Clinicaltrialsgov MCP Server

Public Hosted Server: https://clinicaltrials.caseyjhand.com/mcp

Overview

Clinical trial data from the ClinicalTrials.gov REST API v2 — the US National Library of Medicine's registry of 600K+ clinical trial studies. Search trials, fetch full study records and posted results, discover field names and valid values, and match patient demographics to candidate recruiting trials. Public, read-only, no authentication required. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Resources

Prompts

Capability reference

clinicaltrials_search_studies tool

• Free-text query plus field-specific conditionQuery / interventionQuery / locationQuery / sponsorQuery / titleQuery / outcomeQuery, statusFilter / phaseFilter enums (case and spacing variants accepted; a phaseFilter entry that names no phase, such as an OR expression, fails as enum_invalid), advancedFilter (AREA[FieldName]value / RANGE[min, max]), and geoFilter (distance(lat,lon,radius) with a mi/km suffix); pageSize 1–200 (default 10), pageToken cursor, sort on up to 2 fields
• Returns a compact per-study index by default (nctId, briefTitle, overallStatus, phases, enrollmentCount, hasResults, …); fields (PascalCase leaves) selects a full-fidelity projection — full records run ~70KB
• Typed errors: blank_value, ids_not_found, field_invalid, enum_invalid, query_parse_error, geo_invalid, sort_invalid, page_token_invalid, rate_limited

clinicaltrials_get_study_record tool

• Full protocol record by nctId, with optional locationLimit (≤500), outcomeLimit / referenceLimit (≤100), and nearLocation (lat, lon, radiusMi) to bound and sort locations
• filtersApplied reports upstream totals when a cap trims a list; resultsSection is replaced by resultsSummary counts. Typed errors: study_not_found, rate_limited

clinicaltrials_get_study_count tool

• Same query and filter surface as clinicaltrials_search_studies, returning only totalCount — no study data fetched
• Typed errors: blank_value, field_invalid, enum_invalid, query_parse_error, rate_limited

clinicaltrials_get_field_values tool

• One or more PascalCase fields (e.g. OverallStatus, Phase) — returns each field's type and top values with study counts (capped at 250 by the API), or min / max / avg for numeric and date fields and trueCount / falseCount for booleans
• multiValued flags fields whose per-value counts can sum above the study total. Typed errors: blank_value, field_invalid, rate_limited

clinicaltrials_get_field_definitions tool

• mode: search (keyword query, limit ≤100, default 20), drill (dot-notation path), or overview — resolves the PascalCase names accepted by fields, advancedFilter, sort, and clinicaltrials_get_field_values
• Typed errors: blank_value, mode_mismatch, mode_requires, path_not_found, rate_limited

clinicaltrials_get_study_results tool

• Up to 20 nctIds per call; sections (outcomes, adverseEvents, participantFlow, baseline, moreInfo), summary to condense a result set that can exceed 500KB per study, and outcomeLimit (≤100) / adverseEventLimit (≤500) with resumable outcomeOffset / seriousEventOffset / otherEventOffset
• Per-study fetchErrors / studiesWithoutResults instead of a whole-batch failure, and canonicalNctId when an alias ID resolves to another study. Typed errors: blank_value, offset_not_applicable, rate_limited

clinicaltrials_find_eligible tool

• age, sex (FEMALE / MALE / ALL), conditions[], location (country required, state / city optional), healthyVolunteer, recruitingOnly (default true), maxResults (≤50), locationLimit (≤500)
• Each candidate's locations are bounded to the sites matching the requested location, plus one recruiting site when none of those is open; funnel reports match counts per filter stage (condition → +location → +demographics)
• Candidates are matched on age, sex, location, recruitment status, and a fuzzy condition search; a notice on every non-empty response says inclusion/exclusion criteria were not checked and points to clinicaltrials_get_study_record for review
• Typed errors: blank_value, rate_limited

clinicaltrials://{nctId} resource

• Full protocol record as application/json, with locations, secondary/other outcomes, and references each capped at 50 — fixed server-side, no arguments
• Results data is replaced by resultsSummary counts; truncated and filtersApplied disclose what was capped, with retrieval naming the tools that fetch the full data
• Typed errors: study_not_found, rate_limited

analyze_trial_landscape prompt

• Arguments: topic required; focusAreas (comma-separated) optional
• Returns one user message pointing the agent at the count, search, field-discovery, and results tools for a data-driven landscape analysis

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

ClinicalTrials.gov-specific:

• Type-safe client for the ClinicalTrials.gov REST API v2 — public, no authentication or API keys required
• Serialized request queue enforcing ClinicalTrials.gov's ~1 req/sec rate limit, with retry and exponential backoff on 429/5xx responses
• Auto-corrects field names passed to fields/sort — case/whitespace fixes and known legacy aliases (e.g. RecruitmentStatus → OverallStatus) — before validating, logging every correction; a comma- or pipe-joined fields entry ("NCTId,BriefTitle") is split into separate names first, each name kept once
• Detects upstream HTML error pages returned with a JSON content-type and retries rather than parsing them as data
• Geographic proximity search and nearest-site re-ranking, with no geocoding dependency
• Excludes ClinicalTrials.gov's "unknown" enrollment sentinel (99999999) from searches and counts by default — includeUnknownEnrollment brings it back, and an nctIds lookup never filters it

Agent-friendly output:

• Provenance — clinicaltrials_search_studies / clinicaltrials_get_study_count / clinicaltrials_find_eligible echo searchCriteria on every call, including sentinelFilterActive when the default unknown-enrollment exclusion applies, and clinicaltrials_get_study_results names canonicalNctId when a previous (alias) ID resolves to a different study
• Graceful partial failure — clinicaltrials_get_study_results returns per-study fetchErrors / studiesWithoutResults rows instead of failing the whole batch when one ID is malformed or lacks results
• Discriminated output — typed error reason codes per tool (study_not_found, blank_value, offset_not_applicable, …), and bounded lists (filtersApplied, locationSummary) carry a next*Offset only when more remains, so callers branch on presence instead of parsing text
• Response shaping — clinicaltrials_search_studies and clinicaltrials_find_eligible return a compact per-study index or location-bounded set by default instead of the ~70KB full record, escalating to full fidelity only via fields or clinicaltrials_get_study_record

Getting started

Public Hosted Instance

A public instance is available at https://clinicaltrials.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "streamable-http",
      "url": "https://clinicaltrials.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["clinicaltrialsgov-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "clinicaltrialsgov-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "clinicaltrialsgov-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/clinicaltrialsgov-mcp-server:latest"]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/clinicaltrialsgov-mcp-server.git

1. Navigate into the directory:

cd clinicaltrialsgov-mcp-server

1. Install dependencies:

bun install

Configuration

All configuration is optional — the server works with defaults and no API keys.

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:http
  # or
  bun run start:stdio
  

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, and security audit
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t clinicaltrialsgov-mcp-server .
docker run --rm -p 3010:3010 clinicaltrialsgov-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/clinicaltrialsgov-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, no console calls
• Register new tools and resources via the barrels in src/mcp-server/*/definitions/index.ts
• Validate raw API responses, normalize to domain types, and never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.