Working with LLMs

View Markdown

Large language models (LLMs) can help you troubleshoot your applications and fix issues faster. When integrated with Honeybadger’s error tracking and application monitoring tools, they become even more effective at helping you squash bugs and keep your systems running smoothly.

Honeybadger Model Context Protocol (MCP) server

The Honeybadger MCP server provides structured access to Honeybadger’s API through the Model Context Protocol, allowing AI assistants to interact with your Honeybadger projects and monitoring data. Connect to the hosted server in minutes, or run your own.

See the MCP server documentation for the quick start, authorization details, and example workflows.

Documentation for LLMs

We publish machine-readable content for LLMs: our documentation in llms.txt format, plus task-focused instructions for AI agents. Everything is generated automatically from our documentation and codebase.

Available formats

/llms.txt - Index page with links to full and abridged documentation, plus specialized subsets
/llms-full.txt - Complete documentation in text format
/llms-small.txt - Abridged documentation with non-essential content removed

The abridged version (llms-small.txt) is optimized for token efficiency while preserving essential technical information.

Specialized documentation subsets

We also provide focused documentation subsets for specific use cases:

The Honeybadger Data (REST) API and reporting APIs
Honeybadger Insights and BadgerQL (for generating queries, augment with agent instructions for better results)
Honeybadger’s user interface and product features
Individual documentation sets for each client library (Ruby, JavaScript, Python, PHP, Elixir, etc.)

Visit /llms.txt for the complete list with links to download.

Instructions for AI agents

The documentation subsets above are our docs reformatted for reading. We also publish agent instructions: task-focused documents that teach an agent how to write BadgerQL, query Insights, configure charts and dashboards, manage alarms, and search errors. They focus on the mistakes language models tend to make. The two complement each other: documentation gives an agent product knowledge, and instructions help it avoid common mistakes.

Using llms.txt files

These files are designed to be consumed by LLMs either:

Directly: Some LLM tools can fetch and process llms.txt files automatically
As context: Copy and paste relevant sections into your AI assistant
Via automation: Build tools that fetch and inject documentation into LLM prompts

Responding to alerts in Slack and GitHub

Honeybadger includes full backtraces in Slack error notifications to provide the context that AI coding assistants need for effective debugging.

The backtrace appears as formatted code in Slack, allowing you to copy and paste it to AI debugging assistants like Cursor, Windsurf, or Copilot. If you use Cursor’s Background Agents, you can install their Slack integration to ask Cursor to fix the error directly from Slack:

Slack notification showing a Honeybadger error and integration with AI debugging tools for quick issue resolution.

We include similar information when creating issues for errors in GitHub and other issue trackers, which should help you—for example—assign bugfixes to GitHub Copilot.

See our integration docs to learn more about our third-party integrations.

Natural language tools in Honeybadger

Honeybadger includes a few tools that let you describe what you want in plain English.

Natural language search Find errors by describing the filters you want, such as unresolved production errors from the last 24 hours.

Natural language queries Explore event data in Insights. Describe the data you want to see, and Honeybadger will build the BadgerQL query for you.

Going further

As we continue to develop LLM integrations, we’re exploring ways to make automated monitoring and debugging more intelligent. Some ideas we’re excited about:

Root cause analysis and bug fixes

Do you have ideas for how LLMs could improve your Honeybadger experience? We’d love to hear from you! Drop us a line at support@honeybadger.io.