Guck MCP Server

Guck is a tiny, MCP-first telemetry store for agentic debugging. It provides token-efficient log analytics by capturing JSONL telemetry events and

Local serverstdioPython

What is the Guck MCP MCP server?

Connect Guck MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Guck is a tiny, MCP-first telemetry store for agentic debugging. It provides token-efficient log analytics by capturing JSONL telemetry events and exposing a minimal MCP toolset for fast, filtered queries. The guck mcp mcp server is what makes that connection.

Installation

@guckdev/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • guck.search — guck.search_batch
  • guck.stats — guck.sessions
  • Checkpoint — guck checkpoint writes a .guck-checkpoint file in the root of your store dir (GUCK_DIR or ~/.guck/logs) containing an epoch millisecond timestamp

Credentials and setup notes

Configuration is passed through the environment: GUCK_CONFIG_PATH, GUCK_SESSION_ID, GUCK_DIR, GUCK_RUN_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Worth knowing first

  • 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.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Guck MCP's toolset — guck.search, guck.stats, Checkpoint — is a fair guide to whether it matches your workflow. It is maintained by tillkolter; 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.

Available tools

ToolWhat it does
guck.searchguck.search_batch
guck.statsguck.sessions
Checkpointguck checkpoint writes a .guck-checkpoint file in the root of your store dir (GUCK_DIR or ~/.guck/logs) containing an epoch millisecond timestamp. When MCP tools are called without since, Guck uses the checkpoint timesta

How to install the Guck MCP MCP server

{
  "mcpServers": {
    "guck": {
      "command": "guck",
      "args": ["mcp"],
      "env": {
        "GUCK_CONFIG_PATH": "/path/to/.guck.json"
      }
    }
  }
}

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

Configuration

VariableDescriptionRequired
GUCK_CONFIG_PATHFilesystem location the server is allowed to use.Optional
GUCK_SESSION_IDConfiguration value read at startup.Optional
GUCK_DIRFilesystem location the server is allowed to use.Optional
GUCK_RUN_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use Guck MCP to guck.search.
  • Use Guck MCP to guck.stats.
  • Use Guck MCP to Checkpoint.

Frequently asked questions

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