Global Agent Memory MCP Server

Global Agent Memory gives multiple coding agents one shared, reviewable memory without handing control of your knowledge base to a hosted service. Markdown files are canonical, an authenticated local MCP daemon is the public agent interface, and the dashboard lets a human approve, edit, protect, or remove what agents remember.

People connecting productivity tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-07-16 · ★ 13 · #81 OF 139 MAINTAINED PRODUCTIVITY · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Global Agent Memory

Claude Code

claude mcp add ozankasikci-global-agent-memory -- uvx global-memory-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "ozankasikci-global-agent-memory": {
      "command": "uvx",
      "args": [
        "global-memory-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-07-11 - young repo, little track record yet

license MIT - declared in the repository

pypi package global-memory-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.ozankasikci is GitHub-verified and matches the repo owner

03 · What Global Agent Memory can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.1.6 · 2026-07-16

Highlights · Keeps the daemon responsive while Ollama is offline or slow. · Runs semantic query embedding and background embedding reconciliation outside the daemon event loop. · Makes hybrid search and context…

v0.1.5 · 2026-07-15

Highlights · Restores the installed dashboard by resolving packaged assets from global_memory/_dashboard after backend modularization. · Adds regression coverage for /ui/ and freshly installed wheel assets. · Publishes…

v0.1.4 · 2026-07-13

Global Agent Memory v0.1.4 fixes long-lived MCP connections for Claude Code and Codex. · Fixed · Uses stateless Streamable HTTP requests so agent bridges cannot retain an expired MCP session. · Prevents the recurring…

04 · Who maintains Global Agent Memory

Global Agent Memory is maintained by ozankasikci. It's the only MCP server we track from this author; the repo dates to Jul 2026.

05 · Facts

repository: github.com/ozankasikci/global-agent-memory
website: https://github.com/ozankasikci/global-agent-memory
category: productivity - ranked #81 of 139 actively-maintained productivity servers as of 2026-08-25.
release cadence: 6 releases in the last 90 days (latest 2026-07-16)
registry: io.github.ozankasikci/global-agent-memory (active, first published 2026-07-14 · 3 versions)
packages: pypi:global-memory-mcp

06 · Global Agent Memory FAQ

What is Global Agent Memory?

Is Global Agent Memory still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-16 and it shipped 6 releases in the last 90 days. We re-verify nightly.

How do I install Global Agent Memory?

Run `uvx global-memory-mcp`. You can also paste the ready-made client config above.

Does Global Agent Memory run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Global Agent Memory

Alternatives to Global Agent Memory

Maintained productivity servers if Global Agent Memory isn't the fit.

Pairs well with

Servers that cover what Global Agent Memory doesn't - only shown when the pairing reason fits the companion.

More productivity MCP servers · Parallel Task MCP · P4plan MCP · Dav MCP · macOS Calendar and Reminders · Google Calendar

More Python MCP servers · Northdata MCP · GitHub PR Context · Quant Brain MCP · Prometheus MCP Server · Pagerduty MCP · see all