"Understanding and Working with a Huge Codebase" 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

• upsert_note

  OpenAkashic

  Create or overwrite an OpenAkashic markdown note. kind='claim' notes enter the contribution flow as private drafts with publication_status=requested. Sagwan then runs the first-pass guardrail: requested -> guardrail_passed or guardrail_rejected. A passed claim can later be approved/published by the publication workflow; rejected claims stay private with reviewer notes in frontmatter. Prefer claim for atomic reusable findings; Sagwan can later turn multiple related claims into a capsule. kind='capsule' notes stay private until you request publication review. Other kinds (playbook, concept, etc.) remain Closed-only working memory. Writable roots: personal_vault/, doc/, assets/ only. Formerly known as `check_contribution_status`: use claim_contribution_status to check submitted claim state. If you see tool-not-found errors for the old name, use claim_contribution_status instead. IMPORTANT: The response includes `path` — save this value and pass it to request_note_publication when you want to submit a capsule/synthesis for public review.

  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

• 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

• 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

• 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

• 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

• 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

• 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

• map_business_process

  ALM X++ MCP Server

  WHEN: mapping the technical D365 objects behind a business process, or understanding which tables/forms implement a flow. Triggers: 'processus métier', 'Order-to-Cash', 'Procure-to-Pay', 'Record-to-Report', 'business process flow', 'qui est impliqué dans', 'map the process', 'flux du processus', 'quels objets dans le flux'. Map a D365 F&O business process to its complete object chain. For known processes (Order-to-Cash, Procure-to-Pay, Record-to-Report, Plan-to-Produce, Inventory-Management, Hire-to-Retire, Project-Accounting, Asset-Lifecycle): shows every step with forms, tables, classes, entities, reports, and security roles involved. For any other object name: traces all dependencies (tables, classes, forms, entities) from that entry point. Produces a Mermaid process flow diagram. Use 'list' to see all known process mappings. NOT for a single object's FK relations only -- use `find_related_objects` for that (faster and more precise).

  Connector

• restore_context

  Penfield Memory

  Resume work from a saved cognitive context. This provides a narrative briefing to quickly orient you to: - The investigation that was in progress - Key discoveries and insights made - Current hypotheses being tested - Open questions and blockers - Suggested next steps - All relevant memories with their connections The briefing reconstructs the cognitive state, not just the data. You'll understand not just WHAT was discovered, but WHY it matters and HOW the understanding evolved. Example of what you'll receive: "[API Timeout Investigation - Resuming after 2 hours] SITUATION: You were investigating production API timeouts that occur at exactly batch_size=100. This investigation started when user reported timeouts only in production, not staging. PROGRESS MADE: - Identified sharp cutoff at 100 items (not gradual degradation) - Disproved connection pool theory (monitoring showed only 43/200 connections used) - Found root cause: MAX_BATCH_SIZE=100 hardcoded in batch_handler.py:147 - Confirmed staging uses different config override (MAX_BATCH_SIZE=500) EVIDENCE CHAIN: User report → Reproduced locally → Noticed batch_size correlation → Searched codebase for limits → Found MAX_BATCH_SIZE → Checked staging config → Discovered config difference CORRECTED MISUNDERSTANDINGS: - Initially thought it was Redis connection exhaustion (disproven by monitoring) - Assumed gradual performance degradation (actually sharp cutoff) - Thought staging/production were identical (config differs) CURRENT HYPOTHESIS: Production deployment uses default MAX_BATCH_SIZE=100 from code, while staging has environment variable override. Fix requires either code change or prod config update. BLOCKED ON: Need production deployment access to apply fix. User considering whether to change code default or add production environment variable. RECOMMENDED NEXT STEPS: 1. Verify production environment variables (check if MAX_BATCH_SIZE is set) 2. If not set, add MAX_BATCH_SIZE=500 to production config 3. If code change preferred, update default in batch_handler.py 4. Run load test with batch_size=100-500 range to verify fix KEY MEMORIES FOR REFERENCE: - 'Initial timeout report from user' - Starting point of investigation - 'MAX_BATCH_SIZE discovery' - Root cause identification - 'Redis monitoring data' - Evidence disproving connection theory - 'Staging config analysis' - Explanation for environment difference" This cognitive handoff ensures you can continue the work with full understanding of the problem space, previous attempts, and current direction. The narrative preserves not just facts but the reasoning process, mistakes made, and lessons learned. SPECIAL CASE: restore_context("awakening") The name "awakening" is reserved for loading the user's personality configuration. This loads the Awakening Briefing which includes: - Selected persona identity and voice style - Custom personality traits (Premium+ users) - Any quirks and boundaries from the persona preset Args: name: Name or ID of context to restore. Can be: - Context name (exact match, case-sensitive) - Context UUID (from list_contexts output) - "awakening" for personality briefing limit: Maximum number of memories to restore (default 20) ctx: MCP context (automatically provided) Returns: Dict with: - success: Whether restoration succeeded - description: The cognitive handoff briefing - memories: List of relevant memories - context_id: The restored context identifier

  Connector

• search_akashic

  OpenAkashic

  Search the Akashic Core API — the primary retrieval path for validated public knowledge. Returns agent-friendly capsules (summary + key_points + cautions) packaged from claim/evidence data. Use this FIRST for factual/conceptual questions. For your own working notes use search_notes. - mode='compact' → 1-sentence summary per capsule (smallest, best for small models) - mode='standard' → full capsule without metadata (default) - mode='full' → everything including metadata and timestamps - fields=['summary','key_points'] → custom projection overriding mode

  Connector

• code_get_file

  searchcode

  Get code from a remote public git repository — either a specific function/class by name, a line range, or a full file. PREFERRED WORKFLOW: When search results or findings have already identified a specific function, method, or class, use symbol_name to extract just that declaration. This avoids fetching entire files and keeps context focused. Only fetch full files when you need a broad understanding of a file you haven't seen before. For supported languages (Go, Python, TypeScript, JavaScript, Java, C, C++, C#, Kotlin, Swift, Rust) the response includes a symbols list of declarations with line ranges. This is not a first-call tool — use code_analyze or code_search first to identify targets, then extract precisely what you need.

  Connector

• gbif_get_species_classification

  gbif-biodiversity-mcp-server

  Return the complete parent chain for a taxon — from kingdom (or domain) down to the taxon itself — as an ordered array. Each entry has its rank, canonical name, and taxon key. The array is returned root-first (kingdom → phylum → class → … → parent of given taxon). Useful for building taxonomic trees or understanding placement without navigating the backbone level-by-level.

  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

• 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

• 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

• 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

• get_board

  cnvs.app

  Full structured JSON state of a board: texts (id, x, y, content, color, width, postit, author), strokes (id, points, color, author), images (id, x, y, width, height, dataUrl, thumbDataUrl, author; heavy base64 >8 kB elided to dataUrl:null, tiny images inlined). Use this for EXACT ids/coordinates/content (needed for `move`, `erase`, editing a text by id). For visual layout (where is empty space? what overlaps?) call `get_preview` instead — it's much cheaper for spatial reasoning than a huge JSON dump.

  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