code-search-mcp
Verified Safeby suvaidkhan
Overview
A high-performance semantic code search server that enables intelligent code discovery through natural language queries within a specified codebase.
Installation
./code-search-mcp --path /path/to/your/projectEnvironment Variables
- OPENAI_API_KEY
- CODE_SEARCH_WORKSPACE_ROOT
Security Notes
The server is designed to index a user-specified local codebase (`--path` flag or `CODE_SEARCH_WORKSPACE_ROOT` environment variable). Running it in an untrusted environment or pointing it to sensitive directories could lead to unintended data exposure if the server's API (localhost:8080 by default) is externally accessible without proper access controls. The `internal/fs` package executes the `git check-ignore` command, which involves external process execution, though the paths are controlled by the configured workspace. The OpenAI API key (OPENAI_API_KEY) is required and must be kept secure via environment variables.
Similar Servers
chunkhound
Provides local-first codebase intelligence, extracting architecture, patterns, and institutional knowledge for AI assistants.
codegraph-rust
Transforms codebases into a semantically searchable knowledge graph, enabling AI agents to reason about code relationships, architecture, and impact rather than just performing text-based searches.
semantic-code-search-mcp-server
This MCP server exposes indexed code data to AI coding agents, enabling structured interaction for codebase understanding, code discovery, symbol analysis, and file content reconstruction.
kgraph
Indexes codebases into a knowledge graph to enable semantic search, precise code navigation, and impact analysis for LLM agents.