Agent Replay Debugger Mcp

io.github.CSOAI-ORGPublished by GitHub account CSOAI-ORGv1.0.7Updated Nov 4, 2026

Agent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & MonitoringAI & ML

Overview

AI-generated overview

MCP server that records agent steps and replays them deterministically, with signed audit evidence for debugging agent runs.

What you can do
  • Start a recording session for an agent run
  • Capture individual agent steps as they execute
  • Replay recorded steps deterministically for step-level debugging
  • Produce signed audit evidence of recorded runs
  • Installable as a pip package or via Smithery, running over stdio
When to use it
Useful when you need to debug an agent's behaviour step by step, reproduce a run deterministically, or keep signed evidence of what an agent did for audit purposes.
Requirements
Runs as a local process: install the agent_replay_debugger_mcp package with pip (or via Smithery) and launch the agent-replay-debugger-mcp command over stdio; a remote endpoint at api.meok.ai is also listed. No authentication, environment variables or headers are declared.
Before you install
Recording captures agent steps, which may include prompts, tool inputs and outputs; review what is stored and where before enabling it. The README advertises paid Pro and Enterprise tiers and compliance consulting, so expect upsell. The README's compliance claims are vendor statements, not verified here.

Installation

In SourceWeft

  1. Open Agent Replay Debugger Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.CSOAI-ORG%2Fagent-replay-debugger-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agent-replay-debugger": {
      "type": "http",
      "url": "https://api.meok.ai/v1/a2a/agent-replay-debugger"
    }
  }
}

README

[MCP Scorecard: 88/100]

mcp-name: io.github.CSOAI-ORG/agent-replay-debugger-mcp

Agent Replay Debugger MCP

[MEOK AI Labs] [EU AI Act] [License] [PyPI]

Agent Replay Debugger MCP - step-debug + deterministic replay + signed audit evidence

Agent Replay Debugger MCP - step-debug + deterministic replay + signed audit evidence. MIT. By MEOK AI Labs.

🚀 Quick Start

bash
# Install via pippip install agent_replay_debugger_mcp
# Or install via Smitherynpx -y @smithery/cli@latest install agent-replay-debugger-mcp --client claude

✨ Features

  • MCP protocol compliant
  • Easy installation
  • Well-documented API
  • Production-ready
  • Active maintenance

📖 Documentation

🛡️ Compliance

This MCP server is built with EU AI Act compliance built-in:

  • ✅ Article 9 — Risk Management System
  • ✅ Article 13 — Transparency & Instructions for Use
  • ✅ Article 15 — Bias Detection & Testing
  • ✅ Article 26 — FRIA Support (where applicable)
  • ✅ Article 50 — AI Content Watermarking (where applicable)

Need help getting compliant? Book a free 15-min diagnostic →

🏢 Enterprise

Need custom development, SLA guarantees, or white-label deployment?

  • Pro: $99/mo — Full MCP suite + EU AI Act tracking
  • Enterprise: $499/mo — Custom dev + SLA + Dedicated support

View Pricing → | Contact Sales →

🤝 Part of the MEOK Ecosystem

This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.

DomainPurpose
councilof.aiEU AI Act compliance marketplace
safetyof.aiAI safety & monitoring
meok.aiSovereign AI platform
cobolbridge.aiLegacy modernization

📜 License

MIT © CSOAI-ORG

Built with 💜 by MEOK AI Labs · UK Companies House 16939677

Configuration

Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:

json
{  "mcpServers": {    "agent-replay-debugger-mcp": {      "command": "uvx",      "args": ["agent-replay-debugger-mcp"]    }  }}

Or: pip install agent-replay-debugger-mcp then run the agent-replay-debugger-mcp command (stdio transport).

Examples

Once configured, ask your assistant, for example:

  • "Use start_recording to …"
  • "Use record_step to …"
  • "Use replay_step to …"

See also

MEOK compliance MCP fleet: agent-commerce-protocol-mcp, agent-cost-allocator-mcp, agent-identity-trust-mcp, agent-orchestrator-mcp, agent-x402-paywall-mcp

Source: README.md at commit 53c12a9

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v1.0.7LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.