Claude Connect

What is Claude Connect?

Claude Connect is an MCP-compliant external connector server that enables Large Language Models like Claude to interact with web APIs, filesystem, and custom resources in a standardized way. It is designed for developers and users who want to give LLMs access to web search, file operations, and custom tools. Version 1.1 (March 2025).

How to use Claude Connect?

Install Python 3.10+, create and activate a virtual environment, install dependencies (..\venv\Scripts\pip.exe install -r requirements.txt), rename .env.example to .env and add your API keys (Bing Search API required, Google Search API optional). Run the server in STDIO mode (..\venv\Scripts\python.exe main.py) or HTTP mode (..\venv\Scripts\python.exe main.py --http). Test with ..\venv\Scripts\pytest.exe. For Claude Desktop integration, follow the dedicated guide.

Key features of Claude Connect

• Web search integration (Bing required, Google optional)
• File operations within a secure sandbox
• Custom resources and prompt templates
• Multiple transport options (STDIO and HTTP with JWT)
• Extensible, modular architecture
• Cross‑platform (tested on Windows 10, Python 3.10+)

Use cases of Claude Connect

• Allow an LLM to fetch live web search results
• Let an LLM read and write files in a sandboxed directory
• Expose custom resource types and prompt templates to LLMs
• Deploy as a containerized service using Docker
• Integrate with Claude Desktop via STDIO for enhanced capabilities

FAQ from Claude Connect

What are the runtime requirements for Claude Connect?

Python 3.10 or higher is required. For search functionality, a Bing Search API key is mandatory; a Google Search API key is optional.

How do I run Claude Connect in different modes?

Run in STDIO mode with ..\venv\Scripts\python.exe main.py or in HTTP mode by adding the --http flag. HTTP mode supports optional JWT authentication.

Is there any security for file operations?

Yes. File operations are restricted to a sandbox directory, and the server prevents path traversal attempts to ensure secure access.

Can Claude Connect be deployed using containers?

Yes. A Dockerfile is provided (based on Python 3.11‑slim). Build with docker build -t claude-connect . and run with docker run -p 8000:8000 --env-file=.env claude-connect.

What transport options are available?

STDIO transport for integration with Claude Desktop and other MCP STDIO clients, and HTTP transport (optional JWT authentication) for development, testing, and web application integration.