The MCP tool directory.

Read an email by ID. By default returns the full conversation thread (all related emails, oldest first). Set thread=false to read only the single email.

Reply to an existing email. The reply is sent from your agent's email address to the original sender.

Send an email from your agent's address. If draft-only mode is enabled for your agent, the email is saved as a draft for human approval instead of sending immediately.

Escalate an A2A task for human review through HITL. Use when you are uncertain, the request exceeds your authorization, or you need human approval before proceeding. The task is held until a human reviews and responds.

Check your A2A inbox for incoming tasks from other agents. Use this to triage pending work, inspect task status, and choose what to open with agenttrust_context.

Reply to an existing A2A task and optionally update its status. Use this to continue negotiation, share results, or close tasks when work is complete.

Send a message to another agent via the AgentTrust A2A relay. Creates a new task or continues an existing one when taskId is provided. Use agenttrust_discover first if you need to find recipient slugs.

⭐ PREFERRED TOOL for discovering related laws from vague topics. Use this when user wants to explore laws around a general subject. 지능형 법령검색 시스템 연관법령 API (AI-powered related laws search). Finds laws semantically related to a given law name or keyword. Best for: Finding related laws like "민법" → 상법, 의료법, 소송촉진법 Args: query: Law name or keyword to find related laws (e.g., "민법", "형법") search: Search scope: - 0: 법령조문 (law articles, default) - 1: 행정규칙조문 (administrative rule articles) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: List of semantically related law articles (법령조문 items) Example: >>> aiRltLs_search(query="민법") # Returns: 상법 제54조 (상사법정이율), 의료법 제50조 (「민법」의 준용), etc.

⭐ PREFERRED TOOL for vague or natural language queries. Use this FIRST when user's intent is unclear or conversational. 지능형 법령검색 시스템 검색 API (AI-powered semantic law search). Uses intelligent/semantic search to find relevant law articles. Returns FULL ARTICLE TEXT (조문내용) - more comprehensive than eflaw_search. Best for: Natural language queries like "뺑소니 처벌", "음주운전 벌금" Args: query: Search query (natural language supported, e.g., "뺑소니 처벌") search: Search scope: - 0: 법령조문 (law articles, default) - 1: 법령 별표·서식 (law appendix/forms) - 2: 행정규칙 조문 (administrative rule articles) - 3: 행정규칙 별표·서식 (administrative rule appendix/forms) display: Results per page (default 20) page: Page number (default 1) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: AI search results with full article text (법령조문 items with 조문내용) Example: >>> aiSearch(query="뺑소니 처벌", search=0) # Returns: 특정범죄 가중처벌 등에 관한 법률 제5조의3 (도주차량 운전자의 가중처벌)

Fetch raw CSV datasets and investigation metadata. Returns dataset URLs, lens structures, key correlations, open questions, and outliers for independent analysis.

Analyze an existing website or Google Business listing to extract useful information and assets for rebuilding. Extracts business info, contact details, images, content structure, site type, and design elements. **RECOMMENDED WORKFLOW**: Due to the complexity of site analysis and data extraction, use a subagent to perform the analysis. The subagent can use WebFetch to scrape the site, analyze structure, extract assets, and return organized data for the new build.

Get comprehensive market analysis including probabilities, trading activity, and AI-friendly insights. Combines market data with recent trades.

Analyze repository to detect tech stack and recommend relevant MCP servers. Note: This tool works best with local CLI, not via ChatGPT.

QUICK statistical snapshot for ONE table — row count, null rates, cardinality, numeric min/max/avg, date ranges. Optionally drill into a specific column. Use this for a fast at-a-glance read. Use `data_profile` instead when the user wants a FULL quality report including PII detection and a health score.

Get a comprehensive analysis of any technology with scores across 6 dimensions: performance (perf), developer experience (dx), ecosystem maturity, maintainability (maintain), cost efficiency, and compliance/security. Returns overall grade (A+ to C-), identified strengths and weaknesses. All scores are deterministic - no LLM hallucinations.

Analyze the distribution of trial phases for given search criteria. This tool analyzes the distribution of clinical trial phases (e.g., Phase 1, Phase 2, Phase 3) for a given set of search criteria. Input: - `conditions`: A list of medical conditions to filter the analysis. - `interventions`: A list of interventions to filter the analysis. - `sponsors`: A list of sponsors to filter the analysis. - `max_studies`: The maximum number of studies to include in the analysis. Defaults to 1000.

Submit answers to the template selection questionnaire and receive personalized recommendations. Provide answers as a key-value object where keys are question IDs (purpose, colorPreference, animations, features, complexity) and values are your choices.

Validate an API key value and return the API key object if valid.

Appends new block children to the end of the specified block.

Applies a migration to the database. Use this when executing DDL operations. Do not hardcode references to generated IDs in data migrations.

Approves an entire workstream — sets all 'Idea' status items to 'ApprovedForGeneration' and schedules the first article today, then one every two days.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

See the apps the current caller can act on and whether they are connected. Returns each app's id, name, connected state, and (when connected) the account it is connected as. Call this to answer "what apps do I have?" or when the caller's connection state may have changed since the session started.

Archive a contact record in Clay. This endpoint should only be used when you need to archive a contact.

Archives a content plan. Use this for plans that drifted off-brand, were superseded, or are otherwise dead — archived plans are filtered out of default list_content_plans but remain queryable with status='Archived'. Optional 'reason' is stored on the plan for audit.

Compare how a specific article changed between two law versions (조문 신구대조). Use MST values from law_amendment_summary to compare article text across revisions. Args: mst_old: MST of the older version (법령일련번호, from law_amendment_summary) mst_new: MST of the newer version article: Article number (e.g., 52 for 제52조) article_branch: Branch number (e.g., 2 for 제52조의2, default 0) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: Side-by-side comparison with line-level diff Examples: >>> article_amendment_diff(mst_old="269000", mst_new="273000", article=52)