mcpbeat Sign in

Persome MCP Server

by intuition-lab Your server? Claim it
local only

Persome runs on your own machine — the client starts it, so there is no endpoint to ping. 78 installs a week from pypi. Last commit 11 Aug 2026.

Local-first personal memory and model server for trusted MCP agents on macOS.

Installs per day peak 27 · avg 13 · -1% w/w
a month agotoday
78
Installs / week
pypi · personal-model
1322
Stars
7 open issues
11 Aug 2026
Last commit
0 releases in 90 days
Apache-2.0
License
Python

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Runs commands and sends data out [пакет] src/persome/cli.py:2211
    remove = subprocess.run(
Reads secrets and sends them out src/persome/cli.py:137
    env = dict(os.environ)
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.

Dumps the whole environment src/persome/cli.py:137
    env = dict(os.environ)
Reads files and sends them to the network src/persome/cli.py:377, [пакет] src/persome/cli.py:243
    latest = newest_capture_path(p for p in buf.iterdir() if p.suffix == ".json")

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

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Persome and you get told the day something new turns up.

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 personal-model -- uvx personal-model
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "personal-model": {
      "args": [
        "personal-model"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.personal-model]
command = "uvx"
args = ["personal-model"]
.cursor/mcp.json
{
  "mcpServers": {
    "personal-model": {
      "args": [
        "personal-model"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "personal-model": {
      "args": [
        "personal-model"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to Persome

same job, measured the same way
MCP Light Memory
by peterpirog

Local-first persistent memory for coding agents and MCP clients.

local only
Aifp MCP
by wjabanjj

Persistent memory MCP server for AI coding assistants. Chinese-first and fully local.

267 installs/wk local only
Monet
by team-monet

Local-first, state-centric memory for coding agents. MCP server + CLI.

107 installs/wk local only
OMEGA Memory
by omega-memory

Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.

1 167 installs/wk local only
Norn
by samad001z

Local-first, persistent memory for AI coding agents — remember, recall, forget, and list, over MCP.

50 installs/wk local only
MemoFS MCP Server
by memofs

Persistent memory and virtual filesystem MCP server for AI agents.

90 installs/wk answering
Omega Memory
by omega-memory

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

local only
PMB AI
by oleksiijko

Local-first persistent memory for AI coding agents.

293 installs/wk local only

Persome — questions

Answers built from our own checks of this server.

Why is there no uptime for Persome?
Persome 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 personal-model was installed 78 times last week.
How do I connect Persome?
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 personal-model straight from pypi; nothing to host, nothing to sign up for.
How many people use Persome?
The pypi package personal-model was installed 78 times in the last week. Week over week that is -1%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Persome open source?
Yes — it is published under the Apache-2.0 licence, written in Python, 1 322 stars on GitHub and 7 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.