mcpbeat Sign in

Recall MCP Server

by recallworks Your server? Claim it
local only

Recall runs on your own machine — the client starts it, so there is no endpoint to ping. 100 installs a week from pypi. Last commit 11 May 2026.

Open-source MCP memory server. Persistent, searchable, tiered memory across sessions.

Installs per day peak 44 · avg 20 · -16% w/w
a month agotoday
100
Installs / week
pypi · ai-recallworks
8
Stars
0 open issues
11 May 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 21 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

        img.save(os.path.join(OUT_DIR, f"logo-{sz}.png"), "PNG", optimize=True)
Page executes code built at runtime site/_mockup.html:111, site/index-test.html:207
        textSpan.innerHTML = text;

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add recall -- uvx ai-recallworks
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "recall": {
      "args": [
        "ai-recallworks"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.recall]
command = "uvx"
args = ["ai-recallworks"]
.cursor/mcp.json
{
  "mcpServers": {
    "recall": {
      "args": [
        "ai-recallworks"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "recall": {
      "args": [
        "ai-recallworks"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Recall

same job, measured the same way
Collective Memory
by hustada

MCP server for persistent, semantic memory across AI sessions

40 installs/wk local only
Memstack
by isiomac

MCP server for persistent, searchable memory for AI agents.

39 installs/wk local only
MCP Memory
by infoinlet-marketplace

Persistent searchable memory for AI agents — save/get/search across sessions, tags.

28 installs/wk local only
MCP Memento
by annibale-x

An MCP server that provides persistent memory and context management across sessions

197 installs/wk local only
MCP External Memory
by daedalus

An MCP server that gives LLMs persistent, searchable semantic memory

80 installs/wk local only
memgit
by memgit

Git for AI memory — version-controlled, searchable context that persists across sessions

532 installs/wk local only
Goldhold
by jerrysrodz

Persistent memory for AI agents. Search, store, and recall across sessions.

30 installs/wk answering
Engram
by getengram

Persistent, verbatim, searchable memory for AI assistants — one memory across every MCP client.

answering

Recall — questions

Answers built from our own checks of this server.

Why is there no uptime for Recall?
Recall runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package ai-recallworks was installed 100 times last week.
How do I connect Recall?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls ai-recallworks straight from pypi; nothing to host, nothing to sign up for.
How many people use Recall?
The pypi package ai-recallworks was installed 100 times in the last week. Week over week that is -16%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Recall open source?
Yes — it is published under the MIT licence, written in Python and 8 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.