Koskamo

Webskan MCP

A remote MCP server that allows AI agents to audit live public websites using Lighthouse, axe-core, and custom crawlers. It provides tools to scan performance, accessibility, security, and broken links, then re-check fixes with stable IDs for precise diffs.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Webskan MCP logo, by WebskanCommunity listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by Webskan
You need:No sign-up, no key for the free plan
MCP endpoint (Streamable HTTP)
https://webskan.com/mcp
Vendor documentation

What its tools do

4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (4)

4 of 4 have a description · 4 of 4 declare behavior hints · 4 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Run a 30-second Lighthouse scan on a deployed site
  • Audit up to 30 pages for SEO, accessibility, and security issues
  • Re-check a site to see fixed, open, and new findings
  • Identify broken links and form accessibility errors

Source and maintenance

Community listingRegistry 0.1.0
mcp-registry: io.github.kamilobstawskiagent-ux/webskan@0.1.0Source repositoryProject website
Maintenance checked

Protocol and capabilities

Server
webskan 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
4 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Webskan checks a live, publicly reachable website the way a technical auditor would – use it right after deploying to verify the result. Tools: - scan_website: quick scan of one page (~30-60 s): Lighthouse mobile scores and metrics (LCP, CLS, TBT, weight, requests) plus HTTPS/TLS, security headers, title/meta/H1/alt/viewport/canonical/Open Graph checks. Results for the same host are cached for 24 h. - audit_website: full technical audit of the whole site, asynchronous (1-5 min): crawl of up to 30 pages, broken links, per-page SEO, Lighthouse mobile+desktop, WCAG/axe accessibility, security, platform detection, customer journeys. Returns an auditId; poll get_audit every 20-30 s. - get_audit: status or result of an audit (findings sorted high→low with page URLs). For a re-check it also returns a diff: fixed / still open / new / unverified. - recheck_website: runs the same audit again (same URL and page count) and diffs it against the original – call it after you have deployed fixes. Free limits (no key): scan_website 10/h per IP; audit_website/recheck_website 2 per IP per 24 h and 1 audit per host per 24 h (a second call for the same host returns the existing audit). With a Webskan Developer license key (Authorization: Bearer <key>): 30 audits per 24 h. Lighthouse performance scores vary by a few points between runs – treat ±5 as noise and look at the direction, not single points. All audits are read-only and look at the public version of the site. Only public hosts are accepted (no localhost, private IPs or .local). Docs: https://webskan.com/developers/

Tools

4 advertised

scan_website — Quick website scan
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Quick scan of one page (the URL you pass, usually the home page): Lighthouse mobile scores (performance, accessibility, best practices, SEO) with LCP/CLS/TBT/page weight/requests, plus HTTPS redirect, TLS, HSTS and security headers, title, meta description, H1, image alt texts, viewport, canonical, Open Graph, mixed content. Takes 30-60 s; waits up to 90 s and otherwise returns status "pending" with a scanId – call again with the same URL in 30 s. Results per host are cached for 24 h (field cached: true). Free, 10 calls per hour per IP. Use it right after a deploy as a smoke check; use audit_website for the whole site.

scan_website input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "Public website URL, e.g. https://example.com (scheme optional). Localhost and private hosts are rejected."
    }
  }
}
scan_website annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
audit_website — Full website audit (async)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Starts a full technical audit of a whole website and returns immediately with an auditId (poll get_audit every 20-30 s; typically done in 1-5 min). The audit crawls up to `pages` pages (1-30, default 15) following internal links and the sitemap, and checks: broken internal/external links with the pages they sit on, per-page SEO (title, description, H1, canonical, alt texts, Open Graph), Lighthouse mobile and desktop, WCAG accessibility (axe) with selectors, HTTPS/TLS/security headers, robots/sitemap, platform detection and customer journeys (menu, search, forms, 404). No LLM, deterministic, read-only. Free plan: 2 audits per IP per 24 h and 1 per host per 24 h (a repeat call for the same host returns the existing audit). With Authorization: Bearer <Webskan Developer license key>: 30 per 24 h.

audit_website input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "Public website URL, e.g. https://example.com (scheme optional). Localhost and private hosts are rejected."
    },
    "pages": {
      "type": "integer",
      "maximum": 30,
      "minimum": 1,
      "description": "How many pages to crawl (1-30, default 15). Fewer pages = faster."
    }
  }
}
audit_website annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
get_audit — Get audit status / result
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the status (queued / running with ETA) or the finished result of an audit started with audit_website or recheck_website: summary counts by severity, Lighthouse mobile+desktop scores, findings sorted high → medium → low → info (each with id, area, severity, title, detail and the pages it was found on), pagesCrawled, finalUrl, platform. For a re-check it also returns diff: fixed / open / new / unverified findings and Lighthouse before/after. Poll every 20-30 s while status is queued or running.

get_audit input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "auditId"
  ],
  "properties": {
    "auditId": {
      "type": "string",
      "pattern": "^[0-9a-f]{16}$",
      "description": "auditId returned by audit_website or recheck_website (16 hex characters)."
    }
  }
}
get_audit annotations
{
  "readOnlyHint": true
}
recheck_website — Re-check after fixes (diff)
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Runs the same audit again (same URL, same number of pages) linked to the original auditId, so get_audit returns a diff: fixed / still open / new / unverified findings and Lighthouse before → after. Call it after you have deployed fixes. Asynchronous like audit_website (returns a new auditId to poll with get_audit) and counted against the same limits (free: 2 audits per IP per 24 h).

recheck_website input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "auditId"
  ],
  "properties": {
    "auditId": {
      "type": "string",
      "pattern": "^[0-9a-f]{16}$",
      "description": "auditId of the finished audit to compare against."
    }
  }
}
recheck_website annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
332 ms
95th percentile latency
332 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 332 ms · metadata changed · 4 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http webskan-mcp https://webskan.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add webskan-mcp --url https://webskan.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable webskan-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "webskan-mcp": {
      "url": "https://webskan.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "webskan-mcp": {
      "type": "streamableHttp",
      "url": "https://webskan.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start webskan-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "webskan-mcp": {
      "type": "http",
      "url": "https://webskan.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http webskan-mcp https://webskan.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://webskan.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "webskan-mcp": {
      "serverUrl": "https://webskan.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Webskan MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 8,787