Agent Replay

io.github.mdfifty50-boopPublished by GitHub account mdfifty50-boopv0.1.1Updated Oct 24, 2026

Record and replay AI agent execution for debugging

VerifiedSTDIODesktop onlyDeveloper ToolsAI & ML

Overview

AI-generated overview

A local MCP server that records AI agent sessions and lets an assistant replay, compare and export them to debug non-deterministic behavior.

What you can do
Start and stop recording of an agent session, returning a session ID and a summary of action counts and durations, and log individual actions with input, output, reasoning and timing. Replay a recorded session step by step with full action detail. Compare two sessions to get a similarity ratio, identical and divergent step counts, and the first divergence. Find where an agent first deviated from expected output, given a single value or per-step expectations. Export a session as JSON or a readable markdown transcript, and list all recorded sessions through a resource.
When to use it
Useful when debugging agents whose runs vary between executions, when comparing a run against an earlier baseline to catch behavioral regressions, or when you need a shareable transcript of what an agent did.
Requirements
Runs as a local process on the user's machine, started with npx agent-replay-mcp or from source with Node.js and npm install. Desktop client configuration is needed; no accounts, API keys or environment variables are declared.
Before you install
Recorded actions include inputs, outputs and agent reasoning, which may contain sensitive data; exported sessions and the sessions resource expose that content, so review before sharing. The server writes session records locally.

Installation

In SourceWeft

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

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

agent-replay-mcp

MCP server for agent session recording and replay — debug non-deterministic agent behavior with session comparison and divergence detection.

Record every action an agent takes, replay sessions step by step, diff two runs to find behavioral regressions, and pinpoint exactly where an agent diverged from expected output.

Install

bash
npx agent-replay-mcp

Claude Desktop

Add to claude_desktop_config.json:

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

From source

bash
git clone https://github.com/mdfifty50-boop/agent-replay-mcp.gitcd agent-replay-mcpnpm installnode src/index.js

Tools

record_session

Start recording all actions for an agent session.

ParamTypeDefaultDescription
agent_idstringrequiredUnique agent identifier
metadataobject{}Optional metadata (task, model, environment)

Returns a session_id for use with other tools.

stop_recording

Stop recording and return a session summary.

ParamTypeDescription
session_idstringSession ID from record_session

Returns: action count, total duration, action type breakdown.

log_action

Log a single action during a recording session.

ParamTypeDefaultDescription
session_idstringrequiredActive session ID
action_typestringrequiredType (tool_call, llm_response, decision, error)
inputanyrequiredInput to the action
outputanyrequiredOutput from the action
reasoningstring""Agent reasoning for this step
duration_msnumber0Action duration in milliseconds

replay_session

Replay a recorded session step by step with full action detail.

ParamTypeDescription
session_idstringSession ID to replay

Returns: complete action sequence with timing, reasoning, inputs, and outputs.

compare_sessions

Behavioral diff between two sessions. Aligns actions by step index and highlights differences.

ParamTypeDescription
session_id_1stringFirst session
session_id_2stringSecond session

Returns: similarity ratio, identical/divergent step counts, first divergence step, and per-step diffs.

find_divergence_point

Find where an agent first deviated from expected output.

ParamTypeDescription
session_idstringSession to analyze
expected_outputanyExpected final output, or array of per-step expected outputs

If expected_output is an array, compares step by step. If a single value, finds the last matching output and flags the next step as the divergence point.

export_session

Export a session for sharing and offline analysis.

ParamTypeDefaultDescription
session_idstringrequiredSession to export
formatstring"json""json" or "markdown"

Markdown format produces a readable transcript with step headers, reasoning, and code blocks.

Resources

URIDescription
agent-replay://sessionsAll recorded sessions with status and action counts

Usage Pattern

1. record_session — start recording at agent launch2. For each agent action:   - log_action — capture input, output, reasoning, timing3. stop_recording — finalize the session4. Debug:   - replay_session — review what happened step by step   - compare_sessions — diff today's run vs yesterday's   - find_divergence_point — pinpoint where it went wrong5. Share:   - export_session — JSON for tooling, markdown for humans

Tests

bash
npm test

License

MIT

Source: README.md at commit 5b16b48

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

40% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 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.