Skip to content
MCP server

SyteCheck

MCP server that runs SyteCheck website audits and returns scored reports to your assistant

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, API
Runs
Locally
Version
0.1.4
Listing updated
3 days ago

About SyteCheck

SyteCheck is a freemium MCP server for marketing and seo. It runs locally on your machine and is started by your AI client.

A scan covers ten dimensions: HTML validity, SEO, broken links, accessibility (WCAG 2.2 AA through axe-core), performance via a real Lighthouse run, security headers, responsive layout, AI visibility, content freshness and an AI critique of the visual design. The report comes back as scored, plain-language text the assistant can turn into a fix list.

The server runs locally over stdio with npx -y @ascentws/sytecheck-mcp and needs a SYTECHECK_API_KEY that starts with sck_. Keys can be limited to scans:read, which lets a model read existing scans without spending quota. Only run_scan spends anything, and it is marked non-read-only so clients ask before running it. A bundled scan-and-remediate prompt scans a URL and builds a prioritized fix plan.

Scans share the monthly allowance of the SyteCheck web app, so an agent looping over run_scan can use up a free account's three scans quickly.

Install

Run in a terminal

claude mcp add sytecheck-mcp --env SYTECHECK_API_KEY='<SYTECHECK_API_KEY>' -- npx -y @ascentws/sytecheck-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "sytecheck-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ascentws/sytecheck-mcp"
      ],
      "env": {
        "SYTECHECK_API_KEY": "<SYTECHECK_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "sytecheck-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ascentws/sytecheck-mcp"
      ],
      "env": {
        "SYTECHECK_API_KEY": "<SYTECHECK_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "sytecheck-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ascentws/sytecheck-mcp"
      ],
      "env": {
        "SYTECHECK_API_KEY": "<SYTECHECK_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "sytecheck-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ascentws/sytecheck-mcp"
      ],
      "env": {
        "SYTECHECK_API_KEY": "<SYTECHECK_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "sytecheck-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ascentws/sytecheck-mcp"
      ],
      "env": {
        "SYTECHECK_API_KEY": "<SYTECHECK_API_KEY>"
      }
    }
  }
}

Configuration

  • SYTECHECK_API_KEYSyteCheck API key, created at Account -> API keys on sytecheck.app. Begins with sck_.Required
  • SYTECHECK_API_URLAPI base URL. Only set this to point at a non-production SyteCheck instance.

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

run_scan
Submit a URL and wait for the report; spends quota.
get_scan_report
Full findings for a scan id.
list_scans
Scan history, newest first, with filters.
get_scan_trends
Score history per URL across repeat scans.
list_categories
What SyteCheck can check and what your plan includes.
get_account_usage
Scans remaining this month and when the quota resets.

What it does

Ten-category scans
Checks HTML, SEO, links, accessibility, performance, security headers, layout, AI visibility, freshness and visual design.
Scoped API keys
A scans:read key lets a model read reports without starting scans.
Scan history and trends
See past scans and how a URL's scores change across repeat scans.
Quota awareness
get_account_usage shows scans remaining this month and the reset date.
Remediation prompt
scan-and-remediate turns findings into a prioritized fix plan.

Good for

  • Audit a client site before a pitch
  • Check a page after a deploy and list what to fix first
  • Track a site's scores across repeated scans
  • Have an assistant explain accessibility findings in plain language

Pricing

Freemium

Free plan with 3 scans a month; Pro and Agency are paid, prices not published here

Prices change. Check sytecheck.app before you buy.

SyteCheck FAQ

What do I need to run it?

Node with npx and a SyteCheck API key created under Account, API keys, which begins with sck_.

Is there a free plan?

Yes. Free gives 3 scans a month across 3 categories, with no credit card.

Can I stop the model from spending scans?

Create the key with scans:read only, so it can read existing reports but not start scans.

Which clients has it been tested with?

The vendor lists Claude Code, Claude Desktop, Cursor, Gemini CLI and the OpenAI Agents SDK.

Is SyteCheck free?

SyteCheck has a free plan, with paid plans for more usage or features.

How do I add SyteCheck to Claude Code?

Run this command in your terminal: claude mcp add sytecheck-mcp --env SYTECHECK_API_KEY='<SYTECHECK_API_KEY>' -- npx -y @ascentws/sytecheck-mcp

What are the best alternatives to SyteCheck?

The closest alternatives to SyteCheck are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to SyteCheck

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools