About CitedBy
CitedBy is a free, read-only MCP server for checking how a website is accessible to AI crawlers and search engines. It provides deterministic page findings, crawler access checks, llms.txt status, and backlink data without an account.
Key features
- 01Deterministic page checks
- 02AI crawler access checks
- 03llms.txt and link checks
- 04Backlink domain data
- 05No account or sign-in
Use cases
- 01Find page issues affecting AI answers
- 02Check crawler access through robots.txt
- 03Verify llms.txt links and availability
- 04Inspect domains linking to a site
MCP support
Exposes four tools over a public Streamable HTTP MCP endpoint: page checks, crawler access, llms.txt checks, and backlink lookup. No sign-in is required.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://citedby.eu/mcpclaude mcp add --transport http eu-citedby-citedby https://citedby.eu/mcp{"mcpServers":{"eu-citedby-citedby":{"type":"http","url":"https://citedby.eu/mcp"}}}Open in Cursor{"servers":{"eu-citedby-citedby":{"type":"http","url":"https://citedby.eu/mcp"}}}Open in VS Code{"mcpServers":{"eu-citedby-citedby":{"type":"http","url":"https://citedby.eu/mcp"}}}{"mcpServers":{"eu-citedby-citedby":{"serverUrl":"https://citedby.eu/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMECitedBy MCP server
Ask your AI tool to check whether a website can be found and cited by AI assistants and search engines. Free, no account, read-only.
Server address: https://citedby.eu/mcp (MCP Streamable HTTP, no sign-in). Page with the same instructions: https://citedby.eu/mcp-server
Tools
| Tool | What you get |
|---|---|
check_page | One page, fetched as CitedBot (robots.txt respected): what is wrong for AI answers and search, each finding with why it matters and the exact fix. Deterministic checks only. |
check_ai_crawler_access | For GPTBot, OAI-SearchBot, ChatGPT-User, PerplexityBot, ClaudeBot, Google-Extended, Bingbot and Googlebot: allowed by robots.txt, and answered by the server, or not. |
check_llms_txt | Whether /llms.txt exists, whether its links work, whether /llms-full.txt exists. |
backlinks | How many domains link to a domain, and the strongest ones, from the Common Crawl web graph. Says when a domain is not in the data. |
When a site refuses the crawler or does not answer, the tool says so. It does not score what it could not read.
Install
Claude Code
claude mcp add --transport http citedby https://citedby.eu/mcp
or install the plugin, which also adds a skill that picks the right tool for the question:
/plugin marketplace add resaleiq/citedby-mcp
/plugin install citedby@citedby
Claude on the web and desktop: Settings, Connectors, Add custom connector, paste https://citedby.eu/mcp.
Cursor: add CitedBy to Cursor, or add to ~/.cursor/mcp.json:
{ "mcpServers": { "citedby": { "url": "https://citedby.eu/mcp" } } }
Codex
codex mcp add citedby --url https://citedby.eu/mcp
Any other MCP client: add a remote server with the address above.
Ask it like this
- "Check https://example.com/pricing with CitedBy and tell me what to fix first."
- "Can GPTBot and PerplexityBot read example.com?"
- "Does example.com have a working llms.txt?"
- "Which domains link to example.com?"
Limits
40 checks an hour from one address; a result is reused for up to 6 hours (1 hour for a page check). check_page is one page. A whole-site audit, with every page up to your plan's limit and the exact fix for each, is at https://citedby.eu/plans.
Also from CitedBy: citedby-check, the same AI-crawler check as a command-line tool and GitHub Action.
Questions: [email protected]. MIT licence.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.