Sensegrep

Provides semantic and structural code search, indexing, and analytics via MCP for AI-assisted development.
  • typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

Sensegrep MCP Server exposes code intelligence capabilities to AI agents and clients via a standardized MCP interface. It enables semantic and structural code search, index management, statistics, duplicate detection, and language metadata retrieval so agents can understand and navigate large codebases efficiently.

How to use

You run the MCP server locally or in your development environment and connect using an MCP client. The server exposes a set of tools you can call through the MCP protocol, including search, indexing, statistics, duplicate detection, and language metadata. Use these endpoints to perform semantic searches, manage your code index, and gain actionable insights about your repository.

How to install

Prerequisites: ensure you have Node.js installed on your system. You will also need npm or a compatible package manager.

Install and run the MCP server using the provided command snippet. This starts the server in a way that MCP clients can communicate with it.

npx -y @sensegrep/mcp

Configuration and running locally

To configure the MCP server with your project root, include an MCP configuration that points to the local workspace. This enables the server to access your code for indexing and searching.

{
  "mcpServers": {
    "sensegrep": {
      "command": "npx",
      "args": ["-y", "@sensegrep/mcp"],
      "env": {
        "SENSEGREP_ROOT": "/path/to/your/project"
      }
    }
  }
}

Supported tools and endpoints

The MCP server provides the following tools to your clients.

Examples of available tools

  • sensegrep.search: perform a semantic or structural search over your codebase and return matching symbols or code blocks.

  • sensegrep.index: index a project or update the existing index to reflect new or changed files.

  • sensegrep.stats: retrieve index statistics, such as size, symbol counts, and quality metrics.

  • sensegrep.detect_duplicates: find potential duplicate or near-duplicate code blocks to streamline refactoring.

  • sensegrep.languages: obtain language metadata supported by the server, including identifiers and capabilities.

Security and access

Run the MCP server in a trusted environment and limit access to the machine or network. Use environment isolation and avoid exposing internal paths or credentials.

Troubleshooting

If the server fails to start, verify Node.js is installed, the MCP command is accessible, and the root path in SENSEGREP_ROOT points to an existing project. Check permissions and ensure there are no conflicting processes using the same port.

Available tools

sensegrep.search

Search code semantically or structurally, returning matching functions, classes, or blocks based on meaning and code structure.

sensegrep.index

Create or update the index for a project so future searches are fast and accurate.

sensegrep.stats

Retrieve statistics about the current index, including symbol counts and index health.

sensegrep.detect_duplicates

Identify potential duplicate or near-duplicate code blocks to assist refactoring.

sensegrep.languages

Provide metadata about supported languages and their features within the index.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational