Honeybadger MCP Server

An MCP (Model Context Protocol) server for Honeybadger, providing structured access to Honeybadger's API through the MCP protocol.

Installation

First, pull the Docker image:

docker pull ghcr.io/honeybadger-io/honeybadger-mcp-server:latest

Then, configure your MCP client(s). You can find your personal auth token under the "Authentication" tab in your Honeybadger user settings.

Cursor, Windsurf, and Claude Desktop

Put this config in ~/.cursor/mcp.json for Cursor, or ~/.codeium/windsurf/mcp_config.json for Windsurf. See Anthropic's MCP quickstart guide for how to locate your claude_desktop_config.json for Claude Desktop:

{
  "mcpServers": {
    "honeybadger": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "HONEYBADGER_PERSONAL_AUTH_TOKEN",
        "ghcr.io/honeybadger-io/honeybadger-mcp-server"
      ],
      "env": {
        "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token"
      }
    }
  }
}

Claude Code

Run this command to configure Claude Code:

claude mcp add honeybadger -- docker run -i --rm -e HONEYBADGER_PERSONAL_AUTH_TOKEN="HONEYBADGER_PERSONAL_AUTH_TOKEN" ghcr.io/honeybadger-io/honeybadger-mcp-server:latest

VS Code

Add the following to your user settings or .vscode/mcp.json in your workspace:

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "honeybadger_auth_token",
        "description": "Honeybadger Personal Auth Token",
        "password": true
      }
    ],
    "servers": {
      "honeybadger": {
        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "HONEYBADGER_PERSONAL_AUTH_TOKEN",
          "ghcr.io/honeybadger-io/honeybadger-mcp-server"
        ],
        "env": {
          "HONEYBADGER_PERSONAL_AUTH_TOKEN": "${input:honeybadger_auth_token}"
        }
      }
    }
  }
}

See Use MCP servers in VS Code for more info.

Zed

Add the following to your Zed settings file in ~/.config/zed/settings.json:

{
  "context_servers": {
    "honeybadger": {
      "command": {
        "path": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "HONEYBADGER_PERSONAL_AUTH_TOKEN",
          "ghcr.io/honeybadger-io/honeybadger-mcp-server"
        ],
        "env": {
          "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token"
        }
      },
      "settings": {}
    }
  }
}

Building Docker locally

To build the Docker image and run it locally:

git clone [email protected]:honeybadger-io/honeybadger-mcp-server.git
cd honeybadger-mcp-server
docker build -t honeybadger-mcp-server .

Then you can replace "ghcr.io/honeybadger-io/honeybadger-mcp-server" with "honeybadger-mcp-server" in any of the configs above. Or you can run the image directly:

docker run -i --rm -e HONEYBADGER_PERSONAL_AUTH_TOKEN honeybadger-mcp-server

Building from source

If you don't have Docker, you can build the server from source:

git clone [email protected]:honeybadger-io/honeybadger-mcp-server.git
cd honeybadger-mcp-server
go build -o honeybadger-mcp-server ./cmd/honeybadger-mcp-server

And then configure your MCP client to run the server directly:

{
  "mcpServers": {
    "honeybadger": {
      "command": "/path/to/honeybadger-mcp-server",
      "args": ["stdio"],
      "env": {
        "HONEYBADGER_PERSONAL_AUTH_TOKEN": "your personal auth token"
      }
    }
  }
}

Configuration

Environment Variables

Environment Variable	Required	Default	Description
HONEYBADGER_PERSONAL_AUTH_TOKEN	yes	—	API token for Honeybadger
HONEYBADGER_READ_ONLY	no	true	Run in read-only mode, excluding write operations like delete_project
LOG_LEVEL	no	info	Log verbosity (debug, info, warn, error)
HONEYBADGER_API_URL	no	https://app.honeybadger.io	Override the base URL for Honeybadger's API

Important: The server runs in read-only mode by default for security. This means only read operations (like list_projects, get_project, list_faults) are available. Write operations such as create_project, update_project, and delete_project are excluded to prevent accidental modifications.

To enable write operations, explicitly set HONEYBADGER_READ_ONLY=false. Use with caution as this allows destructive operations like deleting projects.

Command Line Options

When running the server via the CLI you can configure the server with command-line flags:

# Run with custom configuration
./honeybadger-mcp-server stdio --auth-token your_token --log-level debug --api-url https://custom.honeybadger.io

# Enable write operations (use with caution)
./honeybadger-mcp-server stdio --auth-token your_token --read-only=false

# Get help
./honeybadger-mcp-server stdio --help

The --read-only flag defaults to true. Set --read-only=false to enable write operations like create_project, update_project, and delete_project.

Configuration File

You can also use a configuration file at ~/.honeybadger-mcp-server.yaml:

auth-token: "your_token_here"
log-level: "info"
api-url: "https://app.honeybadger.io"
read-only: true

Tools

Projects

• list_projects - List all Honeybadger projects

  • account_id : Account ID to filter projects by specific account (string, optional)

• get_project - Get detailed information for a single project by ID

  • id : The ID of the project to retrieve (number, required)

• create_project - Create a new Honeybadger project (requires read-only=false)

  • account_id : The account ID to associate the project with (string, required)
  • name : The name of the new project (string, required)
  • resolve_errors_on_deploy : Whether all unresolved faults should be marked as resolved when a deploy is recorded (boolean, optional)
  • disable_public_links : Whether to allow fault details to be publicly shareable via a button on the fault detail page (boolean, optional)
  • user_url : A URL format like 'http://example.com/admin/users/[user_id]' that will be displayed on the fault detail page (string, optional)
  • source_url : A URL format like 'https://gitlab.com/username/reponame/blob/[sha]/[file]#L[line]' that is used to link lines in the backtrace to your git browser (string, optional)
  • purge_days : The number of days to retain data (up to the max number of days available to your subscription plan) (number, optional)
  • user_search_field : A field such as 'context.user_email' that you provide in your error context (string, optional)

