AI & Machine Learning
claidex.com
Claidex provides AI-powered tools for rapid research diligence, including risk matrix analysis, health snapshot summaries, and reusable investigation prompts for MCP clients.
ENDPOINT 1
https://app.claidex.com/api/mcp
MCP server metadata
- Name
- claidex
- Version
- 1.0.0
Use Claidex for biomedical post-mortems, failure graphs, MRS risk, claim retrieval, preprint flags, statistical analysis, computation, package checks, and cited research retrieval.
Known tools 24
claidex_capabilitiesReturn the Claidex MCP feature map, configured storage/model providers, safety controls, resources, prompts, and tool counts.
Inferred read-onlyclaidex_claim_risk_matrixSearch claims and summarize MRS bands, trial phases, failure archetypes, and high-risk programs for rapid diligence.
Inferred read-onlyclaidex_health_snapshotReturn Sentinel metrics, coverage, graph counts, recent automation runs, MRS bands, and preprint-watch summaries.
Inferred read-onlyclaidex_research_promptCompose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use.
Inferred read-onlyclaidex_tool_catalogReturn the complete MCP tool catalog, optionally including full input schemas and filtering native versus agent-backed tools.
Inferred read-onlyconsult_specialist_modelAsk a specialist Gateway model for code, database/tool-calling, statistics, literature, preprint, or mechanistic synthesis support.
Inferred read-onlyfetch_research_urlFetch a public HTTPS research URL, JSON API response, package metadata endpoint, documentation page, or dataset preview.
Inferred read-onlyget_claim_contentRetrieve the complete text content of a specific Claidex Claim by its slug.
Inferred read-onlyquery_package_registryLook up package metadata from npm or PyPI before recommending code, analysis packages, API clients, or dataset tooling.
Inferred read-onlyrank_documents_by_embeddingEmbed a query and candidate documents, then rank documents by cosine similarity.
Inferred read-onlyrerank_documentsRerank candidate documents/passages against a query using a dedicated reranking model.
Inferred read-onlyrun_computationEvaluate deterministic mathematical expressions with optional variables.
Inferred read-onlysearch_claimsSearch the Claidex failure database for post-mortems matching a drug name, gene target, disease, failure archetype, or sponsor.
Potential side effectssearch_preprint_flagsSearch the Claidex Preprint Watch database for bioRxiv preprints flagged as contradicting the clinical failure record.
Inferred read-onlyweb_searchSearch the web for recent news, investor commentary, analyst notes, press releases, and conference coverage about drugs, clinical trials, or biomedical mechanisms.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.claidex]
url = "https://app.claidex.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"claidex": {
"type": "http",
"url": "https://app.claidex.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: claidex
Remote MCP URL: https://app.claidex.com/api/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"claidex": {
"url": "https://app.claidex.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"claidex": {
"type": "http",
"url": "https://app.claidex.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "claidex",
"transport": "streamable-http",
"url": "https://app.claidex.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for claidex.com was fetched 2026-08-04T00:46:39.089Z and is being refreshed.
claidex.com is assessed as Trusted: Domain has an established technology history spanning over a year.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.