lighthouse-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LIGHTHOUSE_CHROME_NO_SANDBOX | No | Set to true to disable Chrome sandbox. Only use in isolated environments that cannot support sandboxing. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_website_performanceA | Runs reliable mobile and desktop Lighthouse audits and returns an implementation-ready structured report with equivalent Markdown. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no risk of confusion between tools. The agent will always select the correct one.
The single tool name follows a clear verb_noun pattern and is self-consistent. There are no other tools to conflict with.
With only one tool, the server feels thin for a domain like website performance analysis, which could benefit from multiple tools (e.g., scheduling, comparing). However, for a focused use case it is acceptable.
The single tool covers the core functionality of running Lighthouse audits and generating reports. Minor gaps might include the ability to run only specific audits or retrieve historical reports, but these are not severe.