website-audit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_websiteA | Audit any public website and report what is costing its owner customers. Checks page speed and weight, whether it works on a phone, whether search engines can read it, whether a visitor can actually get in touch, whether the copy reads like AI wrote it, and whether the build looks dated. Returns a 0-100 score with findings grouped by category. |
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
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clearly defined and distinct.
The single tool name 'audit_website' follows a clear verb_noun convention and is immediately understandable.
A single tool feels thin for a server claiming to audit multiple aspects of a website. However, the tool bundles all checks into one comprehensive call, so it may be acceptable for a focused utility.
The tool covers a wide range of audit dimensions (speed, mobile, SEO, contact, AI copy, design) and returns a score with categorized findings. Minor gaps exist, such as no way to drill into individual metrics or get historical data, but the core audit lifecycle is complete.