# Claidex MCP (remote · app.claidex.com)

Biomedical failure intelligence platform for terminated trials and translational analysis.

- Trust score: 79/100 (medium)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `app.claidex.com`: 79/100 (this document), [markdown](https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp.md), [page](https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp)
- npm · `@claidex-mcp/claidex-mcp`: 34/100, [markdown](https://verifymcp.io/servers/com-claidex-failure-intelligence/claidex-mcp-claidex-mcp.md), [page](https://verifymcp.io/servers/com-claidex-failure-intelligence/claidex-mcp-claidex-mcp)

## Channel facts

- Endpoint: `https://app.claidex.com/api/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1839 tokens (~63/item across 29 items; 24 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 56% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http com-claidex-failure-intelligence https://app.claidex.com/api/mcp
```

### Codex

```toml
[mcp_servers.com-claidex-failure-intelligence]
url = "https://app.claidex.com/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-claidex-failure-intelligence": {
      "type": "remote",
      "url": "https://app.claidex.com/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-claidex-failure-intelligence --url https://app.claidex.com/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-claidex-failure-intelligence:
    url: "https://app.claidex.com/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-claidex-failure-intelligence": {
      "type": "http",
      "url": "https://app.claidex.com/api/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 77, +5)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 72, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 70)

First indexed and scored.

## MCP tools (24)

### `claidex_capabilities` (~36 tokens)

Claidex MCP Capabilities

Return the Claidex MCP feature map, configured storage/model providers, safety controls, resources, prompts, and tool counts.

### `claidex_claim_risk_matrix` (~62 tokens)

Claidex Claim Risk Matrix

Search claims and summarize MRS bands, trial phases, failure archetypes, and high-risk programs for rapid diligence.

Input parameters:

- `limit` (integer, required)
- `query` (string, required): Drug, target, disease, sponsor, or failure archetype.

### `claidex_health_snapshot` (~34 tokens)

Claidex Health Snapshot

Return Sentinel metrics, coverage, graph counts, recent automation runs, MRS bands, and preprint-watch summaries.

### `claidex_research_prompt` (~83 tokens)

Claidex Research Prompt

Compose a rigorous, reusable investigation prompt that tells an MCP client which Claidex tools and resources to use.

Input parameters:

- `disease` (string): Optional disease area.
- `objective` (string, required): The investigation objective to turn into a reusable MCP prompt.
- `risk_tolerance` (string, required)
- `target_gene` (string): Optional HGNC target symbol.

### `claidex_tool_catalog` (~55 tokens)

Claidex Tool Catalog

Return the complete MCP tool catalog, optionally including full input schemas and filtering native versus agent-backed tools.

Input parameters:

- `include_schemas` (boolean, required): Include full JSON Schemas in the catalog.
- `source` (string, required)

### `consult_specialist_model` (~99 tokens)

Consult Specialist Model

Ask 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.

Input parameters:

- `context` (string): Relevant context, snippets, or data. Do not include secrets.
- `prompt` (string, required): Focused task for the specialist model.
- `task_type` (string, required): Specialist routing target.

### `fetch` (~43 tokens)

Fetch Claidex Result

Fetch a specific result returned by search. This compatibility tool supports OpenAI and ChatGPT remote MCP retrieval flows.

Input parameters:

- `id` (string, required): Result id returned by the search tool.

### `fetch_research_url` (~62 tokens)

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 truncates large responses.

Input parameters:

- `max_chars` (number, required)
- `url` (string, required): Public HTTPS URL to fetch.

### `get_claim_content` (~82 tokens)

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, failure mechanism, and prevention analysis.

Input parameters:

- `slug` (string, required): The Claidex claim slug, e.g. exicorilant-mcrpc-gr-bypass-fourth-failure

### `query_chembl` (~56 tokens)

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.

Input parameters:

- `drug_name` (string, required): Drug or compound name

### `query_clinicaltrials` (~96 tokens)

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, and why_stopped if terminated.

Input parameters:

- `max_results` (number, required)
- `phase` (string, required)
- `query` (string, required): Search term: drug name, condition, NCT ID, or target
- `status` (string, required)

### `query_failure_graph` (~73 tokens)

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 claim slugs.

Input parameters:

- `target_gene` (string, required): HGNC gene symbol, e.g. PIK3CA, KRAS, EGFR

### `query_openfda` (~62 tokens)

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.

