Linkinator

A Model Context Protocol (MCP) server that provides link checking capabilities usinglinkinator. This allows AI assistants like Claude to scan webpages and local files for broken links.

npx install-mcp linkinator-mcp --client claude

{ "mcpServers": { "linkinator": { "command": "npx", "args": ["linkinator-mcp"] } } }

Edit%APPDATA%\claude-code\config.json:

{ "mcpServers": { "linkinator": { "command": "npx", "args": ["linkinator-mcp"] } } }

If you prefer to install the package globally first withnpm install -g linkinator-mcp, you can simplify the configuration:

{ "mcpServers": { "linkinator": { "command": "linkinator-mcp" } } }

Edit~/Library/Application Support/Claude/claude_desktop_config.json:

{ "mcpServers": { "linkinator": { "command": "npx", "args": ["linkinator-mcp"] } } }

Edit%APPDATA%\Claude\claude_desktop_config.json:

{ "mcpServers": { "linkinator": { "command": "npx", "args": ["linkinator-mcp"] } } }

After updating the configuration, restart your Claude client for the changes to take effect.

Once configured, you can ask Claude to check links on any webpage or local file. Here are some example prompts:

Check all the links on https://example.com

Scan https://example.com recursively and check all links on the same domain

Check the links in /path/to/my/documentation/index.html

Check https://example.com with the following options: - Recurse through all pages - Check CSS for URLs - Validate anchor fragments - Skip links to google.com and facebook.com - Use a 10 second timeout

Thescan_pagetool supports all of linkinator's CLI options:

- path(string): URL or local file path to scan

- concurrency(number): Number of simultaneous connections (default: 100)
- port(number): Server port for local scanning (random port by default)
- timeout(number): Request timeout in milliseconds (0 = no timeout)

- recurse(boolean): Follow links recursively on the same domain
- serverRoot(string): Custom disk location where the server starts
- directoryListing(boolean): Auto-serve directory index files
- cleanUrls(boolean): Enable extensionless link resolution (e.g., /about → /about.html)

- markdown(boolean): Parse and scan markdown files
- checkCss(boolean): Extract and validate URLs in CSS properties
- checkFragments(boolean): Validate URL anchor identifiers

- linksToSkip(string[]): URL patterns to exclude (regex strings)
- userAgent(string): Custom user agent header

- retry(boolean): Retry HTTP 429 responses with retry-after header
- retryErrors(boolean): Retry 5xx errors
- retryErrorsCount(number): Retry attempt limit
- retryErrorsJitter(number): Random delay between retries in milliseconds

- allowInsecureCerts(boolean): Accept invalid SSL certificates

The tool returns a formatted report showing:

Linkinator Scan Results for: https://example.com Summary: Status: ✓ PASSED / ✗ FAILED Total Links: 150 OK: 145 Broken: 5 Skipped: 0 Broken Links: Status 404: - https://example.com/missing-page Found on: https://example.com/index.html - https://example.com/old-blog-post Found on: https://example.com/blog.html Status 500: - https://api.example.com/endpoint Found on: https://example.com/docs.html

- Check that the path inconfig.jsonis absolute, not relative
- Verify the build directory exists:ls /path/to/linkinator-mcp/build/index.js
- Check Claude Code logs for errors
- Ensure Node.js is in your PATH

If you get permission errors on macOS/Linux:

chmod +x /path/to/linkinator-mcp/build/index.js

If scanning local files and getting port errors, try specifying a port:

Contributions are welcome! Please seeCONTRIBUTING.mdfor details on how to get started.

- linkinator- The underlying link checking library
- MCP Servers- Collection of MCP server implementations
- Claude Code- AI coding assistant that uses MCP

Justin Beckwithjustin.beckwith@gmail.com

Built with theModel Context ProtocolSDK.

Help agents automatically write and test stories for your UI components