ClinicalTrials MCP Server

🔍 Enable AI assistants to search and access ClinicalTrials.gov data through a simple MCP interface.

Local serverstdioPython

What is the ClinicalTrials MCP server?

Most developer tooling work still happens through a UI a human drives. ClinicalTrials MCP server moves it into the conversation instead. 🔍 Enable AI assistants to search and access ClinicalTrials.gov data through a simple MCP interface.

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

The tools it exposes

The server publishes 10 tools. What each one is for:

  • Claude — The Claude tool exposed by this server
  • Cursor — Paste the following into Settings → Cursor Settings → MCP → Add new server: - Mac/Linux s npx -y @smithery/cli@latest run ClinicalTrials-mcp-server
  • Windsurf — The Windsurf tool exposed by this server
  • CLine — The CLine tool exposed by this server
  • get_full_study_details — The get_full_study_details tool exposed by this server
  • get_studies_by_keyword — The get_studies_by_keyword tool exposed by this server
  • get_study_statistics — The get_study_statistics tool exposed by this server
  • get_full_studies_and_save — The get_full_studies_and_save tool exposed by this server
  • load_csv_data — The load_csv_data tool exposed by this server
  • list_saved_csv_files — The list_saved_csv_files tool exposed by this server

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch ClinicalTrials.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. ClinicalTrials's toolset — Claude, Cursor, Windsurf and 7 more — is a fair guide to whether it matches your workflow. It is maintained by JackKuo666; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
ClaudeThe Claude tool exposed by this server.
CursorPaste the following into Settings → Cursor Settings → MCP → Add new server: - Mac/Linux s npx -y @smithery/cli@latest run ClinicalTrials-mcp-server --client cursor --config "{}"
WindsurfThe Windsurf tool exposed by this server.
CLineThe CLine tool exposed by this server.
get_full_study_detailsThe get_full_study_details tool exposed by this server.
get_studies_by_keywordThe get_studies_by_keyword tool exposed by this server.
get_study_statisticsThe get_study_statistics tool exposed by this server.
get_full_studies_and_saveThe get_full_studies_and_save tool exposed by this server.
load_csv_dataThe load_csv_data tool exposed by this server.
list_saved_csv_filesThe list_saved_csv_files tool exposed by this server.

How to install the ClinicalTrials MCP server

{
  "mcpServers": {
    "ClinicalTrials": {
      "command": "python",
      "args": ["-m", "ClinicalTrials-mcp-server"]
      }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use ClinicalTrials to Claude.
  • Use ClinicalTrials to Cursor.
  • Use ClinicalTrials to Windsurf.

Frequently asked questions

It connects ClinicalTrials to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Claude, Cursor, Windsurf, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with ClinicalTrials directly.