Codebase Memory MCP logo

Codebase Memory MCP

Codebase Memory MCP AI Agent
Rating:
Rate it!

Overview

Open-source MCP server that indexes codebases into a persistent knowledge graph for fast structural queries by AI coding tools.

Codebase Memory MCP is an open-source code intelligence MCP server from DeusData. It indexes repositories into a persistent knowledge graph so compatible coding tools can query functions, classes, call chains, HTTP routes, and cross-service links with fewer tokens. The GitHub project describes support for tree-sitter AST analysis across 158 languages, hybrid LSP semantic type resolution for major languages including Python, TypeScript, JavaScript, PHP, C#, Go, C, C++, Java, Kotlin, and Rust, 14 MCP tools, and distribution as a single static binary for macOS, Linux, and Windows with zero dependencies.

Product overview

Capabilities, pricing and fit

Codebase Memory MCP is an open-source local code-intelligence backend for AI coding agents. It parses repositories into a persistent knowledge graph and exposes structural search, call tracing, architecture, impact, and related queries through MCP or a CLI; it contains no language model and is not itself an autonomous coding agent.

Information as of August 29, 2026

What it can do

  • Persistent code knowledge graph

    The native engine uses tree-sitter parsing and selected semantic type resolution to index functions, classes, call chains, routes, dependencies, and cross-service links across many languages.[1]

  • Structural analysis tools

    Its MCP and CLI surfaces cover architecture summaries, graph search, call tracing, impact analysis, dead-code detection, Cypher-like queries, semantic search, and a local graph visualization.[1]

  • Local multi-client operation

    The project ships native binaries and packages for macOS, Linux, and Windows and can connect to multiple supported coding-agent clients while keeping repository indexes local.[1], [3]

Where it fits best

  • Developers and coding-agent users who need fast structural understanding, call tracing, cross-service analysis, or persistent repository context without sending code to a hosted indexing service.[1]

Pricing and availability

The project is free, open source, and MIT-licensed. It has no hosted-service subscription or built-in model fee, although users still bear any cost of the separate coding agent or model they connect.[1]

Platforms: macOS, Linux, Windows, MCP-compatible coding agents, Local CLI, Local graph UI[1], [3]

Access: Local native binary, npm, PyPI, Homebrew, Scoop, Winget, Chocolatey, AUR, Go install, Source build[1], [3]

Important considerations
  • This is infrastructure rather than an agent: an MCP-compatible client supplies the language model, interprets requests, and presents results.[1]
  • The program reads source files, writes agent configuration, and can spawn background processes; its security policy explicitly asks users to assess whether those access patterns fit their environment.[2]
  • Core analysis stays local, but the MCP server performs a bounded background request to GitHub release metadata to check for updates unless the environment blocks it.[2]
Sources (3)
  1. DeusData/codebase-memory-mcpGitHub · checked 2026-08-29
  2. Codebase Memory MCP Security PolicyGitHub · checked 2026-08-29
  3. Codebase Memory MCP ReleasesChangelog · checked 2026-08-29

Autonomy level

18/100

Our subjective rating of how independently the product carries out its documented tasks, considering the human setup, input, approval and review it needs. This is not a measured success rate.

Reasoning: Codebase Memory MCP is implemented as a high-performance **code intelligence MCP server** that indexes a codebase into a persistent knowledge graph for use by external AI coding assistants such as Claude Code, Codex CLI, and ChatGPT. It acts as a backend service that parses code (via tree-sitter), builds a structural graph of functions, classes, ca...

Comparisons


Custom Comparisons

Some of the use cases of Codebase Memory MCP:

  • Indexing codebases into a persistent knowledge graph
  • Answering structural code questions through MCP tools
  • Reducing token usage during repository exploration
  • Finding functions, classes, call chains, routes, and cross-service links
  • Adding code intelligence to compatible coding assistants

Loading Community Opinions...

Pricing model:

Code access:

Popularity level: 65%

Codebase Memory MCP Video:

Free credibility widget

Turn this profile into a trust signal

Show prospects that Codebase Memory MCP has a public place where they can check product details, pricing, ratings, and reviews.

Build confidence

Give buyers a third-party profile to explore.

Reduce hesitation

Put validation beside your strongest CTA.

Earn discovery

Every badge links prospects to your listing.

Choose your style

Preview it, then copy the complete embed code.

Live previewReady to embed

Shows buyers where to validate your product, pricing, and reputation.

Plain HTML. No signup, script, or maintenance required.

AI Agent Store · Specialist AI agents

For in-house software product engineering teams

Your AI agent for codebase dependency investigations.

Exploring Codebase Memory MCP? For in-house software product engineering teams, your own AI agent can investigate product issues, implement and test changes, and ship and follow releases. Start with a setup tailored to this work.

  • ✓ Investigate product issues
  • ✓ Implement and test changes
  • ✓ Ship and follow releases
Explore this specialist AI agent

Tailored starting setup. Chat on our site. See the workflow and monthly plan.

Did you find this page useful?

Not useful
Could be better
Neutral
Useful
Loved it!