{"name":"Ferret MCP: AI-Powered Knowledge Extraction for Any Codebase","description":"Ferret MCP is an MCP server designed to extract comprehensive knowledge from any codebase, combining static analysis with AI-powered deep interpretation. It provides detailed insights into architecture, patterns, dependencies, and API surface, delivering a senior engineer's analysis in seconds. This tool integrates seamlessly with various MCP clients, offering both free static analysis and advanced AI-driven reports.","github":"https://github.com/fabdendev/ferret-mcp","url":"https://osrepos.com/repo/fabdendev-ferret-mcp","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/fabdendev-ferret-mcp","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/fabdendev-ferret-mcp.md","json":"https://osrepos.com/repo/fabdendev-ferret-mcp.json","topics":["python","code-analysis","llm","architecture","knowledge-extraction","mcp-server","developer-tools","reverse-engineering"],"keywords":["python","code-analysis","llm","architecture","knowledge-extraction","mcp-server","developer-tools","reverse-engineering"],"stars":null,"summary":"Ferret MCP is an MCP server designed to extract comprehensive knowledge from any codebase, combining static analysis with AI-powered deep interpretation. It provides detailed insights into architecture, patterns, dependencies, and API surface, delivering a senior engineer's analysis in seconds. This tool integrates seamlessly with various MCP clients, offering both free static analysis and advanced AI-driven reports.","content":"## Introduction\n\nFerret MCP is an innovative [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that revolutionizes how developers understand complex codebases. It's engineered to extract complete knowledge, covering everything from architecture and design patterns to dependencies and API surfaces. By combining robust static analysis with advanced AI interpretation, Ferret MCP provides a deep, expert-level understanding of any repository.\n\nThis powerful tool integrates effortlessly with popular MCP clients like Claude Code, Claude Desktop, and Cursor, allowing you to get a senior engineer's analysis of a repository in approximately 30 seconds for a minimal cost.\n\n## Why Use Ferret MCP & Key Benefits\n\nFerret MCP addresses the challenge of quickly grasping unfamiliar or complex codebases, offering a suite of features that enhance developer productivity and understanding:\n\n*   **Comprehensive Codebase Understanding**: Get a holistic view of a project's structure, logic, and underlying principles without manual deep dives.\n*   **Dual Analysis Approach**: Benefit from both free, no-LLM-required static analysis tools (e.g., `scan`, `dependencies`, `architecture`, `patterns`, `api_surface`, `full_extraction`) and powerful AI-powered insights.\n*   **AI-Powered Deep Dives**: The `deep` tool generates a 10-section Knowledge Extraction Report, offering an expert analysis that includes an Executive Summary, Architecture Deep Dive, Technology Stack & Rationale, Data & Control Flow, Design Patterns, API & Interface Contracts, Key Files Reading Guide, Strengths, Risks & Technical Debt, and Learning Takeaways.\n*   **Interactive Q&A**: Use the `ask` tool to pose any question about a repository and receive answers grounded in the full codebase context.\n*   **Cost-Effective**: AI-powered reports are highly affordable, costing around $0.09 per report when using models like Claude Haiku.\n*   **Flexible LLM Integration**: Configure Ferret MCP to work with various LLM providers, including Anthropic, OpenAI-compatible services, and local LLMs like Ollama.\n\n## Installation\n\nGetting started with Ferret MCP is straightforward. You can install and run it with `uvx` without needing to clone the repository, or via `pip`.\n\n### Install & run with uvx (no clone needed)\n\nbash\nuvx ferret-mcp\n\n\n### Or install with pip\n\nbash\npip install ferret-mcp\n\n\n## Examples\n\nFerret MCP is designed to work seamlessly with any MCP client. Here's how to set it up and enable its AI capabilities.\n\n### Claude Code Setup\n\nTo add Ferret MCP to Claude Code:\n\nbash\nclaude mcp add ferret -- uvx ferret-mcp\n\n\nTo enable AI-powered tools (`deep`, `ask`), set your API key:\n\nbash\nclaude mcp add ferret -e FERRET_LLM_API_KEY=sk-ant-... -- uvx ferret-mcp\n\n\n### Claude Desktop / Cursor / Any MCP Client\n\nAdd the following configuration to your MCP config file (e.g., `claude_desktop_config.json`, `.cursor/mcp.json`):\n\n\n{\n  \"mcpServers\": {\n    \"ferret\": {\n      \"command\": \"uvx\",\n      \"args\": [\"ferret-mcp\"],\n      \"env\": {\n        \"FERRET_LLM_API_KEY\": \"sk-ant-...\"\n      }\n    }\n  }\n}\n\n\n### Use with a Local LLM (Ollama)\n\nFerret MCP can also be configured to use local LLMs, such as those provided by Ollama:\n\nbash\nclaude mcp add ferret \\\n  -e FERRET_LLM_PROVIDER=openai \\\n  -e FERRET_LLM_BASE_URL=http://localhost:11434/v1 \\\n  -e FERRET_LLM_MODEL=qwen3:8b \\\n  -- uvx ferret-mcp\n\n\n## Links\n\n*   **GitHub Repository**: [fabdendev/ferret-mcp](https://github.com/fabdendev/ferret-mcp){:target=\"_blank\"}\n*   **PyPI**: [ferret-mcp](https://pypi.org/project/ferret-mcp){:target=\"_blank\"}","metrics":{"detailViews":3,"githubClicks":1},"dates":{"published":null,"modified":"2026-09-14T12:22:17.000Z"}}