Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-check-links check https://example.com for issues"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that analyzes websites for broken links, missing meta tags, and redirect chains. Returns a structured report with a health score and fix suggestions.
Checks all links on a page for 4xx/5xx errors (up to 20 links)
Detects missing meta tags: title, description, og:title, og:description, og:image, canonical, viewport
Traces redirect chains and flags excessive hops
Returns a score (0–100) and actionable suggestions
Related MCP server: SEO Analyzer API
npx mcp-check-linksAdd to your .claude/settings.json (or ~/.claude/settings.json):
{
"mcpServers": {
"check-links": {
"command": "npx",
"args": ["mcp-check-links"],
"env": {
"MCPCAT_PROJECT_ID": "proj_your_id_here"
}
}
}
}Or if running locally from the built output:
{
"mcpServers": {
"check-links": {
"command": "node",
"args": ["/path/to/mcp-check-links/dist/index.js"],
"env": {
"MCPCAT_PROJECT_ID": "proj_your_id_here"
}
}
}
}MCPCAT_PROJECT_ID is optional. Get your project ID from mcpcat.io. The server runs fine without it — analytics are simply disabled.
This server supports MCPcat analytics. Set the MCPCAT_PROJECT_ID environment variable to your project ID (e.g. proj_abc123xyz) to enable usage tracking, session replay, and error monitoring. Without it, the server runs normally with no analytics.
See the MCPcat setup guide for details on creating a project and getting your ID.
check-linksInput: { "url": "https://example.com" }
Output:
{
"url": "https://example.com",
"brokenLinks": [{"href": "...", "status": 404, "text": "..."}],
"missingMetaTags": ["og:image", "canonical"],
"presentMetaTags": {"title": "...", "description": "..."},
"redirectChain": ["https://example.com -> https://www.example.com"],
"score": 85,
"suggestions": ["Add og:image meta tag", "Fix broken link (404): /old-page"]
}Find broken links, missing meta tags, and redirect chains on any website. Returns a structured report with fix suggestions.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The URL of the website to analyze |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses it performs network analysis and returns a report, but does not mention if it's read-only, any side effects, permissions, or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two efficient sentences that front-load the main purpose and include a note about the output. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and simple parameters, description covers the main actions and output. Could mention URL protocol requirements or result format details, but sufficient for a straightforward tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'url' with schema description 'The URL of the website to analyze'. Description does not add value beyond schema, and schema coverage is 100%, baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool finds broken links, missing meta tags, and redirect chains, which is specific and distinct from generic check tools. It mentions returning a structured report with fix suggestions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use or not use this tool. The description implies it's for website analysis, but lacks when-not-to-use criteria or alternatives (though no siblings exist).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.2.0check-linksScored across 1 tool
With only one tool, there is no possibility of confusion between tools.
A single tool name follows a clear naming pattern by default.
A single tool for a focused domain is borderline but acceptable; it might feel too limited for broader use cases.
The tool covers the basic functionality described, but lacks granular options or additional related checks like SEO analysis beyond meta tags.
Free website analyzer: score any public URL 0-100 across 8 quality dimensions. No auth.
Scores any public website on how usable it is by AI agents, with per-check evidence.
AI website audit: security, SEO, performance, UX and accessibility checks with actionable fixes.
Scan any URL for on-page, technical & content SEO; 0-100 score with copy-paste fixes.
