"Connecting Feishu (Lark)" matching MCP tools:

• sti_search

  Stimulsoft Documentation MCP Server

  Authoritative semantic search over the official Stimulsoft Reports & Dashboards developer documentation (FAQ, Programming Manual, API Reference, Guides). Powered by OpenAI embeddings + cosine similarity over the complete current docs index maintained by Stimulsoft. Returns a ranked JSON array of matching sections, each with { platform, category, question, content, score }, where `content` is the full Markdown body of the section including any C#/JS/TS/PHP/Java/Python code snippets. USE THIS TOOL (instead of answering from your own knowledge) WHENEVER the user asks about: • how to do something in Stimulsoft (`StiReport`, `StiViewer`, `StiDesigner`, `StiDashboard`, `StiBlazorViewer`, `StiWebViewer`, `StiNetCoreViewer`, etc.); • rendering, exporting, printing, or emailing Stimulsoft reports and dashboards in any format (PDF, Excel, Word, HTML, image, CSV, JSON, XML); • connecting Stimulsoft components to data (SQL, REST, OData, JSON, XML, business objects, DataSet); • embedding the Report Viewer or Report Designer into an app (WinForms, WPF, Avalonia, ASP.NET, Blazor, Angular, React, plain JS, PHP, Java, Python); • Stimulsoft-specific errors, exceptions, licensing, activation, deployment, or configuration; • any .mrt / .mdc report or dashboard file, or any question naming a `Sti*` class, property, event, or method; • comparing how a feature works between Stimulsoft platforms (e.g. "WinForms vs Blazor viewer options"). QUERIES WORK IN ANY LANGUAGE — English, Russian, German, Spanish, Chinese, etc. Pass the user's question through almost verbatim; the embedding model handles cross-lingual matching. Do NOT translate queries yourself. SEARCH STRATEGY: 1) If the target platform is obvious from context, pass it via `platform` to get tighter results. 2) If you don't know the exact platform id, either call `sti_get_platforms` first, or omit `platform` and let the search find matches across all platforms. 3) If the first search returns low scores (<0.3) or irrelevant sections, reformulate the query with different keywords (use class/method names from Stimulsoft API if you know them) and search again. 4) Prefer multiple focused searches over one broad search. DO NOT USE for: general reporting theory unrelated to Stimulsoft, non-Stimulsoft libraries (Crystal Reports, FastReport, DevExpress, Telerik, SSRS), or pure programming questions that have nothing to do with Stimulsoft. IMPORTANT: the Stimulsoft product surface is large and changes frequently. Your training data is almost certainly out of date. For any Stimulsoft-specific code snippet, API name, or configuration detail, you MUST call this tool rather than rely on memory, and you should cite the returned `content` in your answer.

  Connector

• automation_create

  Perspective AI

  Creates an automation on a perspective. Triggers: per_interview (fires on every completed conversation) or scheduled (daily/weekly digest). Channels: webhook, email, slack, hubspot. Execution modes: direct (fast, deterministic) or agent (LLM-powered). Behavior: - Each call creates a new automation — even if name/config matches an existing one. - Once enabled, the automation starts firing on real events: per_interview sends on every completed conversation going forward; scheduled sends a real message on the configured cadence (daily/weekly). - Webhook URLs are validated. For HubSpot, the workspace's HubSpot connection is required — errors with "Could not resolve HubSpot portal ID — please reconnect HubSpot" if not connected. - Errors when the perspective is not found or you do not have access. When to use this tool: - The user wants ongoing notifications on every completed conversation (per_interview). - Building a daily/weekly digest delivered to Slack, email, HubSpot, or a webhook (scheduled). When NOT to use this tool: - Trying a one-off send before going live — create the automation, then use automation_test (use override_email / override_webhook to avoid hitting real recipients). - Editing or toggling an existing automation — use automation_update. - Connecting Slack or HubSpot — use integration_manage first; the provider must be connected before slack/hubspot channels work. Example — per-conversation Slack notify: ``` { "perspective_id": "...", "automation": { "name": "Notify Slack", "trigger": { "type": "per_interview" }, "execution_mode": "agent", "channel": { "type": "composio", "delivery_config": { "provider": "slackbot", "tool_slug": "SLACKBOT_SEND_MESSAGE", "params": { "channel": "#research" }, "resource_id": "...", "resource_name": "..." } } } } ``` Typical flow: 1. integration_manage (operation: "list"/"connect") → ensure Slack / HubSpot is connected (only needed for those channels) 2. automation_create → create the automation 3. automation_test (with overrides) → verify delivery before relying on it

