SyteCheck MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SYTECHECK_API_KEY | Yes | Your wak_ API key (required). Create one at Account → API keys. | |
| SYTECHECK_API_URL | No | API base URL. | https://api.sytecheck.app |
| SYTECHECK_WAIT_TIMEOUT_MS | No | How long run_scan waits before returning a scan id. | 60000 |
| SYTECHECK_POLL_INTERVAL_MS | No | Gap between status checks while waiting. | 3000 |
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
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| run_scanA | Submit a URL to SyteCheck and wait for the report. Scans ten dimensions of site quality: HTML validity, SEO, broken links, accessibility (WCAG 2.2 AA), performance (Lighthouse), security headers, responsive design, AI visibility, content freshness, and an AI visual critique of the design. IMPORTANT: each scan consumes one of the account's monthly scans and costs real money. Free accounts get three per month. Check get_account_usage first if you are unsure of the remaining quota, and confirm with the user before scanning the same URL more than once — repeat scans of an unchanged page rarely tell you anything new. A scan usually takes a few minutes. If it is still running when this returns, you get the scan id — pass it to get_scan_report to collect the result rather than scanning again. |
| get_scan_reportA | Fetch the full findings for a scan by id, including the executive summary and per-category results. Use this to collect a scan that run_scan left running, or to re-read an earlier scan without spending quota. |
| list_scansA | List this account's scans, newest first. Use it to find a scan id, or to check whether a site has been scanned before starting a new one. |
| get_scan_trendsA | Score history per URL across repeated scans — whether a site is improving or regressing over time. Returns nothing useful for a site scanned only once. |
| list_categoriesA | The analysis categories SyteCheck can run, and which of them this account's plan includes. Check this before passing |
| get_account_usageA | How many scans this account has left this month, its plan, and which categories it may run. Check this before running scans in bulk — quota is per calendar month and does not roll over. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| scan-and-remediate | Run a SyteCheck scan on a URL and turn the findings into a prioritized, actionable remediation plan. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool targets a distinct concern: running scans, fetching reports, listing scans, viewing trends, listing categories, and checking quota. There is no overlap between them.
All tool names follow a consistent verb_noun pattern: run_scan, get_scan_report, list_scans, get_scan_trends, list_categories, get_account_usage. The pattern is uniform and predictable.
Six tools is well-scoped for a scan-oriented service: the set covers the full workflow without redundancy or bloat. Each tool earns its place.
The surface covers the full scan lifecycle: quota check, category discovery, scan initiation, result retrieval, history listing, and trend analysis. A minor gap is the lack of a cancel/delete operation, but that is not essential for the domain.