"Working with Excel" matching MCP tools:

• rotate_key

  BorealHost

  Atomically rotate an API key. Old key is immediately invalidated. Creates a new key with the same name, scopes, and rate limits. The new key is returned once — store it immediately. Requires: API key with write scope. Args: key_id: UUID of the API key to rotate (get from whoami()) Returns: {"api_key": "bh_...", "key_id": "uuid", "prefix": "bh_...", "scopes": ["read", "write"], "message": "Key rotated. Store securely."} Note: The old key stops working immediately. Update BOREALHOST_API_KEY right away.

  Connector

• notes_save

  dialogbrain

  Save a fact or note into the agent's memory. Use scope to choose visibility: 'workspace' = visible to every agent in this workspace (use for shared facts, project conventions); 'agent' = private to this agent (use for personal working notes); 'thread' = scoped to one conversation (use for thread-specific reminders); 'person' = scoped to one contact (use for per-contact context). If a note with the same key+scope exists it will be updated. Do NOT use this tool for behavioral rules or corrections — use feedback.save for those.

  Connector

• adformula_intelligence

  Heista

  Browse proven ad formula blueprints — structural patterns clustered from 3-10+ winning ads that independently converged on the same beat architecture while Meta kept rewarding them with sustained spend. Takes optional filters: vertical, creative_format (e.g. TALKING_HEAD, UGC, FOUNDER_STORY), marketing_angle, algo_intent, hook_type, and limit (1-10, default 5). Each formula returns: source ad count, average active days (runtime proof), confidence score, 6-layer beat blueprint, per-beat visual direction, marketing angle, psychology mission. Free, read-only, idempotent. Use this when the user asks "what's working in [category]", "show me formulas for talking-head ads", "what scripts work in my vertical", or wants category-level pattern discovery before committing to a single ad. Pass the returned formula id to generate_adscript with source_type="formula" for synthesis. When choosing among results: prioritise (1) avg_active_days as primary proof, (2) marketing_angle alignment with the brand's buyer tension, (3) source_ad_count for cluster robustness, (4) confidence_score as tiebreaker. Do NOT use when the user names a specific ad — decode that ad with decode_ad. Do NOT use for sentence-level transcript fidelity — formulas abstract the structure, not exact copy.

  Connector

• get_framework_docs

  main

  Retrieves authoritative documentation directly from the framework's official repository. ## When to Use **Called during i18n_checklist Steps 1-13.** The checklist tool coordinates when you need framework documentation. Each step will tell you if you need to fetch docs and which sections to read. If you're implementing i18n: Let the checklist guide you. Don't call this independently ## Why This Matters Your training data is a snapshot. Framework APIs evolve. The fetched documentation reflects the current state of the framework the user is actually running. Following official docs ensures you're working with the framework, not against it. ## How to Use **Two-Phase Workflow:** 1. **Discovery** - Call with action="index" to see available sections 2. **Reading** - Call with action="read" and section_id to get full content **Parameters:** - framework: Use the exact value from get_project_context output - version: Use "latest" unless you need version-specific docs - action: "index" or "read" - section_id: Required for action="read", format "fileIndex:headingIndex" (from index) **Example Flow:** ``` // See what's available get_framework_docs(framework="nextjs-app-router", action="index") // Read specific section get_framework_docs(framework="nextjs-app-router", action="read", section_id="0:2") ``` ## What You Get - **Index**: Table of contents with section IDs - **Read**: Full section with explanations and code examples Use these patterns directly in your implementation.

  Connector

• prepare_image_upload

  Avocado AI

  MANDATORY first step whenever the user attached an image in chat (or pointed at a local file on disk) and wants edit_image or image-to-video generation. Returns a signed PUT URL plus a file_id. After this tool: either (a) the inline upload widget will let the user drop the file and auto-continue (Claude.ai web), or (b) you run a curl PUT yourself if you have shell access (Claude Desktop / Claude Code) — the response text contains a ready-to-run curl command. Then call edit_image or generate_video with file_id=<returned id>. edit_image and generate_video do NOT accept base64 — calling them with raw image bytes WILL fail. This tool is the only working path for chat attachments. Set `purpose` to 'edit' or 'video' so the upload widget points the user at the right downstream tool.

  Connector

• licium_discover

  Licium

  Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success rates - Compare: "agents for code review" → ranked by reputation, shows pricing - Check status: "is resend-mcp working?" → health check on specific tool/agent - Find alternatives: "alternatives to X that failed" → backup options WHEN TO USE: When you want to browse, compare, or check before executing. If you just want results, use licium instead.

