Get the FREE Ultimate OpenClaw Setup Guide →

Context-Engine

A production-ready TypeScript MCP server that provides comprehensive project analysis, intelligent code search, dependency tracking, and coordinated multi-file editing capabilities.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio raheesahmed-context-engine-mcp-server npx -y context-engine-mcp

How to use

Context Engine MCP Server provides a production-ready set of tools for analyzing TypeScript/JavaScript projects. It offers comprehensive project analysis, intelligent search with regex and structure awareness, multi-file editing with atomic operations and automatic backups, as well as dependency mapping and project health statistics. You can access these capabilities through a unified MCP client configuration, enabling workflows like deep code analysis, fast search across large codebases, safe multi-file edits, and insight into file relationships and imports. The server is designed to work with MCP clients via a simple JSON configuration, and can be run on-demand with npx or installed globally for repeated use. The included tools are:

  • analyze_project: perform a cached, in-depth analysis of a project’s structure and dependencies.
  • search_project: run powerful searches across files with optional structural awareness.
  • edit_multiple_files: apply coordinated changes across several files with optional backups.
  • get_file_relationships: generate dependency and import/export mappings.
  • get_project_stats: retrieve health metrics and statistics about the codebase.
  • clear_cache: reset cached data to ensure fresh analyses. Use these tools by sending the appropriate tool name and payload via the MCP client to the server.

How to install

Prerequisites:

  • Node.js 18.x or higher
  • npm (installed with Node.js)

Install and run via npx (no local install required):

  1. Ensure your environment has Node.js 18+ and npm.
  2. Use the MCP client configuration to point to the npx-based server:
{
  "mcpServers": {
    "context-engine": {
      "command": "npx",
      "args": ["-y", "context-engine-mcp"]
    }
  }
}

If you prefer a local development setup:

  1. Clone the repository:
git clone https://github.com/RaheesAhmed/Context-Engine-MCP-Server.git
cd Context-Engine-MCP-Server
  1. Install dependencies and build (if required by the project):
npm install
npm run build
  1. Point the MCP client to the local server command, e.g.:
{
  "mcpServers": {
    "context-engine": {
      "command": "node",
      "args": ["./dist/index.js"]
    }
  }
}

Optional global install:

npm install -g context-engine-mcp

Then configure:

{
  "mcpServers": {
    "context-engine": {
      "command": "context-engine-mcp"
    }
  }
}

Additional notes

Environment variables and configuration hints:

  • LOG_LEVEL controls verbosity (debug, info, warn, error).
  • CACHE_TTL sets caching duration in milliseconds.
  • MAX_FILE_SIZE limits analysis to files under a certain size. Troubleshooting tips:
  • Ensure Node.js 18+ is installed and accessible in your PATH.
  • When using npx, ensure you have an active internet connection for the initial fetch.
  • If using local builds, verify the compiled dist/index.js path matches your MCP client configuration.
  • If you see zero installation messages with npx, you can still rely on the prebuilt npx flow as shown in the Quick Start.

Related MCP Servers

Sponsor this space

Reach thousands of developers