AgentTwin MCP Server

by agenttwin Your server? Claim it

local only

AgentTwin runs on your own machine — the client starts it, so there is no endpoint to ping. 474 installs a week from npm. Last commit 6 Nov 2026.

Test AI agent workflows against service twins with injected faults. Runs locally; no source upload.

Installs per day peak 1 057 · avg 140 · -61% w/w

a month agotoday

474

Installs / week

npm · agenttwin

Stars

0 open issues

6 Nov 2026

Last commit

from GitHub

MIT

License

language unknown

Nothing serious here today

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

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.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agenttwin -- npx -y agenttwin

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agenttwin": {
      "command": "npx",
      "args": [
        "-y",
        "agenttwin"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agenttwin]
command = "npx"
args = ["-y", "agenttwin"]

.cursor/mcp.json

{
  "mcpServers": {
    "agenttwin": {
      "command": "npx",
      "args": [
        "-y",
        "agenttwin"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agenttwin": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agenttwin"
      ]
    }
  }
}

Alternatives to AgentTwin

same job, measured the same way

Git QA

by meta-taro

Open-source human-in-the-loop QA runner: an AI agent works the test sheet, a person signs off.

local only

CircleCI

by circleci

CircleCI's MCP server: inspect projects, runs, workflows, jobs, logs, tests, and artifacts.

22 tools answering

Testrigor

by testrigor

Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor.

answering

neonloops

by neonloops

Build, test and publish agentic workflows from your AI client: approve steps, read tables, see runs.

answering

BugBug

by bugbug-io

BugBug test automation workflows for AI agents

answering

Vinv

by vinvai

Vinv runs, tests, and finds issues in your services — with zero code changes.

69 installs/wk local only

QA Wrap bridge

by nj-burrito

Read-only MCP server: a coding agent reads test sessions recorded in QA Wrap. Local only.

74 installs/wk local only

MCP Eval Runner

by dbsectrainer

A standardized testing harness for MCP servers and agent workflows

277 installs/wk local only

AgentTwin — questions

Answers built from our own checks of this server.

Why is there no uptime for AgentTwin?

AgentTwin 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 npm package agenttwin was installed 474 times last week.

How do I connect AgentTwin?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls agenttwin straight from npm; nothing to host, nothing to sign up for.

How many people use AgentTwin?

The npm package agenttwin was installed 474 times in the last week. Week over week that is -61%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is AgentTwin open source?

Yes — it is published under the MIT licence and 0 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.