  Connector

• pictify_delete_template

  mcp

  Permanently delete a template. This action cannot be undone. WARNING: Any batch jobs, experiments, or bindings using this template will stop working.

  Connector

• send

  RogerThat

  Send a message to another agent on the channel you joined, or to 'all' to broadcast. Requires a prior join() in this session. The 'to' field accepts: a callsign ('front'), an index ('#1' or '1') from roster(), or 'all'. If omitted, defaults to 'all' (broadcast — walkie-talkie default). Optional `priority` tags urgency (min|low|default|high|urgent). Optional `suggested_replies` hints up to 4 canned replies that human-in-the-loop UIs (like the /remote phone view) render as tappable chips — agent receivers can read them too and pick one. Optional `attachments` carries up to 4 small inline files (≤512KB base64 total) — designed for sporadic screenshots / PDFs; bigger files should be hosted externally and pasted as a URL. Optional `kind`: set 'status' to send an ephemeral 'working on it' signal instead of a normal message (see the `kind` field).

  Connector

• find_examples

  Senzing

  Find working SOURCE CODE examples from 37 indexed Senzing GitHub repositories. REQUIRED: either `query` (string, for search) or `repo` with `file_path` or `list_files=true` — the call WILL FAIL without one. Three modes: (1) Search: pass `query` to find examples across all repos, (2) File listing: pass `repo` + `list_files=true`, (3) File retrieval: pass `repo` + `file_path`. Indexes source code (.py, .java, .cs, .rs) and READMEs — NOT build/data files. For sample data, use get_sample_data. Covers Python, Java, C#, Rust SDK patterns: initialization, ingestion, search, redo, configuration, message queues, REST APIs. Use max_lines to limit large files. Returns GitHub raw URLs for file retrieval.

  Connector

• atlas_list_reports

  CareerProof MCP

  List all generated reports with status and summary info. Returns an array of report objects with id, report_type, status, title, and summary. Use the report id with atlas_get_report for details or atlas_download_report to download completed PDFs. Free.

  Connector

• get_cache_stats

  dannet

  Return statistics about the session-scoped resource cache. Useful for verifying that caching is working: call get_synset_info (or similar) twice for the same ID and check that cache_size grows by 1 on the first call but not on the second, and that cached_keys contains the expected IDs. Returns: Dict with: - cache_size: Total number of cached entries - cached_keys: List of (base_url, resource_id) pairs currently cached

  Connector

• financial_model_3statement

  mcp-knowledge

  Pure-compute 3-statement financial model builder (Income Statement + Balance Sheet + Cash Flow). Feed assumptions (revenue growth, COGS%, OpEx, CapEx, working capital, tax rate, depreciation, debt schedule) → receive a full 3-5 year projection with integrated DCF valuation. Supports IFRS / US_GAAP / PRC_GAAP (中国会计准则) norms with bilingual ZH+EN labels for PRC. Modes: build (full 3-statement model) | scenario_analysis (base/bull/bear ±20% growth) | sensitivity (1 KPI × 1 input, 5-point grid). No external data needed — all computed from assumptions. ICP: VC due diligence, M&A analysts, CFO SMB, startup founders pitching investors, biotech/SaaS modeling. Returns balance_check_ok per year, DCF enterprise/equity value, and coherence warnings.

  Connector

• whensport_tdf_getRacePhase

  tour-de-france-2026

  Get current Tour de France race phase. Returns one of: 'pre' (before the first stage, with nextStage + daysUntil), 'live' (a stage is currently running, with currentStage + elapsedPct), 'rest-day' (rest day between stages, with restDay + nextStage), 'between-stages' (off-day between consecutive stages, with lastStage + nextStage), 'finished' (race over, with finalStage).

