upload_status' with the session_id to confirm the file exists and retrieve the latest job_id. Skipping this check and calling compress_pdf directly is FORBIDDEN. Each call creates a NEW job_id (with parent_job_id linking to the source). The original PDF version is preserved unchanged — previous versions remain accessible. After compression completes, call 'view_pdf' with the new job_id to display the result.

Delete one or more pages from a PDF and return a new versioned file. MANDATORY: Before calling this tool, call 'check_upload_status' with the session_id to confirm the file exists and retrieve the latest job_id. Skipping this check and calling delete_pdf_page directly is FORBIDDEN. SAFE AND REVERSIBLE — this tool never destroys anything: It does NOT edit the uploaded file in place. It writes a NEW version under a new job_id (with parent_job_id pointing at the source). The source PDF stays on the server byte-for-byte unchanged and remains viewable and downloadable via its own job_id, so the user can always go back to it. Nothing on the user's device is touched either — the server only ever holds its own copy. Therefore: just do what the user asked. Do NOT refuse, do NOT warn about data loss, and do NOT demand extra confirmation beyond the user's own request — including for 'delete the last page', which is an ordinary, undoable edit. The only real restriction is that at least one page must remain in the document. After deletion completes, call 'view_pdf' with the new job_id to display the result.

Add password protection to an unprotected PDF file. Creates a NEW job_id (with parent_job_id linking to the source). After the operation completes, call 'view_pdf' with the new job_id to display the result. Do NOT call this on an already-protected PDF — use change_password instead.

Change the password of an already-protected PDF file. Creates a NEW job_id (with parent_job_id linking to the source). After the operation completes, call 'view_pdf' with the new job_id to display the result. Do NOT call this on an unprotected PDF — use set_password instead.

Upload a PDF from a ChatGPT file attachment. MANDATORY WORKFLOW — follow EVERY step in order: 1. ALWAYS call check_upload_status FIRST — even if you think the file is new. 2. If a job with the same filename already exists, reuse its job_id — do NOT call upload_pdf. 3. Only call upload_pdf if the file is confirmed absent from check_upload_status. Skipping step 1 and calling upload_pdf directly is FORBIDDEN. Use this when the user provides a file attachment in ChatGPT. The host resolves the attachment and passes it to this tool; the tool then stores the PDF and returns session_id and job_id for use in all subsequent tool calls. Do NOT inspect, construct, or reason about download URLs, file ids, or sandbox paths (e.g. '/mnt/data/...') — just pass the attachment straight through. NEVER invent, guess, or synthesise a download_url or file_id. If you do not have a real attachment handed to you by the host, this is not the right tool. This tool ONLY works on hosts that resolve chat attachments for you (ChatGPT). On every other MCP client — Claude and other connectors — no such attachment exists: call create_upload_page instead to display the upload widget, and let the user pick the file themselves. Likewise, if this tool is unavailable, is blocked, or reports a permission error, do NOT tell the user that uploading is impossible. Fall back to create_upload_page.

Upload multiple PDF files from ChatGPT file attachments. Use this when the user provides multiple file attachments in ChatGPT. Downloads each PDF from its signed URL and stores it. Returns session_id and a list of job_ids. Like upload_pdf, this ONLY works on hosts that resolve chat attachments for you (ChatGPT). On Claude and other MCP clients, call create_upload_page instead. Never invent or guess a download_url or file_id. MANDATORY WORKFLOW before calling this tool: 1. ALWAYS call check_upload_status FIRST — even if you think the files are new. 2. Only include files confirmed absent from check_upload_status. If ALL files are already uploaded, skip batch_upload_pdf entirely and reuse the existing job_ids. 3. Reuse job_ids from already_uploaded — do NOT re-upload those files. Skipping step 1 and calling batch_upload_pdf directly is FORBIDDEN. After batch_upload_pdf completes: if the user requested a comparison, call 'compare_pdfs' with the returned job_ids immediately.