Input parameters:

- `drug_name` (string, required): Drug name as it appears in FAERS
- `max_results` (number, required)

### `query_opentargets` (~71 tokens)

Query Opentargets

Query Open Targets for target-disease association evidence. Returns genetic evidence score, clinical evidence, known drugs, tractability, and safety liabilities for a gene-disease pair.

Input parameters:

- `disease_term` (string, required): Disease name or EFO term
- `target_gene` (string, required): HGNC gene symbol

### `query_package_registry` (~53 tokens)

Query Package Registry

Look up package metadata from npm or PyPI before recommending code, analysis packages, API clients, or dataset tooling.

Input parameters:

- `ecosystem` (string, required): Package registry to query.
- `package_name` (string, required): Package name.

### `rank_documents_by_embedding` (~68 tokens)

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 lightweight RAG over user-provided passages.

Input parameters:

- `documents` (array, required)
- `query` (string, required)
- `top_k` (number, required)

### `rerank_documents` (~58 tokens)

Rerank Documents

Rerank candidate documents/passages against a query using a dedicated reranking model. Use after retrieval/search when exact relevance ordering matters.

Input parameters:

- `documents` (array, required)
- `query` (string, required)
- `top_n` (number, required)

### `run_computation` (~97 tokens)

Run Computation

Evaluate deterministic mathematical expressions with optional variables. Use for algebra, matrices, vectors, transformations, descriptive numerical checks, and reproducible calculations. Does not execute arbitrary JavaScript or install packages.

Input parameters:

- `expression` (string, required): MathJS expression, e.g. mean(values), std(values), multiply(A, b), inv(A).
- `variables` (object, required): Variables available to the expression. Values must be numbers, strings, vectors, or matrices.

### `run_statistical_analysis` (~181 tokens)

Run Statistical Analysis

Run a statistical analysis computation. Supports: Wilson confidence intervals, binomial proportions, phase transition success rates, power calculations, Bayesian posterior estimates, descriptive statistics, and two-proportion comparisons. Returns computed values, interpretation, and LaTeX formula.

Input parameters:

- `analysis_type` (string, required)
- `context` (string): Optional context about what this analysis is for
- `inputs` (object, required): Named input parameters. wilson_ci: {successes, n, confidence}. phase_transition_rate: {phase, indication, n_succeeded, n_total}. power_calculation: {n, effect_size, alpha}. bayesian_posterior: {prior…

### `search` (~53 tokens)

Search Claidex

Search Claidex failure claims and preprint flags. This compatibility tool returns citation-ready results for OpenAI and ChatGPT remote MCP flows.

Input parameters:

- `limit` (integer, required)
- `query` (string, required): Biomedical failure intelligence query.

### `search_claims` (~113 tokens)

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 title, slug, drug, target, disease, phase, failure archetype, Open Targets score, and MRS score.

Input parameters:

- `category` (string, required)
- `failure_archetype` (string, required)
- `limit` (number, required)
- `query` (string, required): Search term: drug name, gene symbol, disease, or failure archetype

### `search_preprint_flags` (~73 tokens)

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 preprint title.

Input parameters:

- `query` (string, required): Search term: gene symbol, disease, or preprint title fragment
- `severity` (string, required)

### `search_pubmed` (~54 tokens)

Search Pubmed

Search PubMed for biomedical literature. Returns title, authors, journal, year, DOI, abstract, and PMID for each result.

Input parameters:

- `max_results` (number, required)
- `query` (string, required): PubMed search query

### `web_search` (~53 tokens)

Web Search

Search the web for recent news, investor commentary, analyst notes, press releases, and conference coverage about drugs, clinical trials, or biomedical mechanisms.

Input parameters:

- `focus` (string, required)
- `query` (string, required): Search query

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp#diagnostics

## Score history

- 2026-08-03: 79
- 2026-08-02: 78
- 2026-08-01: 78
- 2026-07-31: 77
- 2026-07-30: 72
- 2026-07-29: 72
- 2026-07-28: 71
- 2026-07-27: 70
- 2026-07-26: 70

## Links

- Remote endpoint: https://app.claidex.com/api/mcp
- Authorisation metadata: https://app.claidex.com/.well-known/oauth-protected-resource/api/mcp
- Website: https://claidex.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-claidex-failure-intelligence/api-mcp