Sensegrep MCP Server

Semantic + structural code search MCP server for AI-native development.

Local serverstdioPython

What is the Sensegrep MCP server?

Most developer tooling work still happens through a UI a human drives. Sensegrep MCP server moves it into the conversation instead. Semantic + structural code search MCP server for AI-native development.

The short version

sensegrep understands your code semantically. Instead of matching text patterns, it uses AI embeddings and tree-sitter AST parsing to find code by meaning - so you can search for "authentication logic" and actually find your auth functions, even if they never contain the word "authentication".

What it needs from you

Configuration is passed through the environment: SENSEGREP_PROVIDER, GEMINI_API_KEY, SENSEGREP_OPENAI_API_KEY, SENSEGREP_OPENAI_BASE_URL, SENSEGREP_EMBED_MODEL, SENSEGREP_EMBED_DIM, SENSEGREP_OPENAI_BATCH_SIZE, AWS_REGION. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

@sensegrep/mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. It is maintained by Stahldavid; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the Sensegrep MCP server

{
  "mcpServers": {
    "sensegrep": {
      "command": "npx",
      "args": ["-y", "@sensegrep/mcp"],
      "env": {
        "SENSEGREP_PROVIDER": "your-value",
        "GEMINI_API_KEY": "your-value",
        "SENSEGREP_OPENAI_API_KEY": "your-value",
        "SENSEGREP_OPENAI_BASE_URL": "your-value",
        "SENSEGREP_EMBED_MODEL": "your-value",
        "SENSEGREP_EMBED_DIM": "your-value",
        "SENSEGREP_OPENAI_BATCH_SIZE": "your-value",
        "AWS_REGION": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
SENSEGREP_PROVIDERConfiguration value read at startup.Optional
GEMINI_API_KEYCredential the server authenticates with.Yes
SENSEGREP_OPENAI_API_KEYCredential the server authenticates with.Yes
SENSEGREP_OPENAI_BASE_URLEndpoint or connection string the server talks to.Yes
SENSEGREP_EMBED_MODELConfiguration value read at startup.Optional
SENSEGREP_EMBED_DIMConfiguration value read at startup.Optional
SENSEGREP_OPENAI_BATCH_SIZEConfiguration value read at startup.Optional
AWS_REGIONConfiguration value read at startup.Optional

Frequently asked questions

It connects Sensegrep to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Sensegrep directly.