mcpbeat Sign in

agenthold MCP Server

local only

agenthold runs on your own machine — the client starts it, so there is no endpoint to ping. 271 installs a week from pypi. Last commit 7 Jul 2026.

Shared versioned state for multi-agent AI workflows

Installs per day peak 192 · avg 47 · +32% w/w
a month agotoday
271
Installs / week
pypi · agenthold
2
Stars
0 open issues
7 Jul 2026
Last commit
0 releases in 90 days
MIT
License
Python

Nothing serious here today

Today is the operative word: we check agenthold every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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

Alternatives to agenthold

same job, measured the same way
MCP State Sidecar
by askadvaith

MCP State Sidecar: durable state persistence for multi-agent AI workflows

62 installs/wk local only
Snapstate
by timbassler88

Persistent state for AI agent workflows. Save, resume, and replay multi-step workflows.

28 installs/wk local only
Handoff MCP Server
by josephibra

Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.

3 tools answering
BugBug
by bugbug-io

BugBug workflows for AI agents workflows for AI agents

answering
Aichat
by rcgalbo

Inter-agent communication for multi-agent Claude Code workflows.

51 installs/wk local only
MCP Eval Runner
by dbsectrainer

A standardized testing harness for MCP servers and agent workflows

27 installs/wk local only
MCP Agent Trace Inspector
by dbsectrainer

Step-by-step observability for MCP agent workflows

23 installs/wk local only
Koda
by aabxtract

Verification and memory layer for coding-agent workflows.

48 installs/wk local only

agenthold — questions

Answers built from our own checks of this server.

Why is there no uptime for agenthold?
agenthold 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 agenthold was installed 271 times last week.
How do I connect agenthold?
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 agenthold straight from pypi; nothing to host, nothing to sign up for.
How many people use agenthold?
The pypi package agenthold was installed 271 times in the last week. Week over week that is +32%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is agenthold open source?
Yes — it is published under the MIT licence, written in Python and 2 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.