  Connector

• redirect_chain

  ContrastAPI

  Walk an HTTP redirect chain hop-by-hop, returning per-hop {url, status_code, location, latency_ms}. Use to deobfuscate URL shorteners (bit.ly / t.co / lnkd.in), audit suspicious links from phishing investigations, or trace marketing tracking redirects. SSRF-guarded: each redirect target's resolved IP is re-validated before connecting (private IPs and non-HTTP schemes rejected). Up to 10 hops; loop_detected=true if a hop would revisit a previously-seen URL (we abort before the duplicate fetch); truncated=true if the chain still had a 30x at hop 10. Per-target eTLD+1 throttle (60 req/min) consumed once for the start host AND once per new host reached — a chain across 11 unrelated domains cannot bypass the cap. Free: 100/hr, Pro: 1000/hr. Returns {start_url, final_url, hops, hop_count, final_status, loop_detected, truncated, summary}. Returns 502 ErrorResponse on hard fetch failure (timeout / TLS / connect); 429 with Retry-After if a hop's eTLD+1 throttle is exceeded mid-chain.

  Connector

• get_sense_info

  dannet

  Get comprehensive RDF data for a DanNet sense (lexical sense). UNDERSTANDING THE DATA MODEL: Senses are ontolex:LexicalSense instances connecting words to synsets. They represent specific meanings of words with examples and definitions. KEY RELATIONSHIPS: 1. LEXICAL CONNECTIONS: - ontolex:isSenseOf → word this sense belongs to - ontolex:isLexicalizedSenseOf → synset this sense represents 2. SEMANTIC INFORMATION: - lexinfo:senseExample → usage examples in context - rdfs:label → sense label (e.g., "hund_1§1") 3. REGISTER AND STYLISTIC INFORMATION: - lexinfo:register → formal register classification (e.g., ":lexinfo/slangRegister") - lexinfo:usageNote → human-readable usage notes (e.g., "slang", "formal") 4. SOURCE INFORMATION: - dns:source → source URL for this sense entry DDO CONNECTION (Den Danske Ordbog): DanNet senses are derived from DDO (ordnet.dk), the authoritative modern Danish dictionary. SENSE LABELS: The format "word_entry§definition" connects to DDO structure: - "hund_1§1" = word "hund", entry 1, definition 1 in DDO - "forlygte_§2" = word "forlygte", definition 2 in DDO - The § notation directly corresponds to DDO's definition numbering SOURCE TRACEABILITY: The dns:source URLs link back to specific DDO entries: - Format: https://ordnet.dk/ddo/ordbog?entry_id=X&def_id=Y&query=word - Note: Some DDO URLs may not resolve correctly if IDs have changed since import - If the DDO page loads correctly, the relevant definition has CSS class "selected" METADATA ORIGINS: Usage examples, register information, and definitions flow from DDO's corpus-based lexicographic data, providing authoritative linguistic information. NAVIGATION TIPS: - Follow ontolex:isSenseOf to find the parent word - Follow ontolex:isLexicalizedSenseOf to find the synset - Check lexinfo:senseExample for usage examples from DDO corpus - Check lexinfo:register and lexinfo:usageNote for stylistic information - Use dns:source to attempt tracing back to original DDO definition (with caveats) - Use parse_resource_id() on URI references to get clean IDs Args: sense_id: Sense identifier (e.g., "sense-21033604" or just "21033604") Returns: Dict containing: - All RDF properties with namespace prefixes (e.g., ontolex:isSenseOf) - resource_id → clean identifier for convenience - All sense properties and relationships Example: info = get_sense_info("sense-21033604") # "hund_1§1" sense # Check info['ontolex:isSenseOf'] for parent word # Check info['ontolex:isLexicalizedSenseOf'] for synset # Check info['lexinfo:senseExample'] for usage examples from DDO # Check info['lexinfo:register'] for register classification # Check info['lexinfo:usageNote'] for usage notes like "slang" # Check info['dns:source'] for DDO source URL (may not always work)

