About LinkPreflight
LinkPreflight is a remote MCP server and API for agents that need to assess a URL before clicking or fetching it. A single preflight call reports availability, redirects, parking or dead-link status, phishing flags, content type, and llms.txt presence.
Key features
- 01URL availability and status checks
- 02Redirect reporting
- 03Dead or parked link detection
- 04Phishing flags
- 05Content type and llms.txt checks
Use cases
- 01Checking a link before an agent opens it
- 02Screening citations for dead or parked destinations
- 03Inspecting redirects and phishing flags before fetching
MCP support
Provides a remote MCP server at https://linkpreflight.dev/mcp. Its preflight(url) call returns link status and related URL checks to MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://linkpreflight.dev/mcpclaude mcp add --transport http linkpreflight-linkpreflight https://linkpreflight.dev/mcp{"mcpServers":{"linkpreflight-linkpreflight":{"type":"http","url":"https://linkpreflight.dev/mcp"}}}Open in Cursor{"servers":{"linkpreflight-linkpreflight":{"type":"http","url":"https://linkpreflight.dev/mcp"}}}Open in VS Code{"mcpServers":{"linkpreflight-linkpreflight":{"type":"http","url":"https://linkpreflight.dev/mcp"}}}{"mcpServers":{"linkpreflight-linkpreflight":{"serverUrl":"https://linkpreflight.dev/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 READMELinkPreflight
A remote MCP server and API for AI agents. One preflight(url) call tells you whether a link is safe, live, and what's behind it (status, redirects, dead or parked, phishing flags, content type, llms.txt) before your agent clicks or fetches it.
- Site and docs: https://linkpreflight.dev
- MCP endpoint: https://linkpreflight.dev/mcp
- API:
GET https://linkpreflight.dev/v1/preflight?url=example.com - Free: 200 checks a day. Packs: $10 for 25,000 checks.
Pairs well with
- Clearcrawl, from our studio: once a URL passes preflight, Clearcrawl turns it into clean markdown or JSON.
- VibePicks, from our studio: one clear verdict per AI dev-tool job.
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.