Skip to content

Mitigant MCP server

io.github.mitigant/mitigant-mcpmitigantstreamable-httpv0.1.0Scanned

Run real, auto-recovered cloud attacks on AWS, Azure and GCP to test your defenses.

14 tools: 2 can delete or cancel things, 1 change things and 11 only read.

Tools: 2 delete, 0 irreversible, 1 write, 11 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 0
  • 1 finding, 1 high

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here can delete or cancel things. 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 Mitigant MCP server can do

The Mitigant MCP server is published by the GitHub account mitigant. It has 14 tools. It can delete or cancel things (2 tools: launch_attack and launch_scenario) and create or change data (1 tool: clean_up_attack). 11 tools only read.

1 tool brings in text other people can write (list_attacks).

The fixed checks matched 1 finding, 1 of them high severity (model-directed-text). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 9, 2026, version 0.1.0.

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.

14 tools

Deletes or cancels 2Claude Code: deny
  • launch_attackRun an attack against a cloud account connected to Mitigant.No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Run an attack against a cloud account connected to Mitigant. Returns the result if it finishes within wait_seconds (default 20); otherwise it returns at once with the attackId and status RUNNING while the attack keeps running -- then poll get_attack_status with that attackId, and never launch it again (that would start a second attack). This performs real actions on real cloud infrastructure -- it is not a simulation. Confirm with the user before calling: if their request could match more than one attack in list_attacks (similar names, or an underspecified description like "the security group attack"), show them the matching candidates with their names and descriptions and have them pick one -- don't guess which attack they meant. Some attacks need a person to act during the run (e.g. Azure device code flow abuse and other phishing-style attacks wait for someone to enter a code and sign in): tell the user that before launching, expect several minutes of runtime with no result yet, and know that outcome NOT_EXECUTED is the normal result when nobody completes that step -- report it as "did not run" with its reason, not as a fault or a no-op.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • launch_scenarioRun a multi-step attack chain against a cloud account connected to Mitigant.No findings

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Run a multi-step attack chain against a cloud account connected to Mitigant. Returns the result if every step finishes within wait_seconds (default 20); a multi-step scenario usually takes longer, so expect it to return at once with the attackId and status RUNNING while it keeps running -- then poll get_attack_status with that attackId, and never launch it again (that would start a second scenario). This performs real actions on real cloud infrastructure, as several attacks in sequence -- it is not a simulation, and its blast radius is the combined blast radius of every step. Confirm with the user before calling: if their request could match more than one scenario in list_scenarios, show them the matching candidates with their names and descriptions and have them pick one -- don't guess which scenario they meant.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
Changes things 1Claude Code: ask
  • clean_up_attackClean up a previously launched attack, restoring the cloud resources it changed back to their pre-attack state.1 finding

    Why it is in this group

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

    Findings

    • High

      The description contains "do not tell the user", an instruction to keep something from the user.

      Matched text

      description: "...until cleanup.cleanUpComplete is true; do not tell the user it is restored based on this call alone..."

      What this check looks for
    Description, as the server wrote it
    Clean up a previously launched attack, restoring the cloud resources it changed back to their pre-attack state. Clean-up is normally AUTOMATIC after a short, deliberate inspection window (so the team can verify the attack and collect evidence first); calling this kicks it off immediately rather than waiting out that window. It is NOT a fix for a stall, and it ends that window early -- removing the attack's artifacts before the team may have finished inspecting them -- so only use it when the user explicitly wants the account restored now. This triggers clean-up and returns immediately -- clean-up runs in the background, so a success here means the request was accepted, not that clean-up is done. Confirm the account is actually restored by polling get_attack_status until cleanup.cleanUpComplete is true; do not tell the user it is restored based on this call alone.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
Only reads 11Show 11 read-only tools
  • get_attack_detailsFull description, impact, MITRE mapping, and orchestration type (PROVISIONED or INLINE -- PROVISIONED attacks create and destroy their own target rather than targeting your existin…No findings

