mcpField
M
Memory for AI

Memory for AI

Local
github.comMemory & Knowledge
RepositoryVisit website

About Memory for AI

Memory for AI is a local MCP server that builds persistent codebase graphs for AI coding agents. It combines tree-sitter parsing with type resolution to answer structural questions through graph queries rather than repeated file-by-file reading.

Key features

  1. 01Persistent codebase knowledge graph
  2. 02Parsing for 162 languages
  3. 03Type-aware relationship resolution
  4. 0423 MCP tools for graph queries
  5. 05Background re-indexing on changes
  6. 06One-shot CLI access to tools

Use cases

  1. 01Trace callers and callees across files
  2. 02Inspect architecture, routes, and packages
  3. 03Find dead code and complexity hotspots
  4. 04Compare graph queries with file-based exploration

MCP support

The server exposes 23 tools for indexing and querying codebase graphs to MCP clients. Each tool is also available as a one-shot local CLI command.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
npmmemory-for-ai-mcp0.11.0
pypimemory-for-ai0.11.0
mcpbmemory-for-ai-darwin-amd64.mcpb0.11.0
mcpbmemory-for-ai-darwin-arm64.mcpb0.11.0
mcpbmemory-for-ai-linux-amd64-portable.mcpb0.11.0
mcpbmemory-for-ai-linux-arm64-portable.mcpb0.11.0
mcpbmemory-for-ai-windows-amd64.mcpb0.11.0
mcpbmemory-for-ai-windows-arm64.mcpb0.11.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.