Skip to content

threatcrush MCP server

com.profullstack/threatcrushprofullstack.comstreamable-httpv1.0.0Scanned

Reputation + security findings (threatcrush.com)

20 tools: 2 can delete or cancel things, 2 do something that can't be undone, 8 change things and 8 only read.

Tools: 2 delete, 2 irreversible, 8 write, 8 read.
  • Reads private data · 3
  • Reads text others write · 7
  • Can send data out · 4
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things and 2 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the threatcrush MCP server can do

The threatcrush MCP server is published by profullstack.com, a domain the MCP Registry verified. It has 20 tools. It can delete or cancel things (2 tools: webhooks_delete and webhooks_rotate_secret), do things that cannot be undone, such as sending, paying or publishing (create_invite and webhooks_test) and create or change data (8 tools: reputation_bulk, redeem_credit_code, findings_triage, incidents_update and 4 more). 8 tools only read.

3 tools read private data (av_hash_lookup, reputation_lookup and incidents_get); 7 tools bring in text other people can write (av_hash_lookup, reputation_lookup, reputation_bulk and 4 more); 4 tools can send data out of your system (create_invite, webhooks_create, webhooks_update and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 11, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

20 tools

Deletes or cancels 2Claude Code: deny
  • webhooks_deleteRemove a webhook endpoint and its delivery log.No findings

    Why it is in this group

    • The name "webhooks_delete" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a webhook endpoint and its delivery log.

    Annotations the server declares

    • title: Delete a webhook endpoint
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: false
  • webhooks_rotate_secretReplace an endpoint's signing secret; the old one stops working at once.No findings

    Why it is in this group

    • The description's first verb is "replace": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replace an endpoint's signing secret; the old one stops working at once. Returns the new secret.

    Annotations the server declares

    • title: Rotate a webhook signing secret
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
Can't be undone 2Claude Code: ask
  • create_inviteCreate one invite link (each account has 3, single use, 30 days).Can send data outNo findings

    Why it is in this group

    • The name "create_invite" says "create": a word for a change.
    • The name "create_invite" also says "invite": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "create_invite" says "invite": it sends or publishes something to other people.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Create an invite link
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • webhooks_testSend a signed webhook.test event to one endpoint now and say how it went.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe description's first verb is "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a signed webhook.test event to one endpoint now and say how it went.

    Annotations the server declares

    • title: Send a test webhook
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 8Claude Code: ask
  • findings_triageSet the status and/or note of up to 500 findings: acknowledged, fixed, false_positive, ignored or open.No findings

    Why it is in this group

    • The description's first verb is "set": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Triage findings
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • incidents_raiseRaise an incident report (report_version 1: title, severity, source, dedupe_key, summary, verdict, findings, timeline, recommendations, optional team_id/server_id).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Raise an incident (pages the team)
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • incidents_updateUpdate 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.No findings

    Why it is in this group

    • The name "incidents_update" says "update": a word for a change.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Update an incident
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • redeem_credit_codeRedeem a ThreatCrush credit code (CR-XXXX-XXXX-XXXX-XXXX) into the signed-in account's credit balance (1 credit = $1.00).No findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Redeem a credit code
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • reputation_bulkLook up many IPs or domains at once (up to 100 with a free key, 1,000 with Reputation Pro).Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Look up many IPs or domains
    • readOnlyHint: true
    • openWorldHint: true
  • webhooks_createAdd a webhook endpoint (public https URL).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "webhooks_create" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Add a webhook endpoint (public https URL). Returns the endpoint and its signing secret (whsec_…), shown once.

    Annotations the server declares

    • title: Add a webhook endpoint
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • webhooks_deliveriesRecent webhook deliveries (status, attempts, last HTTP status/error, payload), for one endpoint or all.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Recent webhook deliveries (status, attempts, last HTTP status/error, payload), for one endpoint or all.

    Annotations the server declares

    • title: List webhook deliveries
    • readOnlyHint: true
    • openWorldHint: false
  • webhooks_updateChange a webhook endpoint's url, events, description, or switch it on/off (on again clears its failure count).Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "webhooks_update" says "update": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Change a webhook endpoint's url, events, description, or switch it on/off (on again clears its failure count).

    Annotations the server declares

    • title: Change a webhook endpoint
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 8Show 8 read-only tools
  • av_hash_lookupCrushAV file reputation, no key needed: look up up to 100 SHA-256 file hashes.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "av_hash_lookup" says "lookup": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "file": it reads files.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Look up file hashes (CrushAV)
    • readOnlyHint: true
    • openWorldHint: true
  • findings_getOne tracked finding with its details (code snippet, remediation, evidence), property and history.No findings

    Why it is in this group

    • The name "findings_get" says "get": a word for reading.
    Description, as the server wrote it
    One tracked finding with its details (code snippet, remediation, evidence), property and history.

