Agent Replay MCP Server

by mdfifty50-boop Your server? Claim it

local only

Agent Replay runs on your own machine — the client starts it, so there is no endpoint to ping. 40 installs a week from npm. Last commit 24 Apr 2026.

Record and replay AI agent execution for debugging

Installs per day peak 12 · avg 5 · +17% w/w

a month agotoday

Installs / week

npm · agent-replay-mcp

Stars

0 open issues

24 Apr 2026

Last commit

no releases in 90 days

MIT

License

JavaScript

Nothing serious here today

Today is the operative word: we check Agent Replay 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 agent-replay -- npx -y agent-replay-mcp

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

{
  "mcpServers": {
    "agent-replay": {
      "command": "npx",
      "args": [
        "-y",
        "agent-replay-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-replay]
command = "npx"
args = ["-y", "agent-replay-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "agent-replay": {
      "command": "npx",
      "args": [
        "-y",
        "agent-replay-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-replay": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "agent-replay-mcp"
      ]
    }
  }
}

Alternatives to Agent Replay

same job, measured the same way

Statecli

by charo360

State replay and self-debugging for AI agents. Track, replay, undo, checkpoint.

53 installs/wk local only

Agent Observability

by rudrendupaul

AI agent observability with deterministic record/replay for debugging agent failures.

141 installs/wk local only

Orcareplay

by continuum-ai-corp

Read, replay and fork recorded coding-agent runs.

184 installs/wk local only

Trace Forge

by mdfifty50-boop

Structured execution trace and span logging for AI agents

42 installs/wk local only

Knownissue

by gong8

Shared debugging memory for AI coding agents

answering

Rhumb MCP

by supertrained

Agent gateway for Index discovery, AN Score evaluation, and Resolve governed execution

55 installs/wk local only

Safari DevTools MCP

by hayodev

MCP server for Safari DevTools — browser debugging and automation for AI coding agents

119 installs/wk local only

MCP Debugger

by digital-defiance

Node.js and TypeScript debugging with 25+ tools for AI agents

local only

Agent Replay — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent Replay?

Agent Replay 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 agent-replay-mcp was installed 40 times last week.

How do I connect Agent Replay?

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 agent-replay-mcp straight from npm; nothing to host, nothing to sign up for.

How many people use Agent Replay?

The npm package agent-replay-mcp was installed 40 times in the last week. Week over week that is +17%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agent Replay open source?

Yes — it is published under the MIT licence, written in JavaScript 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.