Huntress logoMCP server · Engineering and operations

Huntress MCP server

Huntress in any MCP client, through Memtro: Huntress does not publish this server. Memtro's Huntress connector reads Huntress through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

Huntress managed security: incident reports (subject, SOC summary, severity, status, platform, organization, indicators) and their remediation plans and comments, escalations, agents on protected endpoints by host name (OS, versions, isolation and Defender status, tamper protection, tags), SOC signals, and organizations with their counts. Can comment on a report, approve or reject its remediation plan, mark a manual remediation done, resolve a report or an escalation, isolate or release a host, and set an agent's tags or tamper protection, each only when asked.

Reads

  • huntress_incident_reportsHuntress incident reports, newest first: subject, severity, status (sent means awaiting the partner, closed, dismissed, auto_remediating), platform…
  • huntress_incident_reportOne Huntress incident report by id with its whole remediation plan: each remediation's type (assisted, manual, containment), status (unapproved…
  • huntress_report_commentsComments on a Huntress incident report, oldest first: author (the Huntress SOC or a person in the account), text and when.
  • huntress_escalationsHuntress escalations (the SOC asking the partner to decide something, such as an unexpected country or VPN sign-in or a suspected false positive)…
  • huntress_agentsHuntress agents (protected endpoints): id, host name, domain, organization (name and id), platform, OS, agent and EDR versions, firewall status…
  • huntress_signalsHuntress signals (behaviours a SOC analyst investigated), newest first: name, type, status (reported, closed), the analyst's investigation context…
  • huntress_organizationsOrganizations (the customers or sites) in the Huntress account: id, name, key, and counts of agents, incident reports, log sources…

Acts, when you ask

These change something in Huntress. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

  • huntress_comment_on_reportAdd a comment to a Huntress incident report.
  • huntress_approve_remediationsApprove every unapproved remediation on a Huntress incident report.
  • huntress_reject_remediationsReject every unapproved remediation on a Huntress incident report…
  • huntress_complete_remediationRecord that a manual remediation on a Huntress incident report has been carried out (or, with completed false, undo that).
  • huntress_resolve_reportResolve a Huntress incident report.
  • huntress_resolve_escalationResolve a Huntress escalation.
  • huntress_isolate_agentIsolate a host protected by Huntress, cutting it off from the network while keeping its connection to Huntress.
  • huntress_release_agentRelease a host from Huntress isolation, restoring its network access.
  • huntress_set_agent_tagsReplace a Huntress agent's tags with the list given (an empty list removes them all).
  • huntress_set_tamper_protectionTurn EDR tamper protection on or off for one Huntress agent.

Connect it

First connect Huntress on Dashboard → Connections, then add Memtro to your client once. The Huntress tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Pi

One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared Huntress connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

  • › Which incident reports are waiting on us?
  • › What remediations has the SOC proposed for the latest critical report?
  • › Which hosts are isolated right now?
  • › Which escalations are overdue?
  • › Isolate the host ACME-WS-114 from the network

Questions

Is this an official Huntress MCP server?
No. It is Memtro's MCP server with Memtro's Huntress connector behind it: the connector reads Huntress through its API with the credentials you connect on Dashboard → Connections, and Huntress publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?
Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in Huntress?
Only when you ask, and only what it has been granted: comment on an incident report (people who get incident report notifications are told); approve an incident report's remediation plan (Huntress runs the assisted remediations at once); reject an incident report's remediation plan (sends it back to the Huntress SOC); mark a manual remediation as done or not done; resolve an incident report (permanent); resolve an escalation (for unwanted-access escalations this can create access rules and revoke and disable identities); isolate a host from the network; release a host from isolation; replace an agent's tags; turn an agent's tamper protection on or off. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?
Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

Other MCP servers · Engineering and operations

Where agents remember your company

Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.

7-day free trial · card on file, nothing charged until it ends · cancel any time