Ferret MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FERRET_LLM_MODEL | No | Model name | claude-haiku-4-5-20251001 |
| FERRET_LLM_API_KEY | No | API key for Anthropic (required for Anthropic provider) | |
| FERRET_LLM_BASE_URL | No | Base URL for OpenAI-compatible providers | http://localhost:11434/v1 |
| FERRET_LLM_PROVIDER | No | LLM provider: anthropic or openai (for Ollama, vLLM, LM Studio) | anthropic |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scanB | Scan a repository and return an overview: languages, file structure, entry points, config files. Args: path: Absolute path to the repository root directory. |
| dependenciesA | Extract all dependencies — external packages and internal import graph with core modules. Args: path: Absolute path to the repository root directory. |
| architectureB | Analyze repository architecture — layers, patterns (MVC, hexagonal, pipeline, etc.), module breakdown. Args: path: Absolute path to the repository root directory. |
| patternsB | Detect code patterns and conventions — design patterns, naming, testing, error handling, config. Args: path: Absolute path to the repository root directory. |
| api_surfaceA | Extract the complete API surface — REST endpoints, MCP tools, CLI commands, GraphQL, gRPC, public exports. Args: path: Absolute path to the repository root directory. |
| full_extractionA | Run ALL analyses and return a comprehensive knowledge extraction report. Combines: scan, dependencies, architecture, patterns, and API surface into a single document. Use this for complete repo understanding. Args: path: Absolute path to the repository root directory. |
| deepB | AI-powered deep analysis — produces a comprehensive Knowledge Extraction Report. Uses an LLM (Anthropic or local) to analyze all static extraction data plus key file contents, producing an expert-level architectural analysis with insights about design decisions, data flow, strengths, risks, and learning path. Requires FERRET_LLM_API_KEY (for Anthropic) or a local LLM server. Configure via env vars: FERRET_LLM_PROVIDER, FERRET_LLM_MODEL, FERRET_LLM_BASE_URL. Args: path: Absolute path to the repository root directory. |
| askA | Ask a specific question about a repository, answered by AI with full codebase context. The LLM receives all static analysis data + key file contents, then answers your question based on that evidence. Requires FERRET_LLM_API_KEY (for Anthropic) or a local LLM server. Args: path: Absolute path to the repository root directory. question: The question you want answered about this codebase. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/fabdendev/ferret-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server