Vectr

Semantic codebase search + persistent working memory for AI code editors. Local, no API key.

Python Local macOSWindowsLinux

★ 2 stars Last pushed 2026-09-06 License: MIT

View repository → Website →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

uvx vectr

Or add to your MCP client config:

{
  "mcpServers": {
    "vectr": {
      "command": "uvx",
      "args": [
        "vectr"
      ]
    }
  }
}

This server takes extra arguments — see its repository.

Package: pypi vectr

VECTR_PORT — Port the local vectr daemon serves MCP on. Start the daemon with `vectr start` before connecting.

Helps agents write and test Storybook stories for UI components.

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

Official PostHog MCP Server for product analytics, feature flags, experiments, and more.

Task management for AI-driven development: PRD parsing, task expansion, multi-provider support and selective tool loading to save context.

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

MCP server for iOS and Android Mobile Development, Automation and Testing

Data from the Official MCP Registry