llms.txt
How AI agents discover DebugBundle capabilities through the llms.txt standard.
DebugBundle publishes a llms.txt file at the site root that helps AI agents
and large language models discover product capabilities, documentation structure,
and integration points.
What is llms.txt?
The llms.txt specification is a standard for providing
machine-readable context to AI systems. Similar to how robots.txt guides web
crawlers, llms.txt guides AI agents.
The file is a structured markdown document that tells AI agents:
- What the product does
- Where to find documentation
- What APIs and tools are available
- How to integrate
DebugBundle's llms.txt
DebugBundle's llms.txt is available at:
https://debugbundle.com/llms.txtIt includes:
Product Summary
A concise description of what DebugBundle is and how it's used — enough for an agent to understand when to suggest or use DebugBundle.
Documentation Links
Structured links to key documentation sections:
- Getting Started guides
- SDK references (Node.js, Browser, Python, PHP)
- CLI command reference
- API endpoint documentation
- MCP tool catalog
Integration Points
How agents can interact with DebugBundle:
- CLI — Command-line interface for local and cloud operations
- MCP — Model Context Protocol tools for direct agent integration
- API — REST API for programmatic access
- Webhooks — Event-driven automation triggers
- SDK — Application instrumentation
Agent Skill Reference
A pointer to the .agents/skills/debugbundle/SKILL.md skill file structure
that agents can install in projects for deep integration.
How Agents Use It
Discovery
When an AI agent encounters a DebugBundle-instrumented project, it can
fetch llms.txt to understand:
- What capabilities are available
- Which documentation to read for specific tasks
- How to authenticate and interact with the API
- What MCP tools are available
Example Agent Flow
1. Agent detects .debugbundle/ directory in project
2. Agent fetches https://debugbundle.com/llms.txt
3. Agent learns about available CLI commands and MCP tools
4. Agent uses debugbundle inspect <incident-id> to investigate issuesMCP Integration
Agents with MCP access can skip llms.txt entirely — the MCP tool
descriptions provide the same information in a structured, tool-native format.
llms.txt is most valuable for agents that discover DebugBundle through
web browsing or documentation reading.
Generation
The llms.txt file is generated during the static site build and stays
in sync with the published documentation. It is not manually maintained.
Next Steps
- Agent Workflows — How agents use DebugBundle
- Agent Skill File — Project-level agent integration
- MCP Tools — MCP tool catalog