Claidex MCP by claidex.com

MCP server · Translation · indexed, not reviewed

HostedLocalvendor's own

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

Biomedical failure intelligence platform for terminated trials and translational analysis.

What the official MCP registry says

Facts

MCP registry
com.claidex/failure-intelligence · 1.0.0
Endpoint
https://app.claidex.com/api/mcp
Packages
npm @claidex-mcp/claidex-mcp stdio
npm / week
16
Registry entry
updated 24 May 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under claidex.com, a namespace the registry only gives to whoever proves they control that domain.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 24 · about 4,095 tokens of context · checked 14 minutes ago

ToolWhat it doesHint
claidex_capabilitiesClaidex MCP CapabilitiesReturn the Claidex MCP feature map, configured storage/model providers, safety controls, resources, prompts, and tool counts.
claidex_claim_risk_matrixClaidex Claim Risk MatrixSearch claims and summarize MRS bands, trial phases, failure archetypes, and high-risk programs for rapid diligence.
claidex_health_snapshotClaidex Health SnapshotReturn Sentinel metrics, coverage, graph counts, recent automation runs, MRS bands, and preprint-watch summaries.
claidex_research_promptClaidex Research PromptCompose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use.
claidex_tool_catalogClaidex Tool CatalogReturn the complete MCP tool catalog, optionally including full input schemas and filtering native versus agent-backed tools.
consult_specialist_modelConsult Specialist ModelAsk a specialist Gateway model for code, database/tool-calling, statistics, literature, preprint, or mechanistic synthesis support. Use for hard subproblems, second opinions, code generation/review, or complex synthesis.
fetchFetch Claidex ResultFetch a specific result returned by search. This compatibility tool supports OpenAI and ChatGPT remote MCP retrieval flows.
fetch_research_urlFetch Research UrlFetch a public HTTPS research URL, JSON API response, package metadata endpoint, documentation page, or dataset preview. Blocks private/internal hosts and truncates large responses.
get_claim_contentGet Claim ContentRetrieve 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, failure mechanism, and prevention analysis.
query_chemblQuery ChemblLook up a drug or compound in ChEMBL. Returns mechanism of action, primary target, ChEMBL ID, max development phase, molecular type, and synonyms.
query_clinicaltrialsQuery ClinicaltrialsSearch ClinicalTrials.gov for clinical trials. Can search by drug name, condition, target, or NCT ID. Returns trial status, phase, sponsor, primary endpoints, and why_stopped if terminated.
query_failure_graphQuery Failure GraphQuery the Claidex failure graph for a specific gene target. Returns the Mechanism Risk Score (MRS), failure counts by phase and archetype, and all related claim slugs.
query_openfdaQuery OpenfdaQuery the FDA FAERS database for adverse event signals for a drug. Returns top adverse event terms, serious case count, and death count.
query_opentargetsQuery OpentargetsQuery Open Targets for target-disease association evidence. Returns genetic evidence score, clinical evidence, known drugs, tractability, and safety liabilities for a gene-disease pair.
query_package_registryQuery Package RegistryLook up package metadata from npm or PyPI before recommending code, analysis packages, API clients, or dataset tooling.
rank_documents_by_embeddingRank Documents By EmbeddingEmbed a query and candidate documents, then rank documents by cosine similarity. Use for semantic matching, retrieval checks, clustering triage, and lightweight RAG over user-provided passages.
rerank_documentsRerank DocumentsRerank candidate documents/passages against a query using a dedicated reranking model. Use after retrieval/search when exact relevance ordering matters.
run_computationRun ComputationEvaluate deterministic mathematical expressions with optional variables. Use for algebra, matrices, vectors, transformations, descriptive numerical checks, and reproducible calculations. Does not execute arbitrary…
run_statistical_analysisRun Statistical AnalysisRun a statistical analysis computation. Supports: Wilson confidence intervals, binomial proportions, phase transition success rates, power calculations, Bayesian posterior estimates, descriptive statistics, and…
searchSearch ClaidexSearch Claidex failure claims and preprint flags. This compatibility tool returns citation-ready results for OpenAI and ChatGPT remote MCP flows.
search_claimsSearch ClaimsSearch the Claidex failure database for post-mortems matching a drug name, gene target, disease, failure archetype, or sponsor. Returns matching claims with title, slug, drug, target, disease, phase, failure archetype,…
search_preprint_flagsSearch Preprint FlagsSearch the Claidex Preprint Watch database for bioRxiv preprints flagged as contradicting the clinical failure record. Search by target gene, disease, or preprint title.
search_pubmedSearch PubmedSearch PubMed for biomedical literature. Returns title, authors, journal, year, DOI, abstract, and PMID for each result.
web_searchWeb SearchSearch the web for recent news, investor commentary, analyst notes, press releases, and conference coverage about drugs, clinical trials, or biomedical mechanisms.

What https://app.claidex.com/api/mcp answered to tools/list, asked without credentials. answered without the initialize handshake. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 57 warnings · 1 note

  • warnTC10claidex_claim_risk_matrix"limit" is required and has a default
  • warnTC10claidex_research_prompt"risk_tolerance" is required and has a default
  • warnTC10claidex_tool_catalog"include_schemas" is required and has a default
  • warnTC10claidex_tool_catalog"source" is required and has a default
  • warnTC10fetch_research_url"max_chars" is required and has a default
  • warnTC10query_clinicaltrials"status" is required and has a default
  • warnTC10query_clinicaltrials"phase" is required and has a default
  • warnTC10query_clinicaltrials"max_results" is required and has a default
  • warnTC10query_openfda"max_results" is required and has a default
  • warnTC10rank_documents_by_embedding"top_k" is required and has a default
  • warnTC10rerank_documents"top_n" is required and has a default
  • warnTC10run_computation"variables" is required and has a default
  • warnTC10search"limit" is required and has a default
  • warnTC10search_claims"category" is required and has a default
  • warnTC10search_claims"failure_archetype" is required and has a default
  • warnTC10search_claims"limit" is required and has a default
  • warnTC10search_preprint_flags"severity" is required and has a default
  • warnTC10search_pubmed"max_results" is required and has a default
  • warnTC10web_search"focus" is required and has a default
  • warnTC11claidex_claim_risk_matrix1 parameter without a description: limit
  • warnTC11claidex_research_prompt1 parameter without a description: risk_tolerance
  • warnTC11claidex_tool_catalog1 parameter without a description: source
  • warnTC11fetch_research_url1 parameter without a description: max_chars
  • warnTC11query_clinicaltrials3 parameters without a description: max_results, phase, status

The first 24 of 58; every finding is in the listing's JSON under mcpTools.check.

The checks from /check and anchor check, run each day on the list above: about 4,095 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.