    Why it is in this group

    • The name "get_attack_details" says "get": a word for reading.
    Description, as the server wrote it
    Full description, impact, MITRE mapping, and orchestration type (PROVISIONED or INLINE -- PROVISIONED attacks create and destroy their own target rather than targeting your existing infrastructure (they may still read or use existing resources along the way), so they're the lower-risk, production-viable choice; INLINE attacks find and attack an existing resource in the account) for one attack, by the action key from list_attacks. Result includes attackName (show this to the user) alongside the attackType you passed in (an opaque id, not for display).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • get_attack_evidenceGet the evidence Mitigant collected for a previously launched attack -- what the account's own logging (CloudTrail, GuardDuty) recorded about it.No findings

    Why it is in this group

    • The name "get_attack_evidence" says "get": a word for reading.
    Description, as the server wrote it
    Get the evidence Mitigant collected for a previously launched attack -- what the account's own logging (CloudTrail, GuardDuty) recorded about it. Returns an 'evidence' summary (counts, sources, and a plain-language statement) plus the raw records, each with an evidenceUrl that opens the matching console entry. Use it to show the user what their defenses saw, especially during the clean-up inspection window. Important: an empty or pending result shortly after an attack is normal -- logging delivery lags by minutes, and evidence usually appears within a few minutes -- and an attack whose purpose is to disable logging is expected to leave none, so never report an empty result as the attack leaving no trace; re-check about every minute or two, for up to 30 minutes after the attack, and not more often. An attack whose outcome is NOT_EXECUTED or FAIL changed nothing, so no evidence will ever exist for it; an attack still running has none yet. Read evidence.statement and relay it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • get_attack_statusGet the current report for a previously launched attack, including its clean-up state.No findings

    Why it is in this group

    • The name "get_attack_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the current report for a previously launched attack, including its clean-up state. Returns the attack report plus a 'cleanup' summary with cleanUpComplete and a plain-language statement. Only tell the user the account is back to its pre-attack state when cleanup.cleanUpComplete is true -- while anything is pending or failed, clean-up is not done, so report it as in progress and check again rather than implying all-clear. A pending clean-up is usually the DELIBERATE inspection window, not a stall: read cleanup.statement and relay it, and poll no faster than that -- a few minutes -- rather than reporting a fault. Each report summary carries 'outcome' (SUCCESS, FAIL, NOT_EXECUTED, CANCELED, IN_PROGRESS) and, when there is one, 'reason': key on those, never on the free-text 'status'. NOT_EXECUTED / FAIL means the step changed nothing, so there is nothing to clean up. While attackStatus or any outcome is IN_PROGRESS, or there are no summaries yet, the attack is still running (attacks that wait for a person, e.g. device code, take minutes): poll again and do not conclude anything.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • get_attacks_by_threat_actorFind the managed attacks that demonstrate a named threat actor's real techniques, for one cloud service -- e.g.No findings

    Why it is in this group

    • The name "get_attacks_by_threat_actor" says "get": a word for reading.
    Description, as the server wrote it
    Find the managed attacks that demonstrate a named threat actor's real techniques, for one cloud service -- e.g. 'which Azure attacks demonstrate Scattered Spider', or to plan a red team exercise around one actor's known behavior. Get the actor's exact name from list_threat_actors first. Each result includes the same fields as list_attacks, plus matchedThreatActorTechniques: exactly which of that attack's own technique id(s) this actor is cited for (never that attack's full technique list, since one attack can implement several techniques and only some may belong to this actor). An actor with no mapped technique yet returns an empty list, not an error.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • get_contextCheck this account's context before planning or launching: whether it is a Mitigant DEMO account and what that allows.No findings