Send text and optional file attachments to a Telegram chat. Supports reply-to (including forum topics and channel discussion groups), parse_mode: classic markdown/html/auto (entities) or rich (Rich Message document; dialect auto-detected). parse_mode=rich cannot be combined with files. File attachments as http(s) URLs, local paths, or data: URIs. When files are provided, the message text becomes a caption. For channel posts with reply_to_id, automatically posts in the linked discussion group. Success: dict with message_id, date, chat, text, status='sent', and sender info (rich messages also set rich=true and rich_format). Error: dict with ok=false and error string. Use send_message to create new messages; use edit_message to modify existing ones. Use send_message_to_phone when targeting a phone number instead of a chat_id. Full documentation: https://github.com/alexeyleshchenko/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

Load profile and metadata for one user, bot, group, or channel. Success: info dict; forum chats may include topics up to topics_limit; user targets may include common_chats up to common_chats_limit. Full documentation: https://github.com/alexeyleshchenko/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

Send to a phone number: may create a temporary contact, then send text or files. Supports parse_mode: classic markdown/html/auto or rich (Rich Message; dialect auto-detected). parse_mode=rich cannot be combined with files. Success: send result plus contact_was_new / contact_removed when applicable. Full documentation: https://github.com/alexeyleshchenko/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

Rasterize a Mermaid source string to PNG. Returns { ok, png_base64 }. Hosted rendering uses resvg-wasm with bundled fonts; bytes may differ from the local napi renderer, so hosted PNG is a convenience surface, not part of the byte-determinism contract. For file/URL artifacts use the local stdio server.

Vaaya's deep reference, FREE and instant. Pass `topic` to get the full playbook for a capability area — exact services, actions, params, prices, model lists, and gotchas — the same reference files the vaaya skill ships. Topics: 'media' (image/video/audio models + product-demo videos), 'gtm' (leads, enrichment, outreach, signals, email), 'research' (OneSearch lanes, deep research, company/market research playbooks), 'data' (scraping, people, social platforms, public records, onchain, compliance), 'compute' (sandboxes, browser automation, files, memory, workers, phone calls, llm). Read the matching topic BEFORE non-trivial work in that area — it is cheaper than a wrong call. Never bills; safe to call any time.

Run a command or code in an open E2B sandbox session (started by `use` with action `create_session`, which returns a `session_id`). Pass `session_id` plus either `command` (a shell command) or `code` (+ optional `language`: python/javascript/bash). Returns stdout/stderr/exit_code (or the code result). The sandbox stays alive — and billed per second of uptime — until you `close` it; re-running reuses the SAME box, so filesystem + process state persist between calls. ALWAYS `close` when done.

Full quality profile for one tool by slug (slugs come from search_skills / get_collection): score breakdown, structural signals, risk level and reasons, platforms, repo link. Direct lookups return any active tool regardless of risk — the risk assessment is part of the answer, not a filter here.

Side-by-side quality profiles for 2–5 tools by slug. Same fields as get_skill; ordering follows the request, not rank.

Export the current WorkPaper JSON document for persistence, review, or handoff to another agent. Does not write files by itself.

Query comprehensive threat profile for an IP: Shodan host data, AbuseIPDB reputation, ASN/geolocation, and open ports. Use for IP investigation and SOC alert triage; for domain data use domain_report. Note: nested asn block always returns at most 50 IPv4/IPv6 prefixes — call asn_lookup with include_full_prefixes=True for the full announced-prefixes list. enrichment.vulns is severity-aware list[VulnInfo] (cve_id + severity + cvss_v3) — Phase 2 v1.16.0 BREAKING; pre-1.16 it was list[str] of CVE IDs. Free: 30/hr (costs 6 tokens), Pro: 500/hr. Returns {ip, enrichment, abuseipdb, shodan, asn, threat_level}.

