# Claidex MCP (slim) > Claidex MCP, an MCP server by claidex.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Biomedical failure intelligence platform for terminated trials and translational analysis. - Full: https://www.anchorterminal.com/tools/claidex-failure-intelligence.md (~2,050 tokens) · this version ~1,980 tokens · JSON https://www.anchorterminal.com/tools/claidex-failure-intelligence.json · canonical https://www.anchorterminal.com/tools/claidex-failure-intelligence - Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05 # Claidex MCP > Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/ - Kind: MCP server, by claidex.com (https://claidex.com) - Category: Translation (https://www.anchorterminal.com/categories/translation.md) - Listed because: It's published in the registry under claidex.com, a namespace the registry only gives to whoever proves they control that domain. - What the official MCP registry says: Biomedical failure intelligence platform for terminated trials and translational analysis. ## Facts - MCP registry: `com.claidex/failure-intelligence` 1.0.0 - Endpoint: https://app.claidex.com/api/mcp (streamable HTTP) - Package: npm `@claidex-mcp/claidex-mcp` (stdio) - Source: https://github.com/ssatanis/claidex-sentinel - Website: https://claidex.com - npm downloads a week: 16 - Registry entry updated: 2026-05-24 ## Tools - Tools it lists (24, about 4,095 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:22 UTC): - `claidex_capabilities`: Return the Claidex MCP feature map, configured storage/model providers, safety controls, resources, prompts, and tool counts. - `claidex_claim_risk_matrix`: Search claims and summarize MRS bands, trial phases, failure archetypes, and high-risk programs for rapid diligence. - `claidex_health_snapshot`: Return Sentinel metrics, coverage, graph counts, recent automation runs, MRS bands, and preprint-watch summaries. - `claidex_research_prompt`: Compose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use. - `claidex_tool_catalog`: Return the complete MCP tool catalog, optionally including full input schemas and filtering native versus agent-backed tools. - `consult_specialist_model`: Ask a specialist Gateway model for code, database/tool-calling, statistics, literature, preprint, or mechanistic synthesis support. Use for hard subproblems,… - `fetch`: Fetch a specific result returned by search. This compatibility tool supports OpenAI and ChatGPT remote MCP retrieval flows. - `fetch_research_url`: Fetch a public HTTPS research URL, JSON API response, package metadata endpoint, documentation page, or dataset preview. Blocks private/internal hosts and… - `get_claim_content`: Retrieve the complete text content of a specific Claidex Claim by its slug. Use this when you need to read the full post-mortem analysis, including hypothesis,… - `query_chembl`: Look up a drug or compound in ChEMBL. Returns mechanism of action, primary target, ChEMBL ID, max development phase, molecular type, and synonyms. - `query_clinicaltrials`: Search ClinicalTrials.gov for clinical trials. Can search by drug name, condition, target, or NCT ID. Returns trial status, phase, sponsor, primary endpoints,… - `query_failure_graph`: Query the Claidex failure graph for a specific gene target. Returns the Mechanism Risk Score (MRS), failure counts by phase and archetype, and all related… - `query_openfda`: Query the FDA FAERS database for adverse event signals for a drug. Returns top adverse event terms, serious case count, and death count. - `query_opentargets`: Query Open Targets for target-disease association evidence. Returns genetic evidence score, clinical evidence, known drugs, tractability, and safety… - `query_package_registry`: Look up package metadata from npm or PyPI before recommending code, analysis packages, API clients, or dataset tooling. - `rank_documents_by_embedding`: Embed a query and candidate documents, then rank documents by cosine similarity. Use for semantic matching, retrieval checks, clustering triage, and… - `rerank_documents`: Rerank candidate documents/passages against a query using a dedicated reranking model. Use after retrieval/search when exact relevance ordering matters. - `run_computation`: Evaluate deterministic mathematical expressions with optional variables. Use for algebra, matrices, vectors, transformations, descriptive numerical checks, and… - `run_statistical_analysis`: Run a statistical analysis computation. Supports: Wilson confidence intervals, binomial proportions, phase transition success rates, power calculations,… - `search`: Search Claidex failure claims and preprint flags. This compatibility tool returns citation-ready results for OpenAI and ChatGPT remote MCP flows. - `search_claims`: Search the Claidex failure database for post-mortems matching a drug name, gene target, disease, failure archetype, or sponsor. Returns matching claims with… - `search_preprint_flags`: Search the Claidex Preprint Watch database for bioRxiv preprints flagged as contradicting the clinical failure record. Search by target gene, disease, or… - `search_pubmed`: Search PubMed for biomedical literature. Returns title, authors, journal, year, DOI, abstract, and PMID for each result. - `web_search`: Search the web for recent news, investor commentary, analyst notes, press releases, and conference coverage about drugs, clinical trials, or biomedical… - How its tools read to an agent (0 errors, 57 warnings, 1 note, about 4,095 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC10 claidex_claim_risk_matrix: "limit" is required and has a default - warn TC10 claidex_research_prompt: "risk_tolerance" is required and has a default - warn TC10 claidex_tool_catalog: "include_schemas" is required and has a default - warn TC10 claidex_tool_catalog: "source" is required and has a default - warn TC10 fetch_research_url: "max_chars" is required and has a default - warn TC10 query_clinicaltrials: "status" is required and has a default - warn TC10 query_clinicaltrials: "phase" is required and has a default - warn TC10 query_clinicaltrials: "max_results" is required and has a default - warn TC10 query_openfda: "max_results" is required and has a default - warn TC10 rank_documents_by_embedding: "top_k" is required and has a default - warn TC10 rerank_documents: "top_n" is required and has a default - warn TC10 run_computation: "variables" is required and has a default - warn TC10 search: "limit" is required and has a default - warn TC10 search_claims: "category" is required and has a default - warn TC10 search_claims: "failure_archetype" is required and has a default - warn TC10 search_claims: "limit" is required and has a default - warn TC10 search_preprint_flags: "severity" is required and has a default - warn TC10 search_pubmed: "max_results" is required and has a default - warn TC10 web_search: "focus" is required and has a default - warn TC11 claidex_claim_risk_matrix: 1 parameter without a description: limit - warn TC11 claidex_research_prompt: 1 parameter without a description: risk_tolerance - warn TC11 claidex_tool_catalog: 1 parameter without a description: source - warn TC11 fetch_research_url: 1 parameter without a description: max_chars - warn TC11 query_clinicaltrials: 3 parameters without a description: max_results, phase, status - JSON: https://www.anchorterminal.com/api/v1/tools/claidex-failure-intelligence.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming