mcpField
A
Appendix

Appendix

Remote
appendix.comAI & Agents2Updated 2w ago

About Appendix

Appendix is an MCP server for agents handling health conversations. It searches medical literature and submits clinical encounters for review by a board-certified physician, who may provide a prescription when appropriate.

Key features

  1. 01Search medical literature and guidelines
  2. 02Submit encounters for physician review
  3. 03List conditions and medications

Use cases

  1. 01Find evidence for a health conversation
  2. 02Request physician review of a clinical letter

MCP support

The server exposes literature search, encounter submission, and condition and medication lookup tools to MCP clients. Physician guidance and prescriptions may follow clinical review when appropriate.

Configuration

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

Endpointhttps://mcp.appendix.com/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

3
ParameterTypeRequiredDescription
querystringYesSearch query (clinical topic or question)
limitintegerNoMax results to return (1-10, default 5)

Details

From the project README

Appendix MCP Server

Appendix turns any AI health conversation into a physician-reviewed opinion, with a prescription if you need one.

Your agent writes a medical encounter summary, submits it through our API, and a real doctor signs off.

Use the Appendix MCP server to search medical literature, submit clinical encounters, and receive clinical guidance and prescriptions from board-certified physicians. Learn more at appendix.com.

Installation

Claude Code
claude mcp add --transport http appendix https://mcp.appendix.com/mcp
Claude Desktop / Claude Web Connectors

Add to your Claude Desktop config (claude_desktop_config.json) or Claude.ai custom-connector form:

{
  "mcpServers": {
    "appendix": {
      "url": "https://mcp.appendix.com/mcp"
    }
  }
}
Other clients
ClientURL
Claude Code, Claude Desktop, Claude.ai connectorshttps://mcp.appendix.com/mcp
Anthropic Messages API (mcp_servers)https://mcp.appendix.com/mcp

The server speaks Streamable HTTP only — the current MCP spec transport (2025-03-26).

Available Tools

ToolDescription
search_knowledge_baseSearch medical literature and treatment guidelines
submit_encounterSubmit a clinical letter for physician review
list_conditionsList available conditions and medications

Development

npm install
npm run build
npm start

Watch mode:

npm run dev

Environment Variables

VariableDefaultDescription
API_BASE_URLhttps://api.appendix.comAppendix API base URL
PORT3001HTTP listener port

Endpoints

MethodPathPurpose
GET/healthHealth probe for the hosting platform
POST GET DELETE/mcpStreamable HTTP transport (stateless mode)

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.