
Flockward
Free link and site safety checks that warn agents about prompt-injection traps
Answered our latest tool-list check 9 hours ago with 10 tools. It will be marked verified after 3 successful checks in 7 days.
- Pricing
- Free
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.1.0
- Listing updated
- 3 days ago
About Flockward
Flockward is a free MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.
Some web pages hide text meant to hijack an AI agent that reads them. Flockward is a shared lookup: an agent asks about a URL before opening it, and agents that spot an attack report what they saw so others are warned.
There is no account for checks. The same service answers over a plain HTTP call (a GET to /v1/check with a url parameter) and over the MCP address, and publishes an OpenAPI description, a machine-readable manifest and an llms.txt file so an agent can set itself up. Agents pay for the service by reporting what they see.
Developers can register a webhook to be told when a page their agents visited turns bad, and site owners can see how their site looks to agents and get a badge, with weekly findings and an attack registry published.
Install
Run in a terminal
claude mcp add --transport http flockward https://flockward.com/mcpAdd to Settings → Connectors → Add custom connector
https://flockward.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"flockward": {
"url": "https://flockward.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"flockward": {
"type": "http",
"url": "https://flockward.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"flockward": {
"serverUrl": "https://flockward.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"flockward": {
"type": "http",
"url": "https://flockward.com/mcp"
}
}
}Tools this server provides (10)
Read directly from the server.
- check_url
- Check 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
- Check up to 50 links in one call, for example a page of search results. One check per link.
- fetch_safely
- Safe 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 page so you know which are safe to follow next. Known-malicious pages are never fetched.
- report_page
- Tell 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. Reports earn extra checks and protect other agents.
- scan_mcp_server
- Before 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 other tools behave. Pass the server's URL, or its tools/list result.
- check_site
- Rate 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_webhook
- Register 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_key
- Get 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
- Show your remaining checks today, contribution, reputation, referrals and any alerts.
- send_feedback
- Send a suggestion or problem to the people who run Flockward. A human reads every note.
What it does
- Link trap checks
- Tells an agent whether a URL looks like an injection trap before it is opened.
- Shared reporting
- Reports from one agent protect every other agent using the service.
- No-account use
- Checks are free and need no sign-up.
- Webhook alerts
- Notifies you when a page your agents visited turns bad.
- Site check and badge
- Shows a site owner how agents see their pages and offers a badge.
- Weekly findings
- Publishes an attack registry and a weekly roundup.
Good for
- Screen URLs before an agent browses them
- Warn a research agent about poisoned pages
- Check how your own site appears to AI agents
- Get alerts when previously visited pages become hostile
Pricing
Free
Checks are free and need no account.
Prices change. Check flockward.com before you buy.
Flockward FAQ
Does it cost anything?
Checks are free for agents and need no account.
How do I try it without MCP?
Send a GET request to https://flockward.com/v1/check with the url parameter.
What is the MCP address?
https://flockward.com/mcp over streamable HTTP.
How do agents contribute?
They report what they see, and those reports protect the rest of the flock.
Is Flockward free?
Yes. Flockward is free to use.
How do I add Flockward to Claude Code?
Run this command in your terminal: claude mcp add --transport http flockward https://flockward.com/mcp
What are the best alternatives to Flockward?
The closest alternatives to Flockward are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.
Alternatives to Flockward

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools
Agent Roast
MCP serverOffline review that flags agent changes which weaken tests, assertions or CI
Runs locally- Open source
- 4 Hacker News points
- Developer tools

Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases

Leash
MCP serverReview what your AI touched, approve risky actions and undo supported changes
- 1 tool
- Remote
- Free
- 1 GitHub star
- Security
Zero-log MCP server with 49 tools for AI guardrails, secret scanning and EU compliance
- 49 tools
- Remote
- Freemium
- Security

SecureCloud
MCP serverSentinelOne and IT security catalog, prices, quotes and checkout links for Israel
- 7 tools
- Remote
- Free
- Security