codebase-memory-mcp vs ferret-mcp
MCP codebase analysis tools compared
codebase-memory-mcp and ferret-mcp expose codebase analysis through the Model Context Protocol for use by AI assistants. The first builds a persistent local graph for structural queries, while the second combines static inspection with optional LLM-powered reports and answers.
codebase-memory-mcp: Build a Searchable Code Knowledge Graph
A local MCP server that indexes repositories into a persistent graph of code structure and relationships. It helps AI coding agents answer architectural and code-navigation questions with focused queries instead of repeated file searches.
ferret-mcp: Analyze Codebases Through MCP
Ferret MCP gives AI assistants static codebase analysis and optional LLM-powered reports about architecture, dependencies, patterns, and APIs. It suits developers exploring unfamiliar repositories, but its quiet, single-contributor project status is worth weighing before relying on it in a team workflow.
| codebase-memory-mcp | ferret-mcp | |
|---|---|---|
| Language | C | Python |
| License | MIT | MIT |
| Stars | 45.7k | 0 |
| Forks | 3.8k | 0 |
| Last analyzed | Oct 3, 2026 | Oct 9, 2026 |
Key differences
- codebase-memory-mcp stores code relationships in a local SQLite graph; ferret-mcp analyzes repository structure, dependencies, conventions, and interfaces.
- codebase-memory-mcp supports graph queries, call tracing, change-impact analysis, and semantic and full-text search; ferret-mcp offers static summaries and extraction reports, plus LLM-powered deep analysis and question answering.
- codebase-memory-mcp is written in C and uses bundled tree-sitter grammars with Hybrid LSP semantic type resolution for supported languages; ferret-mcp is written in Python and specifies Python 3.12 or newer.
- codebase-memory-mcp supports automatic change detection and re-indexing, cross-service route and call links, and indexing Dockerfiles and Kubernetes resources; ferret-mcp focuses on repository analysis and identifies interfaces such as REST, GraphQL, and gRPC.
- Both projects use the MIT license and are not archived. Their listed GitHub counts differ: codebase-memory-mcp has 45.7k stars and 3.8k forks, while ferret-mcp has 0 stars and 0 forks.
Choose codebase-memory-mcp if you…
- need a persistent local graph to trace calls, relationships, and potential change impact.
- want structural, semantic, or full-text queries, including links across services.
- prefer one-shot CLI access or an optional browser-based graph visualization alongside MCP integrations.
Choose ferret-mcp if you…
- want repository summaries covering architecture, dependencies, conventions, tests, and interfaces.
- need static analysis without an LLM, with optional LLM-backed reports and codebase questions.
- want a Python MCP server that identifies API surfaces including REST, GraphQL, gRPC, and CLI commands.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.