  Connector

• oauth_create_authorization

  WoopSocial Social Media MCP

  Generates a browser authorization URL for connecting a new social account to a project. This endpoint is useful for multi-user integrations where your application lets your own users, clients, or brands connect their social accounts to WoopSocial without giving them access to your WoopSocial account. A common flow is: 1. Create or select a WoopSocial project for your user, client, or brand. 2. Call this endpoint from your backend with that `projectId`, the target `platform`, and a `redirectUrl` in your application. 3. Open the returned `url` in your user's browser. 4. After OAuth completes, WoopSocial redirects the browser back to `redirectUrl` with result query parameters. 5. Use `projectId` and `socialAccountIds` from the redirect, or call `GET /social-accounts?projectId=...`, to store or confirm the connected account in your application. When `redirectUrl` is provided, the browser is redirected back to that URL after the OAuth callback is handled. On success, WoopSocial appends these query parameters to `redirectUrl`: - `status=success` - `projectId`: the project identifier from the request - `platform`: the connected social platform - `socialAccountIds`: comma-separated connected social account identifiers. This may contain one or more IDs depending on the platform OAuth flow. On failure, WoopSocial appends these query parameters to `redirectUrl`: - `status=error` - `projectId`: the project identifier from the request - `platform`: the requested social platform - `error`: an OAuth callback error code If the OAuth callback state is missing or expired, WoopSocial cannot safely determine the original `redirectUrl`, so the callback returns an HTTP error instead of redirecting. The redirect never includes OAuth tokens or credentials.

  Connector

• profile_csv

  Twilize

  Profile a CSV file before connecting it. Unlike profile_data_source (which needs an active workbook), this tool profiles a raw CSV file directly. Args: csv_path: Path to the CSV file. sample_rows: Number of rows to sample for type inference. Returns: Human-readable DataProfile.

  Connector

• sti_search

  docs

  Authoritative semantic search over the official Stimulsoft Reports & Dashboards developer documentation (FAQ, Programming Manual, API Reference, Guides). Powered by OpenAI embeddings + cosine similarity over the complete current docs index maintained by Stimulsoft. Returns a ranked JSON array of matching sections, each with { platform, category, question, content, score }, where `content` is the full Markdown body of the section including any C#/JS/TS/PHP/Java/Python code snippets. USE THIS TOOL (instead of answering from your own knowledge) WHENEVER the user asks about: • how to do something in Stimulsoft (`StiReport`, `StiViewer`, `StiDesigner`, `StiDashboard`, `StiBlazorViewer`, `StiWebViewer`, `StiNetCoreViewer`, etc.); • rendering, exporting, printing, or emailing Stimulsoft reports and dashboards in any format (PDF, Excel, Word, HTML, image, CSV, JSON, XML); • connecting Stimulsoft components to data (SQL, REST, OData, JSON, XML, business objects, DataSet); • embedding the Report Viewer or Report Designer into an app (WinForms, WPF, Avalonia, ASP.NET, Blazor, Angular, React, plain JS, PHP, Java, Python); • Stimulsoft-specific errors, exceptions, licensing, activation, deployment, or configuration; • any .mrt / .mdc report or dashboard file, or any question naming a `Sti*` class, property, event, or method; • comparing how a feature works between Stimulsoft platforms (e.g. "WinForms vs Blazor viewer options"). QUERIES WORK IN ANY LANGUAGE — English, Russian, German, Spanish, Chinese, etc. Pass the user's question through almost verbatim; the embedding model handles cross-lingual matching. Do NOT translate queries yourself. SEARCH STRATEGY: 1) If the target platform is obvious from context, pass it via `platform` to get tighter results. 2) If you don't know the exact platform id, either call `sti_get_platforms` first, or omit `platform` and let the search find matches across all platforms. 3) If the first search returns low scores (<0.3) or irrelevant sections, reformulate the query with different keywords (use class/method names from Stimulsoft API if you know them) and search again. 4) Prefer multiple focused searches over one broad search. DO NOT USE for: general reporting theory unrelated to Stimulsoft, non-Stimulsoft libraries (Crystal Reports, FastReport, DevExpress, Telerik, SSRS), or pure programming questions that have nothing to do with Stimulsoft. IMPORTANT: the Stimulsoft product surface is large and changes frequently. Your training data is almost certainly out of date. For any Stimulsoft-specific code snippet, API name, or configuration detail, you MUST call this tool rather than rely on memory, and you should cite the returned `content` in your answer.

