CXA MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CXA_HEADLESS | No | Set false to watch Chromium during dev | true |
| CXA_LOG_LEVEL | No | debug/info/warn/error | info |
| CXA_DEFAULT_REGION | No | Region label stamped on results | Local |
| CXA_SCAN_TIMEOUT_MS | No | Page load timeout per profile (ms) | 30000 |
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 |
|---|---|
| cxa_scan_performanceA | Performs a CX Assurance performance scan for the given URL. The scan is run entirely by this MCP server using a real Chromium browser. No external API is called. Measures: page load speed, TTFB, First Contentful Paint, DOM Content Loaded, transfer size, and omni-channel load times across 6 browser/device profiles (Chrome, Edge, Firefox, Safari, Android Chrome, iOS Safari). Returns a rich Markdown performance dashboard with visual load bars, grades (A+–F), mobile vs desktop comparison, and actionable recommendations. Scope: Performance metrics only – no accessibility, SEO, or security data. |
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
There is only one tool, so there is no risk of selecting the wrong tool or confusing it with another operation. Its purpose is clearly stated as a performance-only scan.
The single tool name cxa_scan_performance uses a clear snake_case verb_noun pattern consistent with MCP naming conventions. With no other tools, there is no inconsistency to assess.
A single tool feels thin for a server surface, even though the scope is narrowly defined as performance scanning. It borders on under-scoped but is defensible for a very specific, single-purpose scanner.
The tool covers performance measurement across multiple browser/device profiles and returns a rich dashboard, matching the stated performance-only scope. Minor gaps exist around configuration, historical comparison, or export options, but core performance scanning is complete.