{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_9x2rs99qqyjy","handle":"agent-architects-studio-gitmem-mcp","url":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp","links":{"self":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp/record.json","html":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp","markdown":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agent-architects-studio-gitmem-mcp","status":"https://wellknown.network/api/v1/agents/agent-architects-studio-gitmem-mcp/status","claim":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp/claim.json","badge":"https://wellknown.network/agents/agent-architects-studio-gitmem-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agent-architects-studio-gitmem-mcp/history","tools":"https://wellknown.network/api/v1/agents/agent-architects-studio-gitmem-mcp/tools"},"ard":{"identifier":"urn:air::server:agent-architects-studio-gitmem-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"gitmem-mcp","summary":"GitMem MCP Server - Token-Efficient Codebase Navigation for AI Agents","description":"# GitMem MCP (Manhattan)\n\n**Token-Efficient Codebase Navigation** - MCP Server for the Manhattan Memory System.\n\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nGitMem MCP is a local [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that provides AI agents (Claude Desktop, Cursor, Windsurf, etc.) with a **Virtual File System (VFS)** backed by compressed, cached code context. It allows agents to understand large codebases while saving 50-80% on tokens.\n\n## Features\n\n- 🏗️ **GitMem Context** - Compressed semantic code skeletons (signatures, summaries, hierarchies).\n- 🔍 **Hybrid Search** - Semantic and keyword search across the entire codebase.\n- 📂 **VFS Navigation** - Browse and read files via token-efficient outlines and contexts.\n- 📝 **Auto-Indexing** - Automatically keeps the code index fresh after edits.\n- 📊 **Token Analytics** - Track token savings and repository indexing status.\n\n## Installation\n\n```bash\npip install gitmem-mcp\n```\n\n## Quick Start\n\n### 1. Install GitMem MCP\n\n```bash\npip install gitmem-mcp\n```\n\n### 2. Configure Your AI Client\n\nSetting up GitMem MCP is a two-step process:\n\n#### Step A: Register the Server (One-time)\nAdd GitMem MCP to your AI tool's global settings.\n\n**Claude Desktop**\nAdd to `claude_desktop_config.json`:\n```json\n{\n  \"mcpServers\": {\n    \"gitmem_mcp\": {\n      \"command\": \"gitmem\",\n      \"args\": [\"start\"],\n      \"env\": {\n        \"MANHATTAN_API_URL\": \"https://www.themanhattanproject.ai\"\n      }\n    }\n  }\n}\n```\n\n**Cursor**\nAdd to Cursor Settings > MCP:\n- Name: `gitmem_mcp`\n- Type: `command`\n- Command: `gitmem start`\n- Env:\n  - `MANHATTAN_API_URL`: `https://www.themanhattanproject.ai`\n\n**VS Code / GitHub Copilot**\nAdd to `mcp.json` or your MCP settings:\n```json\n{\n  \"servers\": {\n    \"gitmem_mcp\": {\n      \"command\": \"gitmem\",\n      \"args\": [\"start\"],\n…","publisher":{"name":"Agent Architects Studio","url":null},"homepage":"https://themanhattanproject.ai/mcp-docs","repository":null,"version":"0.0.3","license":"MIT","protocols":["mcp"],"tags":["mcp","gitmem","memory","ai","agent","llm","claude","manhattan"],"pricing":null,"endpoints":[{"url":"pypi:gitmem-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":1,"provenance":"derived"},{"slug":"knowledge.memory","name":"Agent Memory","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"}],"categories":["dev","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"gitmem-mcp","registry":"pypi","observedAt":"2026-09-15T15:24:51.801Z","publishedAt":"2026-05-05T18:34:20.105708Z","latestVersion":"0.0.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"gitmem-mcp","url":"https://pypi.org/project/gitmem-mcp/","firstSeenAt":"2026-09-09T16:24:01.884Z","fetchedAt":"2026-09-15T15:23:21.988Z","normalizedAt":"2026-09-15T15:23:21.988Z"}]},"firstSeenAt":"2026-09-09T16:24:01.884Z","updatedAt":"2026-09-15T15:24:51.801Z"}