Agentsnap MCP Server

Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.

Local serverstdio

What is the Agentsnap MCP server?

Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions. The agentsnap mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 3 defined tools rather than through you.

What it actually does

An MCP server that gives AI assistants the ability to inspect, normalize, diff, and validate agent tool-call traces.

Its toolset

Everything the assistant can do here goes through one of these:

  • normalize_trace — Coerce a raw tool-call trace into the canonical agentsnap Trace shape and compute a deterministic SHA-256 fingerprint hash. Use this to compare runs
  • diff_traces — Diff a baseline trace against a current run. Returns a uniform additions / removals / changes vocabulary plus the agentsnap status code (PASSED
  • validate_snapshot — Sanity-check a snapshot against the agentsnap Trace schema. Verifies required fields, tool-entry shape, and surfaces actionable issues. Returns

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at @mukundakatta/agentsnap-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agentsnap's toolset — normalize_trace, diff_traces, validate_snapshot — is a fair guide to whether it matches your workflow. It is maintained by MukundaKatta; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agentsnap mcp server does with a few real requests.

Available tools

ToolWhat it does
normalize_traceCoerce a raw tool-call trace into the canonical agentsnap Trace shape and compute a deterministic SHA-256 fingerprint hash. Use this to compare runs cheaply or feed downstream diff tools.
diff_tracesDiff a baseline trace against a current run. Returns a uniform additions / removals / changes vocabulary plus the agentsnap status code (PASSED, OUTPUT_DRIFT, TOOLS_REORDERED, TOOLS_CHANGED, REGRESSION). Use ignore_paths
validate_snapshotSanity-check a snapshot against the agentsnap Trace schema. Verifies required fields, tool-entry shape, and surfaces actionable issues. Returns valid=true on success or a list of human-readable problems.

How to install the Agentsnap MCP server

{
  "mcpServers": {
    "agentsnap": {
      "command": "npx",
      "args": ["-y", "@mukundakatta/agentsnap-mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Agentsnap to normalize trace.
  • Use Agentsnap to diff traces.
  • Use Agentsnap to validate snapshot.

Frequently asked questions

It connects Agentsnap to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (normalize_trace, diff_traces, validate_snapshot) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentsnap directly.