Endpoints: 76,849MCP servers: 32,723Payout addresses: 3,825Paid calls: 6,112Letters: 83Defects: 3,888counted just now
teppi

MCP servercom.flockward/flockward

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

Overview

Score?
UNRATED 0.143
of what a free look can see, on 1 looks
Looks
3
last 1 day ago
Tools
10

More info

URL
flockward.com/mcp
streamable-http
Says it is
flockward 1.1.0
protocol 2025-06-18
In the record since
4 days ago

Among servers32,723 with a card

0median 0.547 · this server 0.143 · highest on record 0.8351

Toolsfrom sha256:e7a436fe9a…68d619

The tools this server lists, read out of the definition it returned
ToolSchema
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 a
input · no output
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, w
input · no output
check_urls
Check up to 50 links in one call, for example a page of search results. One check per link.
input · no output
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
input · no output
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 accurat
input · no output
my_status
Show your remaining checks today, contribution, reputation, referrals and any alerts.
input · no output
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; "fal
input · no output
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
input · no output
send_feedback
Send a suggestion or problem to the people who run Flockward. A human reads every note.
input · no output
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.
input · no output
Verify it yourselfnpx teppi-check https://flockward.com/mcpcurl -s https://api.teppi.xyz/v1/trust/mcp/mcs_01M7C9KXP30CG6CRW47Y6DX4R6