    Annotations the server declares

    • title: Get a finding
    • readOnlyHint: true
    • openWorldHint: false
  • findings_listYour org's tracked findings from threatcrush scan, pentest and ai-scan (deduped across runs, with a triage status).No findings

    Why it is in this group

    • The name "findings_list" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List findings
    • readOnlyHint: true
    • openWorldHint: false
  • incidents_getOne 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 an…Reads private dataNo findings

    Why it is in this group

    • The name "incidents_get" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "note": it reads notes.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Get an incident
    • readOnlyHint: true
    • openWorldHint: false
  • incidents_listYour org's incidents: what `threatcrush investigate --raise`, the daemon (critical detections) and people raised to humans.No findings

    Why it is in this group

    • The name "incidents_list" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List incidents
    • readOnlyHint: true
    • openWorldHint: false
  • list_invitesThe signed-in account's invites: how many are left of 3, who joined, and whether the bonus credits were paid.No findings

    Why it is in this group

    • The name "list_invites" says "list": a word for reading.
    Description, as the server wrote it
    The signed-in account's invites: how many are left of 3, who joined, and whether the bonus credits were paid. Session token only.

    Annotations the server declares

    • title: List my invites
    • readOnlyHint: true
    • openWorldHint: false
  • reputation_lookupLook up an IP address or a domain against the ThreatCrush community threat database (what every linked ThreatCrush daemon blocked).Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "reputation_lookup" says "lookup": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "database": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Look up an IP or domain
    • readOnlyHint: true
    • openWorldHint: true
  • webhooks_listYour org's webhook endpoints (signed Standard Webhooks deliveries, retried for about three days) and the events ThreatCrush emits: detection.created, findings.raised, reputation.ch…No findings

    Why it is in this group

    • The name "webhooks_list" says "list": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: List webhook endpoints
    • readOnlyHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

84 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 3 private-data tools breaks every one.

Reads private data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write7
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out4
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__threatcrush__av_hash_lookup",
      "mcp__threatcrush__incidents_get",
      "mcp__threatcrush__reputation_lookup"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:21 UTC, unchanged since Nov 12, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
12
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://threatcrush.com/.well-known/oauth-protected-resource/api/mcp
Authorization servers
https://threatcrush.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 12 tools that change things (2 destructive, 2 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://threatcrush.com/api/mcp: tools/list returned 20 tools to an anonymous client, including webhooks_delete (destructive), webhooks_rotate_secret (destructive), create_invite (irreversible), webhooks_test (irreversible), reputation_bulk (write) and 7 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http threatcrush https://threatcrush.com/api/mcp
claude mcp add --transport http threatcrush https://threatcrush.com/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__threatcrush__av_hash_lookup",
      "mcp__threatcrush__reputation_lookup",
      "mcp__threatcrush__list_invites",
      "mcp__threatcrush__findings_list",
      "mcp__threatcrush__findings_get",
      "mcp__threatcrush__incidents_list",
      "mcp__threatcrush__incidents_get",
      "mcp__threatcrush__webhooks_list"
    ],
    "ask": [
      "mcp__threatcrush__reputation_bulk",
      "mcp__threatcrush__redeem_credit_code",
      "mcp__threatcrush__create_invite",
      "mcp__threatcrush__findings_triage",
      "mcp__threatcrush__incidents_update",
      "mcp__threatcrush__incidents_raise",
      "mcp__threatcrush__webhooks_create",
      "mcp__threatcrush__webhooks_update",
      "mcp__threatcrush__webhooks_test",
      "mcp__threatcrush__webhooks_deliveries"
    ],
    "deny": [
      "mcp__threatcrush__webhooks_delete",
      "mcp__threatcrush__webhooks_rotate_secret"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as threatcrush. Review it before you use it.

Capability tags behind 9 rules
  • mcp__threatcrush__av_hash_lookup private-data, untrusted-input
  • mcp__threatcrush__reputation_lookup private-data, untrusted-input
  • mcp__threatcrush__reputation_bulk untrusted-input
  • mcp__threatcrush__create_invite outbound
  • mcp__threatcrush__incidents_get private-data
  • mcp__threatcrush__incidents_raise untrusted-input
  • mcp__threatcrush__webhooks_create untrusted-input, outbound
  • mcp__threatcrush__webhooks_update untrusted-input, outbound
  • mcp__threatcrush__webhooks_test untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/com.profullstack/threatcrush/verify?hash=528036f4764445a67d12c6cab220ff2442a3643662c6e8507d37280649194f0a" | jq -e '.changed == false'

Pinned hash 528036f47644, from Nov 11, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/com.profullstack/threatcrush/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for com.profullstack/threatcrush
[![Anlyon Radar](https://radar.anlyon.com/badge/com.profullstack/threatcrush.svg)](https://radar.anlyon.com/servers/com.profullstack/threatcrush)

Source: MCP Registry. Synced Nov 11, 2026, 14:17 UTC.

threatcrush MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the threatcrush MCP server safe?

No scan can promise that. What its definitions show: 20 tools, 12 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the threatcrush MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: webhooks_delete and webhooks_rotate_secret.

Can the threatcrush MCP server do things that cannot be undone?

Yes. 2 tools can send, pay, publish or merge: create_invite and webhooks_test.

What tools does the threatcrush MCP server have?

20 tools: 2 destructive, 2 irreversible, 8 write, 8 read. webhooks_delete, webhooks_rotate_secret, create_invite, webhooks_test, reputation_bulk, redeem_credit_code, findings_triage, incidents_update and 12 more.

Does the threatcrush MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the threatcrush MCP server send data to outside services?

4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_invite, webhooks_create, webhooks_update and webhooks_test.

Has the threatcrush MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.