  Connector

• get_entity_info

  dannet

  Get comprehensive RDF data for any entity in the DanNet database. Supports both DanNet entities and external vocabulary entities loaded into the triplestore from various schemas and datasets. UNDERSTANDING THE DATA MODEL: The DanNet database contains entities from multiple sources: - DanNet entities (namespace="dn"): synsets, words, senses, and other resources - External entities (other namespaces): OntoLex vocabulary, Inter-Lingual Index, etc. All entities follow RDF patterns with namespace prefixes for properties and relationships. NAVIGATION TIPS: - DanNet synsets have rich semantic relationships (wn:hypernym, wn:hyponym, etc.) - External entities provide vocabulary definitions and cross-references - Use parse_resource_id() on URI references to get clean IDs - Check @type to understand what kind of entity you're working with Args: identifier: Entity identifier (e.g., "synset-3047", "word-11021628", "LexicalConcept", "i76470") namespace: Namespace for the entity (default: "dn" for DanNet entities) - "dn": DanNet entities via /dannet/data/ endpoint - Other values: External entities via /dannet/external/{namespace}/ endpoint - Common external namespaces: "ontolex", "ili", "wn", "lexinfo", etc. Returns: Dict containing JSON-LD format with: - @context → namespace mappings (if applicable) - @id → entity identifier - @type → entity type - All RDF properties with namespace prefixes (e.g., wn:hypernym, ontolex:evokes) - For DanNet synsets: dns:ontologicalType and dns:sentiment (if applicable) - Entity-specific convenience fields (synset_id, resource_id, etc.) Examples: # DanNet entities get_entity_info("synset-3047") # DanNet synset get_entity_info("word-11021628") # DanNet word get_entity_info("sense-21033604") # DanNet sense # External vocabulary entities get_entity_info("LexicalConcept", namespace="ontolex") # OntoLex class definition get_entity_info("i76470", namespace="ili") # Inter-Lingual Index entry get_entity_info("noun", namespace="lexinfo") # Lexinfo part-of-speech

  Connector

• revoke_api_key

  BorealHost

  Revoke (deactivate) an API key. The key stops working immediately. Requires: API key with write scope. Args: key_id: UUID of the key to revoke (from list_api_keys or whoami) Returns: {"success": true, "message": "API key revoked"} Errors: NOT_FOUND: Key not found or already revoked

  Connector

• licium_discover

  Licium

  Browse and compare Licium's agents and tools. Use this when you want to SEE what's available before executing. WHAT YOU CAN DO: - Search tools: "email sending MCP servers" → finds matching tools with reputation scores - Search agents: "FDA analysis agents" → finds specialist agents with success rates - Compare: "agents for code review" → ranked by reputation, shows pricing - Check status: "is resend-mcp working?" → health check on specific tool/agent - Find alternatives: "alternatives to X that failed" → backup options WHEN TO USE: When you want to browse, compare, or check before executing. If you just want results, use licium instead.

  Connector

• share_finding

  redm-mcp

  Share a verified finding back to the docs corpus so the next agent can find it. Use AFTER solving a non-trivial problem to record what would have saved you time: a gotcha, a working parameter combo, an undocumented constraint, a relationship between two natives that isn't obvious. Other agents will find this via `semantic_search` (findings are merged into default results; `category: 'learnings'` returns only findings). WHEN to use: - You burned multiple iterations on something not in the docs. - You discovered an undocumented quirk (param order, hash collision, framework export that isn't in `vorp`/`rsgcore`). - You verified that a specific combination works (e.g. native A + flag B for behavior C). WHEN NOT to use: - The information is already in the docs (verify with `semantic_search`/`grep_docs` first). - You're guessing — only contribute verified findings. - It's project-specific (your repo's auth flow, your DB schema). Keep it general to RedM/RDR3. Keep `title` short and searchable. `body` should explain WHY, not just WHAT — context, the trap, the fix.

  Connector

• list_rows

  Dock

  List rows in a workspace's table surface. Returns rows with their data (a JSON object of column-name to value), creation time, the principal who created/updated each row, AND the row's `surface_slug` (the sheet it lives on). Empty array if no rows have been added yet. Multi-surface workspaces: pass `surface_slug` to scope to one sheet; omit to return rows from every surface in the workspace (back-compat: pre-multi-surface clients keep working).

  Connector

• openstates_search_committees

  openstates-mcp-server

  List committees for a jurisdiction. Experimental — Open States is actively working to restore committee support and not all states have data. Use chamber to scope to upper (senate) or lower (house) committees. Use classification=subcommittee to find subcommittees of a parent. Use include=memberships to get the full roster with member roles. The coverage_note field in the output will always note the experimental coverage limitations.

  Connector

• youfiliate_delete_smart_link

  Youfiliate Smart Links

  Delete a smart link permanently. The short URL will stop working. IMPORTANT: Always confirm with the user before executing this action. The `confirm` parameter must be set to true. This is a destructive action that cannot be undone — the slug becomes available for reuse after a cooldown period. Does NOT affect other links or YouTube descriptions. Common errors: - Smart link not found: check the ID. - confirm=False: you must set confirm=True after getting user confirmation.

  Connector