Projectmem MCP Server

Local-first memory + judgment layer for AI coding agents — warns before repeating failed fixes.

Local serverstdioPython

What is the Projectmem MCP server?

If you already use Projectmem, the projectmem mcp server is the piece that lets your assistant work with it directly. Local-first memory + judgment layer for AI coding agents — warns before repeating failed fixes.

What the server does

We don't make AI smarter. We make it experienced. AI coding memory — the local-first memory + judgment layer for AI coding agents. Save up to 50%+ of AI tokens. Stop repeating yesterday's bug.

projectmem is an open-source agent memory layer built for that job. It is local-first: memory lives in a plain .projectmem/ directory inside your repository, with no cloud, no account and no telemetry. A native MCP server exposes 15 tools to Claude Code, Claude Desktop, Cursor, Antigravity and Codex, so your agent reads memory and logs its work on its own.

  • Session-Start Briefing — (new in 0.1.4) — pjm brief answers "where was I?" in one screen: active warnings, possibly-stale memories, open issues, recent decisions, stack gotchas, and your prevention score with a week-over-week delta
  • Smart Context Injection — — pjm wrap claude (or cursor/aider) injects a token-budgeted memory block into your AI before the session opens. Your AI starts experienced, not blank
  • Provable ROI Score — — pjm score outputs a letter grade (A+ → F) backed by concrete numbers — debugging hours saved, tokens prevented, dollars protected. CI-friendly JSON output and shields.io badge for your README
  • Cross-Project Memory — — Lessons learned in one repo follow you forever. Library gotchas, decisions, and patterns live in ~/.projectmem/global/ and auto-inherit into every new project that matches your stack
  • Real-time File Watcher — — Background daemon detects rapid edits to the same file (debugging sessions) between commits. Battery-aware, gitignore-aware, auto-started by pjm init
  • 100% Local — — No cloud, no telemetry, no accounts. Your code, your memory, your machine

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Pre — Commit Warnings** — pjm precheck warns you before you commit if you're about to repeat a failed approach, modify a high-churn file, or touch an
  • Stale — Memory Detection** (new in 0.1.4) — other memory tools silently decay or delete old memories; projectmem never deletes. Every decision that
  • Session — Start Briefing** (new in 0.1.4) — pjm brief answers "where was I?" in one screen: active warnings, possibly-stale memories, open issues, recent
  • Cross — Project Memory** — Lessons learned in one repo follow you forever. Library gotchas, decisions, and patterns live in ~/.projectmem/global/ and
  • Real — time File Watcher** — Background daemon detects rapid edits to the same file (debugging sessions) between commits. Battery-aware, gitignore-aware
  • macOS — ** Claude menu → Settings… → Developer tab → Local MCP serversEdit Config
  • Doc — What's in it
  • Capabilityprojectmem
  • Price — ✅ Free · MIT
  • Cursor — Two ways to register the MCP server — pick whichever fits your workflow:
  • Antigravity — 1. Open the Agent window (the chat panel on the right). 2. Click the ⋯ Additional Options button in the panel header. 3. Choose **MCP
  • Codex — Codex stores MCP config as TOML (not JSON) in ~/.codex/config.toml. There's a UI form at Settings → MCP Servers → Add MCP Server, but during

Installation

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

Where it fits

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Projectmem's toolset — Pre, Stale, Session and 9 more — is a fair guide to whether it matches your workflow. It is maintained by Ripon Chandra Malo; 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.

Worth knowing first

  • 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.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Projectmem.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
PreCommit Warnings** — pjm precheck warns you *before* you commit if you're about to repeat a failed approach, modify a high-churn file, or touch an unresolved issue. No other AI tool does this — it requires the memory laye
StaleMemory Detection** *(new in 0.1.4)* — other memory tools silently decay or delete old memories; projectmem **never deletes**. Every decision that cites a file is cross-checked against that file's git history — when the f
SessionStart Briefing** *(new in 0.1.4)* — pjm brief answers "where was I?" in one screen: active warnings, possibly-stale memories, open issues, recent decisions, stack gotchas, and your prevention score with a week-over-week
CrossProject Memory** — Lessons learned in one repo follow you forever. Library gotchas, decisions, and patterns live in ~/.projectmem/global/ and auto-inherit into every new project that matches your stack.
Realtime File Watcher** — Background daemon detects rapid edits to the same file (debugging sessions) between commits. Battery-aware, gitignore-aware, auto-started by pjm init.
macOS** Claude menu → Settings… → Developer tab → **Local MCP servers** → **Edit Config**.
DocWhat's in it
Capability**projectmem**
Price✅ Free · MIT
CursorTwo ways to register the MCP server — pick whichever fits your workflow:
Antigravity1. Open the **Agent** window (the chat panel on the right). 2. Click the **⋯ Additional Options** button in the panel header. 3. Choose **MCP Servers** → **Manage MCP Servers** → **Add new** (or **Edit Config**).
CodexCodex stores MCP config as **TOML** (not JSON) in ~/.codex/config.toml. There's a UI form at Settings → MCP Servers → Add MCP Server, but during cross-client verification the form's **Save button didn't reliably persist*

How to install the Projectmem MCP server

{
  "mcpServers": {
    "projectmem": {
      "command": "uvx",
      "args": ["projectmem"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Projectmem to Pre.
  • Use Projectmem to Stale.
  • Use Projectmem to Session.

Frequently asked questions

It connects Projectmem to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (Pre, Stale, Session, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Projectmem directly.