mcp-net-bridge
Local Network Request MCP Server
Documentation
Local Network Request MCP Server
An MCP server that sends HTTP requests to endpoints on your local network.
Features
- Send HTTP requests (GET, POST, PUT, DELETE, etc.) to local network endpoints
- Support for JSON payloads and custom headers
- Comprehensive error handling for timeouts and connection issues
- Built with FastMCP framework
Setup
1. Install dependencies:
uv sync2. Test the server:
uv run python3 main.pyConnecting to Claude
Add this configuration to your Claude MCP settings:
Using Claude Desktop
Add to your `claude_desktop_config.json`:
{
"mcpServers": {
"local-network-requests": {
"command": "uv",
"args": ["run", "python3", "/absolute/path/to/main.py"],
"cwd": "/Users/kazikgolinski/Documents/Projekty_priv/MPCtoAPI"
}
}
}Using Claude CLI
Add the MCP server:
claude mcp add local-network-requests uv run python3 /Users/kazikgolinski/Documents/Projekty_priv/MPCtoAPI/main.pyOr find your uv path and use it:
which uv
claude mcp add local-network-requests /full/path/to/uv run python3 /Users/kazikgolinski/Documents/Projekty_priv/MPCtoAPI/main.pyUsage
Once connected, you can use the `send_request` tool:
- url: Target endpoint (e.g., "http://192.168.1.245:8000")
- method: HTTP method (default: "POST")
- payload: JSON data for POST/PUT or query params for GET
- headers: Optional HTTP headers
- timeout: Request timeout in seconds (default: 30)
Example
Send a POST request to http://192.168.1.100:8080 with JSON payload {"action": "status"}Frequently asked questions
What is mcp-net-bridge?
mcp-net-bridge is Local Network Request MCP Server
How do I install mcp-net-bridge?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-net-bridge open source?
Yes — it is hosted on GitHub at https://github.com/KazikGolinski/mcp-net-bridge.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP