Name: Honeybadger MCP Server by bobtista
Author: bobtista

LABSCO SUMMARY

Two tools, and they are the two you want.

Triage is a search followed by a drill-down, and that is the whole surface here: find the faults matching a term or a time window, then read the notices behind the one that matters. Sorting by frequency rather than recency is what turns "something is broken" into "this is broken most often", and the 25-result ceiling keeps a busy project from swamping the conversation.

What it is

A read-side bridge to Honeybadger error monitoring. It lists and filters the faults in a project and pulls the notices behind any one of them, so an assistant can work from real error data instead of a pasted stack trace.

What you get

list_faults searches by text and filters on creation or occurrence timestamps
Ordering by recent or frequent, so "what is happening now" and "what happens most" are different questions
get_fault_details returns the notices for one fault, newest first
Time windows on both — created_after, created_before, occurred_after — as Unix timestamps
Pagination with a limit of at most 25 per call, which keeps a noisy project from flooding the context

Requirements

Python 3.10+ or the Docker image. A Honeybadger API key and project ID, given either as HONEYBADGER_API_KEY and HONEYBADGER_PROJECT_ID or as --api-key and --project-id. Transport defaults to SSE on 127.0.0.1 port 8050; pass --transport stdio to let the client launch it instead. Read-only against Honeybadger — nothing here resolves or deletes a fault. Version 0.2.1.

Setup effort

Run a container — build the image from the repository, then point your client at it

See installation options

USE CASES

01

Working out what broke after a deploy

List faults that first occurred after the release timestamp, ordered by recency.

list_faults

02

Finding the error worth fixing first

Order by frequency, then read the notices behind the top one.

list_faultsget_fault_details

03

Chasing one exception across a time window

Search by text, then narrow the notices to a start and end timestamp.

list_faultsget_fault_details

2 tools

Listed in project docs. Your client may show a different list.

list_faults

get_fault_details

BEFORE YOU INSTALL

What to know first

Tools you get

2 tools named in the project's documentation. Both tools only read; neither resolves nor comments on a fault. Each returns at most 25 results per call, so paginate for more.

Requires

docker on PATH
Python 3.10+
A Honeybadger API key and project ID, passed as --api-key and --project-id or as HONEYBADGER_API_KEY and HONEYBADGER_PROJECT_ID (the .env file for the Docker image)

Where it runs

All 3 documented setups run the server on your machine.

INSTALLATION

Connect your client

Build the image from the repository, then point your client at it.

Server setup

TERMINAL

git clone https://github.com/bobtista/honeybadger-mcp.git
cd honeybadger-mcp
cp .env.example .env
docker build -t honeybadger/mcp --build-arg PORT=8050 .

MCP Clients

Any MCP client — SSE

This entry connects to a server that is already running in SSE mode on port 8050, so start it first — from the Docker image you built: docker run --env-file .env -p 8050:8050 honeybadger/mcp, or from your clone: HONEYBADGER_API_KEY=<YOUR_HONEYBADGER_API_KEY> HONEYBADGER_PROJECT_ID=<YOUR_HONEYBADGER_PROJECT_ID> uv run src/honeybadger_mcp_server/server.py. Then add:

ANY MCP CLIENT — SSE · JSON

{
  "mcpServers": {
    "honeybadger": {
      "type": "sse",
      "url": "http://localhost:8050/sse"
    }
  }
}

Claude Desktop — uv

CLAUDE DESKTOP — UV · JSON

{
  "mcpServers": {
    "honeybadger": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "<YOUR_PATH_TO_HONEYBADGER_MCP>",
        "<YOUR_PATH_TO_HONEYBADGER_MCP>/src/honeybadger_mcp_server/server.py",
        "--transport",
        "stdio",
        "--api-key",
        "<YOUR_API_KEY>",
        "--project-id",
        "<YOUR_PROJECT_ID>"
      ]
    }
  }
}

<YOUR_PATH_TO_HONEYBADGER_MCP>, in both places, is the full path of your clone (git clone https://github.com/bobtista/honeybadger-mcp.git). uv run --project picks the project but does not change the working directory, so the script is given by its full path here; the README writes it as src/honeybadger_mcp_server/server.py, which only resolves when the client starts it from inside the clone. <YOUR_API_KEY> and <YOUR_PROJECT_ID> are your Honeybadger API key and project ID.

Claude Desktop — Docker

CLAUDE DESKTOP — DOCKER · JSON

{
  "mcpServers": {
    "honeybadger": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "honeybadger/mcp",
        "--transport",
        "stdio",
        "--api-key",
        "<YOUR_API_KEY>",
        "--project-id",
        "<YOUR_PROJECT_ID>"
      ]
    }
  }
}

Honeybadger MCP Server by bobtista