threatcrush is answering right now. Last checked 7 min ago. It exposes 20 tools.
Reputation + security findings (threatcrush.com)
Uptime history
4 hours of history · worst hour 75%
4 hours agonow
92.3%
Uptime 24h
12 of 13 checks
20
Tools
read from the server
362 ms
Response time
average over 24h
open, no key
Access
streamable-http
threatcrush does not always answer
Over the last week it answered 92.3% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
run in your terminal
claude mcp add threatcrush --transport http https://threatcrush.com/api/mcpSettings → Connectors → Add custom connector, then paste this address
https://threatcrush.com/api/mcp~/.codex/config.toml
[mcp_servers.threatcrush]
url = "https://threatcrush.com/api/mcp".cursor/mcp.json
{
"mcpServers": {
"threatcrush": {
"url": "https://threatcrush.com/api/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"threatcrush": {
"type": "http",
"url": "https://threatcrush.com/api/mcp"
}
}
}Available tools 20
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
webhooks
webhooks_create
Add a webhook endpoint (public https URL). Returns the endpoint and its signing secret (whsec_…), shown once.
webhooks_delete
Remove a webhook endpoint and its delivery log.
webhooks_deliveries
Recent webhook deliveries (status, attempts, last HTTP status/error, payload), for one endpoint or all.
webhooks_list
Your org's webhook endpoints (signed Standard Webhooks deliveries, retried for about three days) and the events ThreatCrush emits: detection.created, findings.raised, reputation.changed. Endpoints behind a Webhook alert destination follow your alert rules; the others get every event they subscribe to. Org owner/admin session token or an admin tc_agent_ key.
webhooks_rotate_secret
Replace an endpoint's signing secret; the old one stops working at once. Returns the new secret.
webhooks_test
Send a signed webhook.test event to one endpoint now and say how it went.
webhooks_update
Change a webhook endpoint's url, events, description, or switch it on/off (on again clears its failure count).
incidents
incidents_get
One incident: linked forensic evidence, recent events from the same observed source IP on its server, block history for that IP, saved AI assessment, multi-person assignees, fix and test progress, work history, recorded resolution/operator, findings, timeline, notes and who was paged.
incidents_list
Your org's incidents: what `threatcrush investigate --raise`, the daemon (critical detections) and people raised to humans. Filter by host and explicit since timestamp; only teams you can see. Session token or tc_agent_ key.
incidents_raise
Raise an incident report (report_version 1: title, severity, source, dedupe_key, summary, verdict, findings, timeline, recommendations, optional team_id/server_id). The same dedupe_key while open updates it; a new incident pages the team by SMS and email once. Reports that contain anything shaped like a private key or mnemonic are refused. Needs write.
incidents_update
Update fix work performed by your assigned agent or human: set multiple assignees, fix status, PR URL, test status and evidence, verification or blocker, and/or add a note. ThreatCrush catalogs the incident and does not execute remediation. Closing requires status fixed with passing tests and verification, or false_positive with a reason and verification, plus resolution.reason/action/verification. Needs write.
findings
findings_get
One tracked finding with its details (code snippet, remediation, evidence), property and history.
findings_list
Your org's tracked findings from threatcrush scan, pentest and ai-scan (deduped across runs, with a triage status). Default: open + acknowledged. Session token or tc_agent_ key.
findings_triage
Set the status and/or note of up to 500 findings: acknowledged, fixed, false_positive, ignored or open. fixed is reopened by a later run that still sees it; false_positive and ignored never are. Needs write.
reputation
reputation_bulk
Look up many IPs or domains at once (up to 100 with a free key, 1,000 with Reputation Pro). Results come back in request order; each counts against the daily allowance.
reputation_lookup
Look up an IP address or a domain against the ThreatCrush community threat database (what every linked ThreatCrush daemon blocked). Returns `listed` (the corroboration bar: independent reporters agree), a 0-100 `score`, severity, reports, reporters, rules and country; a domain is answered from its A/AAAA addresses plus nichedb.dev's public answer (abuse.ch, SURBL). With Reputation Pro: 90 days of history, the /24 neighbourhood, the network owner (ASN) and how much of it is listed, city and the reasons behind the score. Registered servers, allowlisted addresses and anyone who logged in are never reported.
hash
av_hash_lookup
CrushAV file reputation, no key needed: look up up to 100 SHA-256 file hashes. For each hash something is known about, returns `knownMalicious` (the source listing it as malware), `malwareName`, `trust` (0-100: how sure CIRCL hashlookup is that this is a published, known-good file from NSRL or a major OS/package repo) and a `fileName` it was seen as. Unknown hashes are omitted. Send hashes only, never file contents.
invite
create_invite
Create one invite link (each account has 3, single use, 30 days). When a new account joins on it and confirms its email, both get bonus credits. Session token only.
invites
list_invites
The signed-in account's invites: how many are left of 3, who joined, and whether the bonus credits were paid. Session token only.
redeem
redeem_credit_code
Redeem a ThreatCrush credit code (CR-XXXX-XXXX-XXXX-XXXX) into the signed-in account's credit balance (1 credit = $1.00). Needs the account's session token (`threatcrush login`), not a tc_agent_ key: agent keys belong to a team, not a person.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://threatcrush.com/api/mcp | streamable-http | answering | 355 ms | 7 min ago |
Alternatives to threatcrush
same job, measured the same wayAgent Security
by mdfifty50-boop
Security scanning and threat detection for AI agents
The Agent Commons
by startekenterprises-ai
Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools.
V
vetkit
by vetkit
Audit repos for security, code quality and AI code risks; read findings and open fix PRs.
T
Traceproof
by raised-traceproof
Search security findings and contribute versioned, evidence-backed reproduction reports.
Security Engineer
by guardbee
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
Hackaiz
by hacktualiz
Analyze authorized assets and read security findings through your Hackaiz account.
Claw GRC
by clawgrc
AI-native GRC: compliance scores, security findings, tickets and agent trust tiers.
Eleion Scanner
by hernaninverso
Register/verify your domains, queue security scans, and read findings (CVE, severity).
threatcrush — questions
Answers built from our own checks of this server.
What can threatcrush do?
It exposes 20 tools, read directly from the server on our last check. Among them: av_hash_lookup, create_invite, findings_get, findings_list, findings_triage, incidents_get and 14 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
What is threatcrush mostly used for?
Its tools cluster around webhooks, incidents and findings. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is threatcrush working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 12 of 13 checks got a reply (92.3%), average response time 362 ms. The bar chart above shows every period we have measured.
How do I connect threatcrush?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does threatcrush need an API key?
No. threatcrush completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 20 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is threatcrush?
It answers our handshake in 362 ms on average, which is faster than 38% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.