Record and replay AI agent execution for debugging
Record and replay AI agent execution for debugging
MCP server for agent session recording and replay — debug non-deterministic agent behavior with session comparison and divergence detection.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| log_action | capture input, output, reasoning, timing |
| 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 |
| export_session | JSON for tooling, markdown for humans |
| record_session | |
| stop_recording | Returns: action count, total duration, action type breakdown. |
{
"mcpServers": {
"agent-replay": {
"command": "npx",
"args": ["-y", "agent-replay-mcp"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Consulta el pla estratègic Catalunya 2022: 3 àmbits, 12 objectius, 91 accions. Trilingüe CA/EN/ES.
Lean 4 MCP server: compile, prove theorems, and formalize math with Mathlib.
Instead of clicking through ProductPlan's interface, just ask:
Resumable API pagination, repeated-failure detection and tool-progress cache hints for AI agents