Agents Index

Flockward

OnlineNew

Free safety checks for AI agents: links, sites, MCP servers, and pages read with traps removed.

Visit publisherConnectJSON

What it can do: 10 tools

  • check_url read-onlyCheck whether a web page is known to attack AI agents (prompt injection, data theft, destructive commands, payment fraud) or is on a phishing/malware list. Returns verdict block, warn, safe or unknown, with the reason.
  • check_urls read-onlyCheck up to 50 links in one call, for example a page of search results. One check per link.
  • fetch_safely read-onlySafe browser in one call: checks the page, fetches it, returns readable text with hidden elements, HTML comments, invisible characters and sentences that try to instruct AI agents removed, and rates every link on the pag
  • report_pageTell Flockward about a page you visited. Use kind "suspicious" if it had hidden text, instructions aimed at agents, or asked for secrets or payment; "visit" for a normal page; "false_positive" if we flagged a safe page.
  • scan_mcp_server read-onlyBefore connecting to a new MCP server, check its tool descriptions for hidden instructions (tool poisoning): requests to read credential files, hide actions from the user, redirect messages or payments, or change how oth
  • check_site read-onlyRate a whole website for AI agents: safe, caution, unsafe or not_checked, from threat lists, Flockward's own findings and a scan of its home page for hidden instructions aimed at agents.
  • set_webhookRegister an https URL. When a page you checked in the last 30 days is later confirmed as hostile to agents, Flockward POSTs the alert there. Needs a key.
  • get_free_keyGet a free Flockward key with no sign-up. Pass it as api_key on later calls for a higher daily limit, alerts about pages you visited that later turn bad, and reputation for accurate reports.
  • my_status read-onlyShow your remaining checks today, contribution, reputation, referrals and any alerts.
  • send_feedbackSend a suggestion or problem to the people who run Flockward. A human reads every note.

Connect it

Claude Code
claude mcp add --transport http flockward https://flockward.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://flockward.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "flockward": {
      "url": "https://flockward.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "flockward": {
      "type": "http",
      "url": "https://flockward.com/mcp"
    }
  }
}

Questions

What does Flockward do?

Free safety checks for AI agents: links, sites, MCP servers, and pages read with traps removed. It exposes 10 tools to AI assistants.

What tools does Flockward provide?

10 tools, including check_url, check_urls, fetch_safely, report_page, scan_mcp_server, check_site, set_webhook, get_free_key, my_status, send_feedback.

How do I connect Flockward to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://flockward.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Flockward require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Flockward online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Flockward?

flockward.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Agents & Orchestration