Skip to main content
Glama

Claude Parallel Tasks MCP Server

README.md2.24 kB
# Claude Parallel Tasks MCP Server An MCP (Model Context Protocol) server that enables running multiple Claude prompts in parallel, with optional file contexts and output redirection. ## Features - Run multiple Claude prompts simultaneously in parallel - Provide file contexts to Claude prompts - Redirect output to individual files for each task - Built with TypeScript and the MCP SDK ## Prerequisites - Node.js and pnpm - Claude CLI tool installed and configured - Anthropic API key ## Setup 1. Clone the repository: ```bash git clone https://github.com/CaptainCrouton89/claude-code-mcp.git cd claude-code-mcp ``` 2. Install dependencies: ```bash pnpm install ``` 3. Set up your environment variables: ```bash cp .env.example .env.local ``` 4. Edit `.env.local` and add your Anthropic API key: ``` ANTHROPIC_API_KEY=your_anthropic_api_key_here ``` 5. Build the project: ```bash pnpm run build ``` ## Usage ### Running the Server ```bash pnpm start ``` ### Configuring with Claude Desktop Add the following to your `claude_desktop_config.json`: ```json { "mcpServers": { "claude-parallel": { "command": "node", "args": ["/path/to/claude-code-mcp/dist/index.js"], "env": { "ANTHROPIC_API_KEY": "your_anthropic_api_key_here" } } } } ``` ### Available Tools #### run_parallel_claude_tasks Runs multiple Claude prompts in parallel with optional file contexts. **Parameters:** - `queries`: Array of query objects, each containing: - `queryText`: The text prompt to send to Claude - `contextFilePaths` (optional): Array of file paths to provide as context **Example:** ```json { "queries": [ { "queryText": "Explain this code", "contextFilePaths": ["src/index.ts"] }, { "queryText": "Write a summary of this project", "contextFilePaths": ["README.md", "package.json"] } ] } ``` ## Development ```bash # Install dependencies pnpm install # Build the project pnpm run build # Run in development mode pnpm run dev ``` ## Security - API keys are stored in environment variables, not in code - The `.env.local` file is gitignored to prevent accidental commits - Use the provided `.env.example` as a template ## License MIT

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/CaptainCrouton89/claude-code-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server