Bio-Agents MCP

MCP servers for Protein Data Bank, ChemBL, and other life science data (WIP), with Ollama client for local testing.

Catalog onlyCatalog onlySTDIO

Overview

Bio-Agents MCP is a collection of microservices and clients designed for natural language interaction with biological databases, including the Protein Data Bank and ChEMBL.

To use Bio-Agents MCP, configure your environment, start the services using Docker, and launch the web interface to begin querying biological data.

Natural language interface for biological databases - Support for Protein Data Bank and ChEMBL APIs - Modular architecture allowing independent service operation - Built using the FastMCP framework for asynchronous operations

Querying structural data from the Protein Data Bank.
Accessing chemical data from ChEMBL.
Interacting with biological data using natural language queries.

Add to your AI client

Use these steps to connect Bio-Agents MCP in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "bio-agents-mcp-dogeplusplus": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "bio-agents-mcp-dogeplusplus": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "bio-agents-mcp-dogeplusplus": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "bio-agents-mcp-dogeplusplus": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bio-agents-mcp-dogeplusplus": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "bio-agents-mcp-dogeplusplus": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-bio-agents-mcp-dogeplusplus"
      ]
    }
  }
}

FAQ

What databases does Bio-Agents MCP support?

Bio-Agents MCP currently supports the Protein Data Bank and ChEMBL databases.

How do I start using the service?

Follow the quick start guide to configure your environment and launch the services.

Is there documentation available?

Yes, each module has its own README with detailed documentation.

Research and data