Project MCP Server

Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.

Local serverstdioGo

What is the Project MCP server?

Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo. The project mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 5 defined tools rather than through you.

What it actually does

A small, local MCP server that gives AI agents (Claude Code, Cursor, VS Code / GitHub Copilot, …) a shared, persistent memory of the projects in a code folder — what each project is, decisions made, and every bug/issue faced during development.

Its toolset

Everything the assistant can do here goes through one of these:

  • remember_preference — turn a correction / stated habit into a remembered pattern (## Preferences in the root AGENTS.md for a global habit, or a project's for a local one)
  • log_issue — record a bug/problem → issues.jsonl
  • search_issues — "have we hit this before?" across all projects (field-scoped; optional tags filter)
  • sync_registry — reconcile the root AGENTS.md projects table with what's on disk (adds rows for new projects, flags stale ones)
  • find_by_file — given a file path, surface the issues + decisions/learnings that touch it ("why is this code like this?")

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @kaaustubh/project-memory-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Project's toolset — remember_preference, log_issue, search_issues and 2 more — is a fair guide to whether it matches your workflow. It is maintained by kaaustubh; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the project mcp server does with a few real requests.

Available tools

ToolWhat it does
remember_preferenceturn a correction / stated habit into a remembered pattern (## Preferences in the root AGENTS.md for a global habit, or a project's for a local one); rides the auto-load, so it comes back next session
log_issuerecord a bug/problem → issues.jsonl
search_issues"have we hit this before?" across all projects (field-scoped; optional tags filter)
sync_registryreconcile the root AGENTS.md projects table with what's on disk (adds rows for new projects, flags stale ones)
find_by_filegiven a file path, surface the issues + decisions/learnings that touch it ("why is this code like this?")

How to install the Project MCP server

{
  "mcpServers": {
    "project-memory": {
      "command": "npx",
      "args": ["-y", "@kaaustubh/project-memory-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Project to remember preference.
  • Use Project to log issue.
  • Use Project to search issues.

Frequently asked questions

It connects Project to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (remember_preference, log_issue, search_issues, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Project directly.