An MCP server that lets AI assistants inspect, normalize, diff, and validate agent tool-call traces. It exposes tools for converting raw traces into a canonical agentsnap format, comparing two traces, and checking a snapshot against the trace schema.
From the registry: Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Please install the `agentsnap` 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 the MCP server can be launched with npx.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@mukundakatta/agentsnap-mcp"]
Note: The README also provides a local install alternative: install globally with npm (`npm install -g @mukundakatta/agentsnap-mcp`) and run `mcp-agentsnap`, which listens on stdio. The npx launch is the simplest portable 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.