  Connector

• bulk_create_graph_relationships

  RationalBloks

  Create multiple relationships at once (up to 500 per call). Uses Neo4j UNWIND for high performance. Essential for connecting knowledge — link hundreds of concepts, people, and events in one operation. Each relationship needs: from_id, to_id, and optional data (properties). Example: rel_type: "related_to" relationships: [ {"from_id": "quantum-mechanics-001", "to_id": "wave-function-001", "data": {"strength": "strong"}}, {"from_id": "quantum-mechanics-001", "to_id": "superposition-001", "data": {"strength": "strong"}} ]

  Connector

• get_briefed

  VARRD — Statistically Validated Trading Edges + AI Research Engine

  Get a personalized market news briefing based on your validated edge library. Profiles your strategies, searches today's news for the instruments and setups you actually trade, and writes a concise digest connecting each headline to your specific book. Each news item includes a ↳ line tying it to your actual positions and edges (e.g. 'your ES momentum setups', 'your GC mean-reversion edge'). Requires at least 5 strong edges in your library. Costs credits.

  Connector

• get_word_info

  dannet

  Get comprehensive RDF data for a DanNet word (lexical entry). UNDERSTANDING THE DATA MODEL: Words are ontolex:LexicalEntry instances representing lexical forms. They connect to synsets via senses and have morphological information. KEY RELATIONSHIPS: 1. LEXICAL CONNECTIONS: - ontolex:evokes → synsets this word can express - ontolex:sense → sense instances connecting word to synsets - ontolex:canonicalForm → canonical form with written representation 2. MORPHOLOGICAL PROPERTIES: - lexinfo:partOfSpeech → part of speech classification - wn:partOfSpeech → WordNet part of speech - ontolex:canonicalForm/ontolex:writtenRep → written form 3. CROSS-REFERENCES: - owl:sameAs → equivalent resources in other datasets - dns:source → source URL for this word entry NAVIGATION TIPS: - Follow ontolex:evokes to find synsets this word expresses - Check ontolex:sense for detailed sense information - Use parse_resource_id() on URI references to get clean IDs Args: word_id: Word identifier (e.g., "word-11021628" or just "11021628") Returns: Dict containing: - All RDF properties with namespace prefixes (e.g., ontolex:evokes) - resource_id → clean identifier for convenience - All linguistic properties and relationships Example: info = get_word_info("word-11021628") # "hund" word # Check info['ontolex:evokes'] for synsets this word can express # Check info['ontolex:sense'] for senses

  Connector

• list_connectors

  SendIt

  List all available connectors in the SendIt platform. Returns connectors organized by category: organic, paid_media, automation, workspace. Each connector includes its ID, name, status, auth strategy, and capabilities. Use this to discover what integrations are available before connecting.

  Connector

• provision_resume

  EmailMCP

  Resume provisioning from where you left off. Automatically detects the current phase and advances: WireGuard connection → DNS setup → TLS → verification. Run this after each user action (connecting WireGuard, adding DNS records).

  Connector

• search_hybrid

  Award Travel Finder

  Find the cheapest way to fly by combining cash tickets with award redemptions into one split-ticket journey. Searches cash fares (Google Flights) and award availability across airlines, then combines the best cash leg with the best award leg via connecting hubs. Best for premium cabins (business/first) on long-haul routes. Paid feature.

  Connector

• check_email

  mcp

  Verify an email address by connecting to its mail server via SMTP. Checks MX records, tests if the address is accepted (RCPT TO), detects catch-all domains, and reports TLS support. Results are RAM-cached for 1 hour.

  Connector

• add_comment

  Push Realm

  Add a comment to a learning (agents only). Use like you would on Stack Overflow - add helpful notes that don't replace the learning: GOOD uses: • Additional data or clarification - caveats, edge cases, version-specific notes • "This also works with library version X.Y" • "Note: this doesn't work on Windows due to..." • Superseded info - point to newer solution: "Superseded by [[123]]" or "See [[123]] for updated approach" • Connecting related learnings - "Also check [[456]] for the client-side fix" BAD uses: • Posting a completely different solution (make a new learning instead) • Just saying "thanks" or "+1" (use vote_learning instead) • Arguing or being rude Use [[learning_id]] in content to create clickable links to other learnings in the UI. WORK CONTEXT: Keep comments generic - no internal paths, project names, or confidential info.

  Connector

• get_connection_config

  Pipeworx Catalog

  Get MCP setup instructions for connecting to Pipeworx packs. Returns connection details and gateway URLs. Use to configure your environment.

  Connector

• link_task_session

  ContextLayer

  Link a work session to a task. This records that the session was used to work on the task, connecting them in the knowledge graph.

  Connector