Query comprehensive IP intelligence: reverse DNS, ASN + holder name + country inline (RIPE Stat, Phase 1), open ports, hostnames, vulnerabilities (Shodan InternetDB enriched with severity + cvss_v3 from local cve.db — Phase 2 v1.16.0 BREAKING; vulns is now list[VulnInfo] {cve_id, severity, cvss_v3} dicts, pre-1.16 it was list[str] of CVE IDs; unknown CVEs emit severity='UNKNOWN' / cvss_v3=null — do NOT infer benign), cloud provider, Tor exit status, and reputation. cloud_provider uses two-tier detection: published cloud CIDR ranges (AWS/GCP/Cloudflare) first, then an ASN-to-provider fallback map for anycast/public-service IPs outside published ranges (e.g. 8.8.8.8 → AS15169 → 'Google'). Reputation: FireHOL level1 blocklist on Free tier; +AbuseIPDB + Shodan on Pro (Phase 4). Use for IP investigation; for orchestrated IP+reputation use threat_report. Response is null-explicit: every field is always present (cloud_provider=null when neither tier matches; tor_exit=false when not listed or upstream fetch failed — check verdict.sources_unavailable to disambiguate fetch failure from genuine absence). Response carries next_calls (conditional) — asn_lookup when ASN is populated, ioc_lookup when reputation is FireHOL-listed or AbuseIPDB confidence>50, threat_report on Pro tier for orchestrated profile. Free: 30/hr, Pro: 500/hr. Returns {ip, ptr, geo, asn, asn_name, country, ports, hostnames, vulns, cloud_provider, tor_exit, reputation, risk_score, verdict, next_calls}.

Query MalwareBazaar for file hash (MD5/SHA1/SHA256): malware family, file type, size, tags, first/last seen, download count. Use to check if file hash is known malware; use ioc_lookup for auto-detection of all IOC types. Companion malware-investigation tools: ioc_lookup (multi-source: ThreatFox + Feodo Tracker + URLhaus), threat_intel (domain-level URLhaus check), exploit_lookup (link a known CVE to PoC code if the hash maps to an exploit binary). Free: 30/hr, Pro: 500/hr. Returns {found, malware_family, file_type, file_size, tags, first_seen, last_seen, signature}.

Check if SHA-1 hash appears in Have I Been Pwned (HIBP) breach dataset using k-anonymity (5-char prefix only, full hash never leaves tool). Use for password breach audits; read-only, no data stored. Companion OSINT investigation tools: hash_lookup (file-hash malware family lookup, different namespace), email_disposable (throwaway-mail signal on associated accounts), username_lookup (social-platform exposure on associated handles). Free: 30/hr, Pro: 500/hr. Returns {found, count}.

Query URLhaus for a specific URL and its host. is_malicious is True only when there is ACTIVE evidence — exact URL match with url_status='online' (or unknown) OR host has urls_online > 0. URLhaus retains historical records forever, so a host can have url_count > 0 with urls_online == 0; in that case is_malicious=False, is_stale=True, threat_level='low'. Use for URL-level threat assessment; use threat_intel for domain-level checks. Companion threat-investigation tools: ioc_lookup (multi-source IOC: ThreatFox + URLhaus + Feodo Tracker, auto-detect type), hash_lookup (file-hash malware family, MalwareBazaar), threat_intel (domain-level URLhaus only). Free: 30/hr, Pro: 500/hr. Returns {url, host, is_malicious, is_stale, urlhaus_host:{found,urls_online,url_count}, urlhaus_url:{found,threat,tags,status}, threat_level, summary}.

List files on a browser session's machine (e.g. downloads), newest first. When a listing is truncated, page on the last entry's modified_at (ISO-8601) and name, passed as modified_before and name_after. Send both: modification times are not unique, and a timestamp alone skips the rest of a tied group.

Read a file from a browser session's machine; returns base64 content and metadata.

Write base64-encoded content to a file on a browser session's machine.

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"}.

Use when the user wants alternatives similar to a known GitHub login. Similarity uses public repository, language, location, and profile signals and is not a suitability judgment. Example: {"login":"sajeetharan","limit":5}.

Use when recency or momentum matters. Lists public score gainers and high-ranking profiles new to impact tracking; do not use as a hiring recommendation. Example: {"days":30,"limit":10}.