    Why it is in this group

    • The name "get_context" says "get": a word for reading.
    Description, as the server wrote it
    Check this account's context before planning or launching: whether it is a Mitigant DEMO account and what that allows. Call this first on a new connection. If isDemo is true, every attack or scenario with allowedOnDemo=false WILL be rejected at launch -- treat those as not runnable and don't attempt them; use list_attacks' allowedOnDemo field (or list_scenarios demo_only:true) to pick ones that run. Returns no account/org identity, just the demo status, what you can do, and how to upgrade.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • get_scenario_detailsFull details for one attack scenario -- description, impact, and the step-by-step composition, by the scenario key from list_scenarios.No findings

    Why it is in this group

    • The name "get_scenario_details" says "get": a word for reading.
    Description, as the server wrote it
    Full details for one attack scenario -- description, impact, and the step-by-step composition, by the scenario key from list_scenarios. A scenario runs several attacks in sequence; this returns every step, not just the first. Result includes scenarioName (show this to the user) alongside the scenarioKey you passed in (an opaque id, not for display).

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • list_attacksBrowse Mitigant's attack actions -- atomic tests that each emulate one attacker technique -- that you can launch on their own against AWS, Azure or GCP.Reads text others writeNo findings

    Why it is in this group

    • The name "list_attacks" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Browse Mitigant's attack actions -- atomic tests that each emulate one attacker technique -- that you can launch on their own against AWS, Azure or GCP. Currently 111 attack actions (AWS 49, Azure 36, GCP 26). Returns each action's attackName (show this to the user) and attackType (an opaque id -- pass this, not attackName, to get_attack_details or launch_attack), what it does, its impact, the MITRE ATT&CK technique it maps to, and its orchestration type (PROVISIONED or INLINE -- see orchestration_filter for what these mean). Optionally filter by cloud service (S3, IAM, ...), category, or orchestration type. Some attack actions run only as steps inside a scenario and appear via list_scenarios / get_scenario_details, not here. Start here to find an attack action to run.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • list_cloud_accountsList the cloud accounts available for attack emulation -- any account not listed here cannot be attacked, so check this before guessing an account_no for launch_attack.No findings

    Why it is in this group

    • The name "list_cloud_accounts" says "list": a word for reading.
    Description, as the server wrote it
    List the cloud accounts available for attack emulation -- any account not listed here cannot be attacked, so check this before guessing an account_no for launch_attack. An empty result means no accounts are onboarded for attack emulation (for that cloud, or at all), not a failure -- the account may still exist in Mitigant for other purposes (e.g. posture scanning) without being eligible here. Each result's accountNo is already the value launch_attack expects; accountName is for display to the user. defaultRegion is the region attacks against that account run in by default (and where their evidence is collected); it can be overridden per attack request, but unless you do, actions target that region. State it when telling the user where an attack will run.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • list_recent_attacksList your own recent attack and scenario runs for a cloud account, most recent first, each with its attackId and status.No findings

    Why it is in this group

    • The name "list_recent_attacks" says "list": a word for reading.
    Description, as the server wrote it
    List your own recent attack and scenario runs for a cloud account, most recent first, each with its attackId and status. Use this to recover an attackId you no longer have -- for example when a launch_attack / launch_scenario call's connection dropped before it returned, or to check whether a long-running scenario is still running or has failed -- then pass the attackId to get_attack_status, get_attack_evidence or clean_up_attack. Shows only your own runs, not other users' activity on the account.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • list_scenariosList Mitigant's attack scenarios -- multi-step chains that combine several attack actions run in sequence, so treat a scenario as having the combined blast radius of every step.No findings

    Why it is in this group

    • The name "list_scenarios" says "list": a word for reading.
    Description, as the server wrote it
    List Mitigant's attack scenarios -- multi-step chains that combine several attack actions run in sequence, so treat a scenario as having the combined blast radius of every step. Currently 45 scenarios (AWS 26, Azure 12, GCP 7). Returns each scenario's scenarioName (show this to the user) and scenarioKey (an opaque id -- pass this, not scenarioName, to get_scenario_details or launch_scenario), plus description, impact, and the step-by-step composition (each attack action's name, service, MITRE mapping, and impact). Use this to find a multi-step chain to run; use list_attacks instead for a single attack action.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
  • list_threat_actorsList every real-world threat actor Mitigant's catalog tracks (name, description, references).No findings

