agent-replay-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-replay-mcprecord a session for my QA agent"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
npx agent-replay-mcpClaude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"agent-replay": {
"command": "npx",
"args": ["agent-replay-mcp"]
}
}
}From source
git clone https://github.com/mdfifty50-boop/agent-replay-mcp.git
cd agent-replay-mcp
npm install
node src/index.jsRelated MCP server: opencode-lens
Tools
record_session
Start recording all actions for an agent session.
Param | Type | Default | Description |
| string | required | Unique agent identifier |
| object |
| Optional metadata (task, model, environment) |
Returns a session_id for use with other tools.
stop_recording
Stop recording and return a session summary.
Param | Type | Description |
| string | Session ID from record_session |
Returns: action count, total duration, action type breakdown.
log_action
Log a single action during a recording session.
Param | Type | Default | Description |
| string | required | Active session ID |
| string | required | Type (tool_call, llm_response, decision, error) |
| any | required | Input to the action |
| any | required | Output from the action |
| string |
| Agent reasoning for this step |
| number |
| Action duration in milliseconds |
replay_session
Replay a recorded session step by step with full action detail.
Param | Type | Description |
| string | Session 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.
Param | Type | Description |
| string | First session |
| string | Second 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.
Param | Type | Description |
| string | Session to analyze |
| any | Expected 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.
Param | Type | Default | Description |
| string | required | Session to export |
| string |
|
|
Markdown format produces a readable transcript with step headers, reasoning, and code blocks.
Resources
URI | Description |
| All recorded sessions with status and action counts |
Usage Pattern
1. record_session — start recording at agent launch
2. For each agent action:
- log_action — capture input, output, reasoning, timing
3. stop_recording — finalize the session
4. 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 wrong
5. Share:
- export_session — JSON for tooling, markdown for humansTests
npm testLicense
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mdfifty50-boop/agent-replay-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server