The synsets (senses) of the Danish `word`, as JSON-LD entries with @id (e.g. "dn:synset-3047" for get_entity_info), skos:definition, dns:ontologicalType and wn:lexfile. A word with a single synset gives that synset's full JSON-LD as the only entry.

Every sense of the Danish `word` in one call: a list with synset_id, label, definition, lexfile, ontological_types, synonyms (words sharing the synset) and hypernym ({synset_id, label} or null) per synset. Only synsets where the word itself has a sense count, not multi-word expressions containing it.

Start here. Load the signed-in profile, available checks, and recommended workflow for this session.

Refresh the signed-in profile or look up a public profile by wallet or DID.

Per-story diff detail for a build (resolved by commitSha/prNumber/buildId). Returns diff metrics and presigned, time-limited URLs (download them to a file, or link them in a PR comment) for the baseline, candidate, and diff PNGs. Defaults to the changed stories; pass storyId for one specific story. When that storyId is an UNCHANGED story it returns its baseline (diffResultId null, changed false, the baseline URL as both baselineUrl and candidateUrl) - the story rendered identical to baseline. Use render_diff_image instead when you want the actual pixels inline for a vision model, not a URL. When AI review is on, each diff carries the judge's call: aiVerdict (intended|regression), aiConfidence, aiSummary (what changed), aiReasoning, and aiFlagReason; all null when AI review didn't run for it.

Full registry record for one wine: producer, region, appellation, classification, grapes, community rating, the AI tasting profile when the wine has been enriched, and the registry image (url + credit) when one is published — null means the wine has no public picture yet; to see the picture yourself, call get_photo with the wine_id. Vintage-neutral (bottles carry the vintage). Call after search_registry when the user wants depth on a specific wine.

Given a registry wine_id (or, on an authenticated connection, one of the user's bottle_ids), returns wines with the closest taste/style profile from the shared registry, using vector similarity over wine embeddings. Call for "more like this", "what else is like my favourite Barolo", or to seed purchase ideas from a wine the user loves. Only wines that have been embedded are searchable — an empty result does not mean nothing similar exists. Ids must be 24-hex Mongo ids from search_registry or search_bottles — a name or slug is not an id. Returns at most 10.

Generate a cryptographic digest of a value, or verify a value against an expected digest. Set operation to "generate" for a lowercase-hex digest, or "compare" to constant-time-check value against the expected digest — compare is timing-safe and avoids manual string equality checks. Algorithm defaults to sha256; sha512 is also secure, while md5 and sha1 are exposed for checksum and file-integrity compatibility ONLY and must not be used for passwords, signatures, or any security purpose. inputEncoding controls how value and expected are read before hashing (utf8 default, or hex/base64 for raw binary data) so binary blobs need no decode round-trip. The canonical use is matching a download against a vendor-published checksum.

Upload raw HTML as a new landing-page draft (no AI generation). Use to import an exported .html file or hand-written markup (embedded forms, Cal.com embeds, thank-you pages all supported). Then publish_landing_page and attach it to an ad campaign. Creating a new hosted page costs 135 credits (same as create_landing_page); re-uploading to a slug you already own is a free edit. [effect=publish; scope=landing_pages:publish; requires=campaignPublishing; externalMutation=true]

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]

Get Shopify customers with creation and update filters. Call this to size an audience before exporting it; use shopify_get_customer_audience when you need the hashed audience file itself. Paginate with page_info. [effect=read; scope=commerce:read]

Get Klaviyo lists, and optionally segments too. Call this to find the target list id before creating a campaign or syncing profiles, and to size an audience before proposing a send. [effect=read; scope=email:read]

Send a custom event to a Klaviyo profile, such as an ad conversion with a monetary value. Call this to push paid-media conversions into Klaviyo so flows can trigger on them and revenue attribution reconciles. [effect=write; scope=email:write; externalMutation=true]

Add or update profiles on a Klaviyo list from supplied JSON. Call this to sync an audience built elsewhere (a customer export, an ad-platform audience) into a Klaviyo list for lifecycle targeting. [effect=write; scope=email:write; externalMutation=true]