    Why it is in this group

    • The name "list_threat_actors" says "list": a word for reading.
    Description, as the server wrote it
    List every real-world threat actor Mitigant's catalog tracks (name, description, references). Not scoped to a cloud service. Use this to find an actor's exact name (e.g. 'Storm-0940', 'Scattered Spider') before calling get_attacks_by_threat_actor, or to summarize what an actor is known for directly from its description. An actor can legitimately have no attacks mapped yet -- the report documenting it never cited a specific MITRE ATT&CK technique id, so nothing is attributed to it rather than guessed.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: 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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

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 16, 2026, 14:23 UTC, unchanged since Oct 25, 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
3
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 3 tools that change things (2 destructive, 1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.mitigant.io/mcp: tools/list returned 14 tools to an anonymous client, including launch_attack (destructive), launch_scenario (destructive), clean_up_attack (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 high
  • The description contains "do not tell the user", an instruction to keep something from the user.

    Matched text

    description: "...until cleanup.cleanUpComplete is true; do not tell the user it is restored based on this call alone..."

    What this check looks for

History

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

  1. Tools4 added, 6 changed.+4 added~6 changedView diff

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http mitigant https://mcp.mitigant.io/mcp --header 'apiToken: <your-apitoken>'
claude mcp add --transport http mitigant https://mcp.mitigant.io/mcp --header 'apiToken: <your-apitoken>'

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__mitigant__list_attacks",
      "mcp__mitigant__get_attack_details",
      "mcp__mitigant__list_cloud_accounts",
      "mcp__mitigant__list_scenarios",
      "mcp__mitigant__get_scenario_details",
      "mcp__mitigant__get_attack_status",
      "mcp__mitigant__list_recent_attacks",
      "mcp__mitigant__get_context",
      "mcp__mitigant__get_attack_evidence",
      "mcp__mitigant__list_threat_actors",
      "mcp__mitigant__get_attacks_by_threat_actor"
    ],
    "ask": [
      "mcp__mitigant__clean_up_attack"
    ],
    "deny": [
      "mcp__mitigant__launch_attack",
      "mcp__mitigant__launch_scenario"
    ]
  }
}

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 mitigant. Review it before you use it.

Capability tags behind 1 rule
  • mcp__mitigant__list_attacks untrusted-input

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/io.github.mitigant/mitigant-mcp/verify?hash=9359ac5d6ea498908ee7b40bb6c7af0267b8c68c6028bfaaa3acdec685605903" | jq -e '.changed == false'

Pinned hash 9359ac5d6ea4, from Nov 9, 2026, 05:17 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.mitigant/mitigant-mcp/changes.xml

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

Badge

Anlyon Radar badge for io.github.mitigant/mitigant-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.mitigant/mitigant-mcp.svg)](https://radar.anlyon.com/servers/io.github.mitigant/mitigant-mcp)

Source: MCP Registry · repository. Synced Oct 25, 2026, 13:17 UTC.

Mitigant MCP server: questions and answers

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

Is the Mitigant MCP server safe?

No scan can promise that. What its definitions show: 14 tools, 3 of which can change, send or delete something, and 1 finding (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Mitigant MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: launch_attack and launch_scenario.

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

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Mitigant MCP server have?

14 tools: 2 destructive, 1 write, 11 read. launch_attack, launch_scenario, clean_up_attack, list_attacks, get_attack_details, list_cloud_accounts, list_scenarios, get_scenario_details and 6 more.

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

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

Does the Mitigant MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the Mitigant MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.