SiteLint Auditor MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUDITOR_PORT | No | Port for SSE transport. | 3100 |
| AUDITOR_TIMEOUT | No | Navigation/render timeout (ms). | 30000 |
| AUDITOR_HEADLESS | No | Set false to see browser. | true |
| AUDITOR_TRANSPORT | No | stdio or sse. | stdio |
| AUDITOR_CONCURRENCY | No | Max concurrent audit pages (hard cap). | 3 |
| AUDITOR_BROWSER_PATH | No | Custom Chromium/Chrome path. Defaults to Puppeteer default. |
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| audit_urlA | Run a SiteLint audit on a live URL. Checks WCAG accessibility, SEO, performance, and security. Optionally filter by standard, audit type, WCAG level, version, or specific success criteria. |
| audit_htmlA | Audit raw HTML snippet against WCAG/SEO standards. Creates a sandbox page to analyze the markup. |
| check_wcag_criterionA | Check a single WCAG success criterion against a page. Filters audit to one criterion, level, and WCAG standard — faster than full audit. Returns pass/fail per element. |
| list_issuesA | List recent runtime issues captured by the SiteLint auditor for a site. Returns trimmed fields (issueId, ts, type, severity, pageUrl, message, fingerprint, count). This is the "go find what I just hit" call. |
| get_issueB | Get full detail for a single issue group: stack trace, user events log (steps to reproduce), network context, and console tail. |
| capture_page_issuesB | Load a page with Puppeteer, inject the SiteLint auditor with runtime issue collection enabled, wait, and return captured issues inline. No platform account required — works fully offline. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| auditor-standards | Supported WCAG standards and criteria |
TDQS
Scored across 6 tools
Core issue tools list_issues/get_issue are clearly distinct retrieval levels, and audit_html/audit_url separate raw markup from live URL auditing. However, check_wcag_criterion overlaps heavily with audit_url's optional success-criteria filtering, and capture_page_issues vs audit_url both load pages, so an agent could sometimes hesitate between them.
All names use snake_case and a predictable verb_noun pattern: list_issues, get_issue, capture_page_issues, audit_html, audit_url, check_wcag_criterion. Singular/plural differences (get_issue vs list_issues) follow normal REST-like conventions.
Six tools is well-scoped for an auditing server, with each tool covering a distinct operation: retrieve issues, inspect issue detail, capture runtime issues, audit HTML, audit URL, and check one WCAG criterion. No obvious filler or missing bulk.
The surface covers issue discovery/detail, live page capture, HTML/URL audits, and single-criterion checks, which are the core operations for an auditor. Minor gaps exist around batch/multi-page auditing or listing available sites/audit history, but these are likely workable around.