The MCP tool directory.

Run a tailored Discounted Cash Flow (DCF) analysis using the FMP Custom DCF Advanced API. With detailed inputs, this API allows users to fine-tune their assumptions and variables, offering a more personalized and precise valuation for a company.

Make this identity's calendar public or private. Public calendars are viewable at /identities/:id/calendar.json

EMERGENCY STOP: stops EVERY run currently executing for the tenant, including runs started by other users and by other applications. Use this when something is burning credits and identifying the specific run would take too long — otherwise prefer cancel_run. Same timing as cancel_run: runs stop at their next checkpoint, not instantly.

Stops a run that is currently executing, and every sub-agent it spawned. Use list_runs and look for Outcome 'running' to find candidates. NOT instant: the run checks for the signal between tool-calling iterations, so a model call already in flight finishes first — expect it to stop within one model turn. Whatever the run produced before stopping is still returned to its caller and still billed; cancelling saves the work that had not happened yet, not the work already done. Cancelling a run that already finished is harmless and reports signalled=0.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Associate one or more candidates to a target Job Opening, Client, or Contact. The body's `data` array contains `Jobids` (or `Clientids` / `Contactids`) plus `ids` of candidates to associate.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Upload a resume (PDF/DOCX) and parse it into a new Candidate record.

Use this when you need a visual capture of a web page. Renders in a real Chromium browser and returns an image. Returns: 1. Binary image (PNG, JPEG, or WebP) 2. Custom viewport support (width/height

Lists all product categories in the directory. Use category slugs to filter product searches in products.search / products.find_by_capability. Response: { categories: [{ slug, name, description }] }. Note: this is a thin call. For a full directory briefing (subcategories, capability slugs per category, product counts, locked-vertical flags), prefer directory.overview as a single up-front call.

Search the Ceramic AI knowledge base for relevant information. Returns ranked results with titles, URLs, and descriptions.

Search ministry law interpretations (중앙부처 1차 해석 목록 조회). Search law interpretation opinions from Korean central government ministries. Args: ministry: Ministry name in Korean. Valid values: 고용노동부, 국토교통부, 기획재정부, 해양수산부, 행정안전부, 기후에너지환경부, 관세청, 국세청, 교육부, 과학기술정보통신부, 국가보훈부, 국방부, 농림축산식품부, 문화체육관광부, 법무부, 보건복지부, 산업통상부, 성평등가족부, 외교부, 중소벤처기업부, 통일부, 법제처, 식품의약품안전처, 인사혁신처, 기상청, 국가유산청, 농촌진흥청, 경찰청, 방위사업청, 병무청, 산림청, 소방청, 재외동포청, 조달청, 질병관리청, 국가데이터처, 지식재산처, 해양경찰청, 행정중심복합도시건설청 query: Search keyword (default "*") display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" search: 1=사건명 (case name), 2=본문검색 (full text) sort: Sort order gana: Dictionary search ctx: MCP context (injected automatically) Returns: Ministry interpretation list or error Examples: Search 고용노동부 interpretations: >>> cgm_expc_search(ministry="고용노동부", query="퇴직금")

Retrieve ministry interpretation full text (중앙부처 1차 해석 본문 조회). Args: ministry: Ministry name (same values as cgm_expc_search) id: Interpretation serial number (해석례일련번호) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" ctx: MCP context (injected automatically) Returns: Full interpretation text or error

Track law amendment history with optional article-level diff (법령 개정 추적). Chains: amendment summary → article diff between latest two versions. If article=0, returns only the revision list. If article is specified, also diffs that article between the two most recent revisions. Args: law_name: Law name (e.g., "근로기준법") article: Article number to diff (0 = summary only, e.g., 52 for 제52조) date_from: Start date YYYYMMDD (default "20200101") date_to: End date YYYYMMDD (default "20261231") oc: Optional OC override type: Response format Returns: Revision history and optional article diff Examples: >>> chain_amendment_track(law_name="근로기준법") >>> chain_amendment_track(law_name="근로기준법", article=52, date_from="20180101")

Prepare for a legal dispute by gathering all case law (분쟁 준비 자료). Chains: precedent search + admin appeals + constitutional decisions + special tribunal. Gathers all decision-type legal sources in one call. Args: query: Dispute topic (e.g., "부당해고", "개인정보 유출", "조세 부과 취소") display: Results per category (default 5) oc: Optional OC override type: Response format Returns: Precedents, admin appeals, constitutional decisions, and special tribunal decisions Examples: >>> chain_dispute_prep(query="부당해고") >>> chain_dispute_prep(query="개인정보 유출 과징금")

Complete legal research in one call (종합 법률 조사). Chains: AI search → statutes → precedents with outcome analysis → interpretations → citations. This is the most comprehensive single-call research tool. Args: query: Natural language query (e.g., "음주운전 처벌 기준", "임대차 보증금 반환") display: Results per sub-query (default 5) oc: Optional OC override type: Response format Returns: Combined legal analysis with statutes, precedent statistics, interpretations, and citations Examples: >>> chain_full_research(query="부당해고 구제") >>> chain_full_research(query="개인정보 유출 신고 의무")

Map the full law system hierarchy (법령 체계 조회). Chains: law search → delegation tree → related admin rules → linked ordinances. Shows how a law connects to its subordinate regulations. Args: law_name: Law name (e.g., "건축법", "근로기준법") oc: Optional OC override type: Response format Returns: Law hierarchy: parent law, delegated decrees/rules, linked ordinances Examples: >>> chain_law_system(law_name="건축법") >>> chain_law_system(law_name="개인정보 보호법")

Change a customer's CRM conversion state (category) for a product.

Check your remaining ThreadSnoop API credit balance and rate limit. Free — 0 credits.

$0.01 USDC on Base mainnet: check model/configuration fit against bounded StackBench capacity evidence.

Check a disposable AgentMail inbox for new messages. Use after create_test_inbox to read verification emails, OTP codes, welcome emails, or password reset links. Automatically extracts verification codes from email content.

Check compatibility between MCP servers. Detects conflicts (e.g., two database providers), redundancies (e.g., two ORMs), and synergies (e.g., GitHub + Vercel). Returns a health score (0-100) with grade (A/B/C/D) and detailed breakdown.

Find precedent statistics and key outcome factors for a legal question (판례 승률 분석). Searches court precedents, analyzes outcomes (인용/기각/파기), and extracts key factors that influenced decisions. Useful for assessing legal odds. Args: query: Legal question or keywords (e.g., "택배 파손 보상", "임대차 보증금 반환") display: Number of precedents to search (max 100, default 20) top_n: Number of top precedents to analyze in detail (default 5) oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: Outcome statistics, key factors, and representative case summaries Examples: >>> check_precedent_odds(query="택배 파손 보상") >>> check_precedent_odds(query="부당해고", display=50, top_n=10)

Check if a screenshot is already cached without capturing a new one. Does not count against your quota.

Upload an audio or speech file to detect whether it is human-recorded or AI-synthesized. Provide the audio content as a base64-encoded string. Returns a classification identifier for async result retrieval. WARNING: base64 encoding adds ~33% overhead to the original file size. For audio files larger than 10 MB, use classify_audio_url instead and provide a publicly accessible URL to avoid payload size issues. Authentication: provide your Identifai API key via the apiKey parameter or configure the X-Api-Key HTTP header in your MCP client (recommended).

Submit a publicly accessible audio URL for AI-generated speech detection. Returns a classification identifier for async result retrieval. Authentication: provide your Identifai API key via the apiKey parameter or configure the X-Api-Key HTTP header in your MCP client (recommended).