AI-driven semantic code search as an MCP tool using Windsurf's reverse-engineered SWE-grep protocol.
fast-context-mcp is worth checking the docs before setup with trust notes worth reviewing. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view SammySnake-d/fast-context-mcp --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Fast Context MCP is a tool that lets you search code using natural language. It connects to an AI service that understands your query and finds relevant code files. It works with any MCP-compatible client like Claude Code or Cursor.
Fast Context MCP is an AI-driven semantic code search tool that implements the MCP (Model Context Protocol) standard. It uses a reverse-engineered version of Windsurf's SWE-grep protocol to enable natural language code search. The tool bundles all dependencies via npm, including ripgrep via @vscode/ripgrep and tree via tree-node-cli, so no system-level installations are required. It works on macOS, Windows, and Linux. The server maps your project to a /codebase directory, sends queries to the Windsurf Devstral API, which generates rg/readfile/tree commands. These commands are executed locally, and results are returned to the AI. The process repeats for multiple rounds to refine results. The tool returns file paths, line ranges, and suggested search keywords. It requires Node.js >= 18 and a Windsurf account (free tier works). Configuration is done via environment variables like WINDSURF_API_KEY, FC_MAX_TURNS, FC_MAX_COMMANDS, etc. The tool is published on npm as @sammysnake/fast-context-mcp.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 60 days ago.
264 GitHub stars indicate community interest.
3 open issues signal maintenance load.
MIT license detected.
Find authentication logic in a large codebase using natural language.
Locate all database-related functions without knowing exact file names.
Identify error handling patterns across multiple files.
Search for specific API endpoint implementations quickly.
Discover code related to a feature by describing it in plain English.
Sends code queries to Windsurf's external API; code snippets may be transmitted.
Requires a Windsurf API key; ensure it is kept secure.
The tool executes commands locally; review generated commands for safety.
264
Stars
39
Forks
3
Issues
MIT
License
Local codebase intelligence CLI and MCP server for AI coding agents with change-safety gates and audit evidence.
An offline MCP server that indexes your codebase for semantic search, code search, and git history retrieval.
Official MCP reference servers from Anthropic. Includes servers for filesystem, GitHub, Postgres, Slack, and more.
AI-driven semantic code search as an MCP tool using Windsurf's reverse-engineered SWE-grep protocol.
Full-stack developers working on large codebases., AI-assisted coding enthusiasts using MCP-compatible clients., Developers who prefer natural language queries over regex.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Sends code queries to Windsurf's external API; code snippets may be transmitted. Requires a Windsurf API key; ensure it is kept secure.
Similar or complementary options to evaluate include roam-code, code-memory, MCP Server Collection.
Jun 6, 2026
3 security/trust notes recorded.
Setup difficulty is 3/5.