Agents Index

Mitigant

OnlineNew

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

Visit publisherConnectJSON

What it can do: 16 tools

  • list_attacks read-onlyBrowse 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 128 attack actions (AWS 66, Azure 36, GCP 26). Returns ea
  • get_attack_details read-onlyFull 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
  • launch_attackRun 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 ru
  • list_cloud_accounts read-onlyList 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
  • list_scenarios read-onlyList 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 50 scenarios (AWS 31, Azure 12,
  • get_scenario_details read-onlyFull 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 f
  • launch_scenarioRun 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
  • get_attack_status read-onlyGet 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 accoun
  • list_recent_attacks read-onlyList 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_sce
  • get_context read-onlyCheck 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=f
  • clean_up_attackClean 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 attac
  • get_attack_evidence read-onlyGet 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 state
  • list_threat_actors read-onlyList every real-world threat actor Mitigant's catalog tracks (name, description, references, other names the actor is known by with the source of each, and the tools it uses). Not scoped to a cloud service. Use this to f
  • get_attacks_by_threat_actor read-onlyFind 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
  • list_adversary_tools read-onlyList the tools and frameworks attackers use that Mitigant's catalog tracks, for example the AI attack framework ARTEX, Pacu, AADInternals, ROADTools, Peirates and AndroxGh0st. Each has a name, description, references, wh
  • get_attacks_by_adversary_tool read-onlyFind the managed attacks that reproduce what a named adversary tool is reported to do, for one cloud service -- e.g. 'which AWS attacks reproduce ARTEX', or 'run what Pacu does'. The tool itself is not an attack; these a

Connect it

Claude Code
claude mcp add --transport http mitigant https://mcp.mitigant.io/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.mitigant.io/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "mitigant": {
      "url": "https://mcp.mitigant.io/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "mitigant": {
      "type": "http",
      "url": "https://mcp.mitigant.io/mcp"
    }
  }
}

Questions

What does Mitigant do?

Run real, auto-recovered cloud attacks on AWS, Azure and GCP to test your defenses. It exposes 16 tools to AI assistants.

What tools does Mitigant provide?

16 tools, including list_attacks, get_attack_details, launch_attack, list_cloud_accounts, list_scenarios, get_scenario_details, launch_scenario, get_attack_status, list_recent_attacks, get_context, clean_up_attack, get_attack_evidence….

How do I connect Mitigant to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.mitigant.io/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Mitigant require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Mitigant online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Mitigant?

@mitigant on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Cloud & DevOps