Recall MCP Server

A better memory server for AI agents - works for one, scales to many. Local, free, zero-config, MCP-native. Your data stays on your machine.

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

VERIFIED ACTIVE

LAST COMMIT 2026-06-16 · ★ 7 · #163 OF 259 MAINTAINED MEMORY · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Recall

before you install - you'll need

API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

claude mcp add recallworks-recall -- uvx ai-recallworks

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "recallworks-recall": {
      "command": "uvx",
      "args": [
        "ai-recallworks"
      ]
    }
  }
}

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

license MIT - declared in the repository

pypi package ai-recallworks - check the name against the project README before installing (PyPI has no namespace ownership)

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

03 · What Recall can do

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

Latest releases

v0.5.1 · 2026-04-30

Patch release: republishes the package with the v0.5.4 README rewrite (works for one, scales to many) and adds the mcp-name: io.github.recallworks/recall marker required for MCP Registry namespace verification. · No…

v0.5.0 · 2026-04-30

Recall v0.5.0 - multi-agent coordination wedge · The single-agent memory problem (mem0, Letta, Zep) is well-served. The · multi-agent coordination problem isn't. v0.5.0 ships six new MCP · primitives so parallel AI…

ts-sdk-v0.2.0 · 2026-04-24

BREAKING CHANGE. 0.1.0 was published with a fictional API. This rewrite matches the real Recall server contract verified end-to-end against ghcr.io/recallworks/recall:0.1.0. · Install · bash · npm install…

04 · Who maintains Recall

recall is maintained by recallworks. It's the only MCP server we track from this author; the repo dates to Apr 2026.

05 · Facts

category
memory - ranked #163 of 259 actively-maintained memory servers as of 2026-08-25.
registry
io.github.RecallWorks/recall (active, first published 2026-05-08)
packages
pypi:ai-recallworks

06 · Recall FAQ

What is Recall?

A better memory server for AI agents - works for one, scales to many. Local, free, zero-config, MCP-native. Your data stays on your machine.

Is Recall still maintained?

Yes - as of 2026-08-25, its last commit was 2026-06-16. We re-verify nightly.

How do I install Recall?

Run `uvx ai-recallworks`. The README documents one environment variable (API_KEY) to set first. You can also paste the ready-made client config above.

Does Recall 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 Recall

Pairs well with

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

  1. Server Filesystem → filesystem companion filesystem · ★ 38,704
  2. X402 List MCP → filesystem companion filesystem · ★ 58