whistle
A Whistle proxy management tool based on Model Context Protocol that allows AI assistants to directly control local Whistle proxy servers, simplifying network debugging, API testing, and proxy rule configuration through natural language interaction.
claude mcp add --transport stdio 7gugu-whistle-mcp whistle-mcp --host=<whistle server IP address> --port=<whistle server port number>
How to use
Whistle MCP Server exposes a set of MCP tools that let AI assistants manage and monitor a local Whistle proxy without manual interaction with the Whistle UI. You can query, create, update, and organize rules, groups, and values; control the proxy and HTTPS interception; view intercepted requests; and replay or modify requests. The tools are designed to be called through the MCP protocol, enabling automation and natural language-driven proxy management. Start by pointing the MCP server at your running Whistle instance, then use the provided tool set to perform tasks such as creating a rule for a specific URL, grouping related rules, enabling or disabling proxy features, and replaying captured requests with custom parameters.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- A Whistle proxy server running locally or accessible from the same environment
Installation steps:
- Install the MCP tool globally via npm:
npm install -g whistle-mcp-tool
- (Optional) If you plan to use Smithery for automatic installation, you can install via Smithery per the project’s guidance. This is not required for basic MCP operation.
- Ensure Whistle is running and accessible on your host/port you configure in the MCP JSON configuration (default host is localhost and default port is 8899 for Whistle).
- Prepare your MCP JSON configuration file (see the example in the repository) and point your MCP client to the whistle-mcp server name you configured.
Additional notes
Tips and common considerations:
- Defaults: host defaults to localhost and port defaults to 8899 if you don’t override them in the command line.
- Ensure network access between the MCP server and your Whistle instance; if Whistle is on a different host, use the appropriate --host and --port values.
- Tools are organized by category (Rule, Group, Value, Proxy, Request). Use them to script common workflows like deploying a baseline rule set, grouping related rules, or enabling multi-rule mode.
- If you encounter authentication or connection issues, verify that Whistle is running, the port is correct, and no firewall blocks the connection.
- You can combine multiple tool calls in sequence to implement complex debugging and automation tasks.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.