Agent Replay
Records every action an AI agent takes so you can replay sessions step by step and catch regressions. Provides tools to start and stop recording, log individual actions with inputs, outputs, reasoning and timing, then replay the full sequence. The real utility is in compare_sessions, which diffs two runs and shows you exactly where behavior diverged, and find_divergence_point, which pinpoints the first step that deviated from expected output. Export sessions as JSON for tooling or markdown for human review. Useful when debugging non-deterministic agent behavior, comparing model versions, or proving that a workflow changed between runs. Works over stdio and stores sessions in memory keyed by session ID.
- tools
- 7
- transport
- STDIO
- last updated
- Apr 24, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
record_sessionStart recording all actions for an agent session.
Start recording all actions for an agent session.
No parameter schema in public metadata yet.
stop_recordingStop recording and return a session summary.
Stop recording and return a session summary.
No parameter schema in public metadata yet.
log_actionLog a single action during a recording session.
Log a single action during a recording session.
No parameter schema in public metadata yet.
replay_sessionReplay a recorded session step by step with full action detail.
Replay a recorded session step by step with full action detail.
No parameter schema in public metadata yet.
compare_sessionsBehavioral diff between two sessions. Aligns actions by step index and highlights differences.
Behavioral diff between two sessions. Aligns actions by step index and highlights differences.
No parameter schema in public metadata yet.
find_divergence_pointFind where an agent first deviated from expected output.
Find where an agent first deviated from expected output.
No parameter schema in public metadata yet.
export_sessionExport a session for sharing and offline analysis.
Export a session for sharing and offline analysis.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
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-mcp
Claude 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.js
Tools
record_session
Start recording all actions for an agent session.
| Param | Type | Default | Description |
|---|---|---|---|
agent_id | string | required | Unique agent identifier |
metadata | object | {} | Optional metadata (task, model, environment) |
Returns a session_id for use with other tools.
stop_recording
Stop recording and return a session summary.
Details
- Repository
- github.com/mdfifty50-boop/agent-replay-mcp
- Category
- AI & LLM Tools
- Package
agent-replay-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from mdfifty50-boop
Related AI & LLM Tools MCP servers
View all
Memoryshackleai/memory-mcpPersistent memory for AI coding tools. 11 tools for any MCP-compatible AI tool.0stars
MADB — Agent Memory Databasespshkar84/madb-meta-agents-dbDurable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.0stars
RPCS-1 Agent Tuner & Translation Bridgetravisbergen2/rpcs1-sdkFind your AI agent's likely failure mode, get runtime settings, and clarify ambiguous prompts.0stars
Agent Bankwirternow/ai-agent-bank-mcp-serverFinancial infrastructure for AI agents: wallets, USDC transfers, lending, jobs on Polygon0stars
HIPAA Agentxbt786/hipaa-agent-aiHIPAA compliance AI agent — scan, grade, SRA, and generate compliance docs.0stars
Secant Agent Research Packjnilrac/secant-agent-research-mcpPaid MCP web research for agents: search, extraction, citations, and x402 payment discovery.0stars