• update_project - Update an existing Honeybadger project (requires read-only=false)

  • id : The ID of the project to update (number, required)
  • name : The name of the project (string, optional)
  • resolve_errors_on_deploy : Whether all unresolved faults should be marked as resolved when a deploy is recorded (boolean, optional)
  • disable_public_links : Whether to allow fault details to be publicly shareable via a button on the fault detail page (boolean, optional)
  • user_url : A URL format like 'http://example.com/admin/users/[user_id]' that will be displayed on the fault detail page (string, optional)
  • source_url : A URL format like 'https://gitlab.com/username/reponame/blob/[sha]/[file]#L[line]' that is used to link lines in the backtrace to your git browser (string, optional)
  • purge_days : The number of days to retain data (up to the max number of days available to your subscription plan) (number, optional)
  • user_search_field : A field such as 'context.user_email' that you provide in your error context (string, optional)

• delete_project - Delete a Honeybadger project (requires read-only=false)

  • id : The ID of the project to delete (number, required)

• get_project_occurrence_counts - Get occurrence counts for all projects or a specific project

  • project_id : Project ID to get occurrence counts for a specific project (number, optional)
  • period : Time period for grouping data: 'hour', 'day', 'week', or 'month'. Defaults to 'hour' (string, optional)
  • environment : Environment name to filter results (string, optional)

• get_project_integrations - Get a list of integrations (channels) for a Honeybadger project

  • project_id : The ID of the project to get integrations for (number, required)

• get_project_report - Get report data for a Honeybadger project

  • project_id : The ID of the project to get report data for (number, required)
  • report : The type of report to get: 'notices_by_class', 'notices_by_location', 'notices_by_user', or 'notices_per_day' (string, required)
  • start : Start date/time in ISO 8601 format for the beginning of the reporting period (string, optional)
  • stop : Stop date/time in ISO 8601 format for the end of the reporting period (string, optional)
  • environment : Environment name to filter results (string, optional)

Faults

• list_faults - Get a list of faults for a project with optional filtering and ordering

  • project_id : The ID of the project to get faults for (number, required)
  • q : Search string to filter faults (string, optional)
  • created_after : Filter faults created after this timestamp (string, optional)
  • occurred_after : Filter faults that occurred after this timestamp (string, optional)
  • occurred_before : Filter faults that occurred before this timestamp (string, optional)
  • limit : Maximum number of faults to return (max 25) (number, optional)
  • order : Order results by 'recent' or 'frequent' (string, optional)
  • page : Page number for pagination (number, optional)

• get_fault - Get detailed information for a specific fault in a project

  • project_id : The ID of the project containing the fault (number, required)
  • fault_id : The ID of the fault to retrieve (number, required)

• get_fault_counts - Get fault count statistics for a project with optional filtering

  • project_id : The ID of the project to get fault counts for (number, required)
  • q : Search string to filter faults (string, optional)
  • created_after : Filter faults created after this timestamp (string, optional)
  • occurred_after : Filter faults that occurred after this timestamp (string, optional)
  • occurred_before : Filter faults that occurred before this timestamp (string, optional)

• list_fault_notices - Get a list of notices (individual error events) for a specific fault

  • project_id : The ID of the project containing the fault (number, required)
  • fault_id : The ID of the fault to get notices for (number, required)
  • created_after : Filter notices created after this timestamp (string, optional)
  • created_before : Filter notices created before this timestamp (string, optional)
  • limit : Maximum number of notices to return (max 25) (number, optional)

• list_fault_affected_users - Get a list of users who were affected by a specific fault with occurrence counts

  • project_id : The ID of the project containing the fault (number, required)
  • fault_id : The ID of the fault to get affected users for (number, required)
  • q : Search string to filter affected users (string, optional)

Insights

• query_insights - Execute a BadgerQL query against Insights data
  • project_id : The ID of the project to query insights for (number, required)
  • query : BadgerQL query string to execute against your Insights data (string, required)
  • ts : Time range - shortcuts like 'today', 'week', or ISO 8601 duration (e.g., 'PT3H'). Defaults to PT3H (string, optional)
  • timezone : IANA timezone identifier (e.g., 'America/New_York') for timestamp interpretation (string, optional)

Development

Local Development Setup

This project uses the api-go library for API interactions. For local development, you'll need to set up a Go workspace to work with both repositories simultaneously.

From the parent directory containing both honeybadger-mcp-server and api-go:

# Initialize the workspace (if not already done)
go work init
go work use ./honeybadger-mcp-server
go work use ./api-go

# The go.work file is gitignored and won't be committed

Now you can work on both repositories and changes to api-go will be immediately reflected when working on the MCP server.

Working with Dependencies

When using the workspace, Go uses the local api-go directory instead of fetching from GitHub. However, go.sum must still contain checksums for the published api-go module to support:

• CI/CD builds (which don't have the workspace)
• Developers who clone only this repository
• Docker builds

When to use GOWORK=off:

# Update dependencies and go.sum with published module checksums
GOWORK=off go mod tidy

# Install a specific version of a dependency
GOWORK=off go get github.com/some/[email protected]

# Test the build as if no workspace exists (simulates CI/end-user builds)
GOWORK=off go build ./...
GOWORK=off go test ./...

The GOWORK=off flag temporarily disables the workspace, ensuring that go.sum contains the correct checksums for the published modules.

Running Tests

go test ./...

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add my amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.