mcpField
C
ClinicalTrials.gov MCP by usefulapi

ClinicalTrials.gov MCP by usefulapi

Remote
usefulapi.ioHealth0Updated today

About ClinicalTrials.gov MCP by usefulapi

A hosted MCP server for searching and reading ClinicalTrials.gov studies, aimed at people researching clinical trials. It provides study lookup alongside field metadata and aggregate statistics, without local installation.

Key features

  1. 01Search clinical trials
  2. 02Retrieve studies by NCT ID
  3. 03Count matching studies
  4. 04Inspect field values and metadata
  5. 05View study statistics and API version

Use cases

  1. 01Find trials matching research criteria
  2. 02Review a study using its NCT ID
  3. 03Check field distributions and study counts

MCP support

Exposes read-only ClinicalTrials.gov search, study retrieval, counts, field data, statistics, and API-version tools to MCP clients. It is hosted and connects through its remote MCP endpoint.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://clinicaltrialsgov.usefulapi.io/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

7
ParameterTypeRequiredDescription
idsarrayNoRestrict to these NCT ids (maps to filter.ids), e.g. ['NCT00841061'].
sortstringNoSort order, e.g. '@relevance', 'LastUpdatePostDate:desc', 'EnrollmentCount:desc', 'StudyFirstPostDate:desc'.
termstringNoGeneral full-text 'other terms' query (maps to query.term).
titlestringNoWords in the study title (maps to query.titles).
fieldsarrayNoFields or modules to return, e.g. ['NCTId','BriefTitle','OverallStatus'] or ['protocolSection.identificationModule']. Omit to return full study records.
statusarrayNoFilter by overall recruitment status (maps to filter.overallStatus). One or more of: ACTIVE_NOT_RECRUITING, COMPLETED, ENROLLING_BY_INVITATION, NOT_YET_RECRUITING, RECRUITING, SUSPENDED, TERMINATED, WITHDRAWN, AVAILABLE, NO_LONGER_AVAILABLE, TEMPORARILY_NOT_AVAILABLE, APPROVED_FOR_MARKETING, WITHHELD, UNKNOWN.
sponsorstringNoSponsor / collaborator name (maps to query.spons).
advancedstringNoAdvanced Essie expression applied as an additional filter (maps to filter.advanced).
locationstringNoStudy location text, e.g. a city/state/country (maps to query.locn).
pageSizeintegerNoNumber of studies per page (1–1000; API default 10).
conditionstringNoDisease / condition to match (maps to query.cond), e.g. 'diabetes'.
geoFilterstringNoGeo filter as a raw geo-function string (maps to filter.geo), e.g. 'distance(39.0027,-77.1,50mi)'.
pageTokenstringNoOpaque token from a previous response's nextPageToken, to fetch the next page.
countTotalbooleanNoInclude the total number of matching studies (totalCount) on the first page.
interventionstringNoTreatment / drug / intervention to match (maps to query.intr).

Details

From the project README

ClinicalTrials.gov MCP by usefulapi

Search and read ClinicalTrials.gov studies, sites and outcomes. Hosted, no local install.

Live endpoint: https://clinicaltrialsgov.usefulapi.io/mcp · Homepage: https://usefulapi.io

Connect

  • Claude (claude.ai, Desktop): open Customize → Connectors, click + Add → Add custom connector, and paste https://clinicaltrialsgov.usefulapi.io/mcp.
  • Claude Code: claude mcp add --transport http clinicaltrialsgov https://clinicaltrialsgov.usefulapi.io/mcp, then run /mcp to log in.
  • VS Code: Add to VS Code.
  • Cursor and other clients: add the URL as a remote MCP server:
{
  "mcpServers": {
    "clinicaltrialsgov": {
      "url": "https://clinicaltrialsgov.usefulapi.io/mcp"
    }
  }
}

Add only the URL. Do not add an Authorization header or an API key to the client config: the server signs you in with OAuth, and the login page asks for your email address and a 6-digit code.

Step-by-step setup, where to find your credentials, and FAQ: https://usefulapi.io/clinicaltrialsgov/

This server needs no credential — ClinicalTrials.gov is a public data source. On first connect you log in with your email: we send a 6-digit code from [email protected]. The address is used only to send the code; we keep a one-way hash of it as your account id, so your free calls and your plan stay yours.

Tools

ToolTypeWhat it does
clinicaltrialsgov_search_studiesreadSearch clinical trials (ClinicalTrials.gov)
clinicaltrialsgov_get_studyreadGet a clinical trial by NCT ID
clinicaltrialsgov_count_studiesreadCount matching clinical trials
clinicaltrialsgov_list_field_valuesreadList value statistics for study fields
clinicaltrialsgov_get_study_metadatareadGet the study data-model (field tree)
clinicaltrialsgov_get_studies_statsreadGet study size statistics
clinicaltrialsgov_get_api_versionreadGet the ClinicalTrials.gov API version
clinicaltrialsgov_usage_statusmetaUsage status (free-tier meter)
clinicaltrialsgov_request_featuremetaRequest a missing feature
clinicaltrialsgov_upgrademetaUpgrade to Pro (unlimited*)
clinicaltrialsgov_cancel_subscriptionmetaCancel the Pro subscription

read tools are read-only; write tools mutate data (clients should confirm them); meta tools report usage, manage your subscription or send a feature request.

Pricing

PlanPriceLimit
Free$050 tool calls / month
Pro$9/mo or $90/yr (2 months free)Unlimited*

*Pro has a fair use limit of 10,000 tool calls a month on this server. For more, write to [email protected].

Pro covers this server only. Subscribe with clinicaltrialsgov_upgrade (it returns a Stripe Checkout link). Cancel any time with clinicaltrialsgov_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running clinicaltrialsgov_upgrade before then undoes the cancel. Or write to [email protected].

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.