An MCP server for recording agent sessions, replaying them step by step, and comparing runs to detect where behavior diverges. It also supports exporting sessions and viewing recorded session metadata as a resource.
From the registry: Record and replay AI agent execution for debugging
Please install the `agent-replay` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js and npm/npx** — Install Node.js so you can run the MCP server with npx.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["agent-replay-mcp"]
Note: README provides a portable stdio install path via npx. No environment variables are documented. A source install path is also provided, but npx is the simplest preferred option.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.