Huntress

io.github.WYRE-AIPublished by GitHub account WYRE-AIv1.2.24Updated Nov 4, 2026

MCP server for Huntress — accounts, organizations, agents, incidents, and reports.

VerifiedSTDIODesktop onlySecurity & MonitoringBusiness & Commerce

Overview

AI-generated overview

MCP server giving AI assistants structured access to Huntress cybersecurity platform data: accounts, organizations, agents, incidents, billing, signals and…

What you can do
  • Explore Huntress domains through a navigation tool, then load domain-specific tools
  • Read account info and the current actor, and list or fetch agents
  • List, get, create, update and delete organizations
  • Work with incidents: reports, remediations (approve or reject) and escalations (resolve)
  • Review billing and summary reports, and list or fetch security signals
  • Manage user memberships with full create, read, update and delete operations
When to use it
Useful when an assistant should answer questions or take action on a Huntress security account — reviewing incidents, escalations and signals, checking billing reports, or maintaining organizations and memberships — without switching to the Huntress console.
Requirements
Runs as a local process over stdio, or as an HTTP container from the published image. Needs Huntress API credentials in HUNTRESS_API_KEY and HUNTRESS_API_SECRET for stdio or env auth mode; the Docker image defaults to gateway mode, where credentials arrive as request headers and CONDUIT_S2S_SECRET is required. Node.js is needed only for the npx or from-source routes.
Before you install
Requires a Huntress API key and secret, which grant access to your security tenant data. Tools include create, update and delete for organizations and memberships, and approve or reject for remediations, so assistant actions can change real data. HTTP mode needs a strong CONDUIT_S2S_SECRET; never commit it, and avoid the insecure development override outside local testing.

Installation

In SourceWeft

  1. Open Huntress in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Huntress MCP Server

[Build Status] [License] [Node.js]

A Model Context Protocol (MCP) server that provides AI assistants with structured access to Huntress cybersecurity platform data and operations.

Note: This project is maintained by Wyre Technology.

Quick Start

Claude Desktop — download, open, done:

  1. Download huntress-mcp.mcpb from the latest release
  2. Open the file (double-click or drag into Claude Desktop)
  3. Enter your Huntress credentials when prompted (API Key, API Secret)

No terminal, no JSON editing, no Node.js install required.

Claude Code (CLI):

bash
claude mcp add huntress-mcp \  -e HUNTRESS_API_KEY=your-api-key \  -e HUNTRESS_API_SECRET=your-api-secret \  -- npx -y github:WYRE-AI/huntress-mcp

See Installation for Docker and from-source methods.

Features

  • 🔌 MCP Protocol Compliance: Full support for MCP resources and tools
  • 🛡️ Comprehensive Security Coverage: Tools spanning agents, organizations, incidents, escalations, billing, signals, and users
  • 🔍 Decision-Tree Navigation: Start with huntress_navigate to explore domains, then dynamically load domain-specific tools
  • 📝 CRUD Operations: Create, read, update, delete operations for organizations, memberships, incidents, and more
  • 🔒 Secure Authentication: HTTP Basic Auth with Huntress API credentials
  • 🌐 Dual Transport: Supports both stdio (local) and HTTP Streamable (remote/Docker) transports
  • 📦 MCPB Packaging: One-click installation via MCP Bundle for desktop clients
  • 🐳 Docker Ready: Containerized deployment with HTTP transport and health checks
  • ⚡ Rate Limiting: Built-in rate limiter respects Huntress API limits (60 req/min)
  • 📊 Structured Logging: Comprehensive logging with configurable levels

Table of Contents

Installation

Option 1: MCPB Bundle (Claude Desktop)

The simplest method — no terminal, no JSON editing, no Node.js install required.

  1. Download huntress-mcp.mcpb from the latest release
  2. Open the file (double-click or drag into Claude Desktop)
  3. Enter your Huntress credentials when prompted (API Key, API Secret)

For Claude Code (CLI), one command:

bash
claude mcp add huntress-mcp \  -e HUNTRESS_API_KEY=your-api-key \  -e HUNTRESS_API_SECRET=your-api-secret \  -- npx -y github:WYRE-AI/huntress-mcp

Option 2: Docker

The image listens on 0.0.0.0 inside the container and defaults to AUTH_MODE=gateway. Publish the port on loopback and pass the service-to-service secret. In gateway mode, Huntress credentials arrive on each request as headers; they are not read from the environment.

bash
docker run -d \  -e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \  -p 127.0.0.1:8080:8080 \  ghcr.io/wyre-ai/huntress-mcp:latest

Compose refuses to start when CONDUIT_S2S_SECRET is unset:

bash
CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose up

Option 3: From Source

bash
git clone https://github.com/WYRE-AI/huntress-mcp.gitcd huntress-mcpnpm cinpm run build

Configuration

Copy .env.example and set the variables below.

VariableRequiredDescription
HUNTRESS_API_KEYFor stdio and AUTH_MODE=envHuntress API public key
HUNTRESS_API_SECRETFor stdio and AUTH_MODE=envHuntress API secret
MCP_TRANSPORTNostdio (default) or http
AUTH_MODENogateway (Docker image and Compose default) or env. Gateway mode requires X-Huntress-Api-Key and X-Huntress-Api-Secret on each /mcp request and never falls back to HUNTRESS_*. env uses those variables only after S2S auth succeeds.
CONDUIT_S2S_SECRETYes for HTTPService-to-service secret. The HTTP server logs an error and exits non-zero when this is empty or a known placeholder (changeme, secret, replace-me, your-s2s-secret, and the other example values). Compose will not start without it. Never commit a real value. Generate one with openssl rand -hex 32.
MCP_ALLOW_INSECURE_DEVNoSet to exactly 1 only for local development to start HTTP without CONDUIT_S2S_SECRET. The process logs a warning, does not enforce X-Gateway-S2S, and listens on 127.0.0.1 only. A non-loopback MCP_HTTP_HOST (including 0.0.0.0) is ignored and the override is logged. A known placeholder secret is still refused.
MCP_HTTP_HOSTNoBind address when CONDUIT_S2S_SECRET is set. Defaults to 127.0.0.1 when unset. The container image sets 0.0.0.0.
MCP_HTTP_PORTNoHTTP port. Defaults to 8080.
LOG_LEVELNoLog level (debug, info, warn, error). Defaults to info.

/health and /healthz stay unauthenticated and do not read credentials. The stdio transport does not use CONDUIT_S2S_SECRET.

HTTP authentication

With MCP_TRANSPORT=http and CONDUIT_S2S_SECRET set, every /mcp request must include X-Gateway-S2S:

t=<unix seconds>,v1=<hex hmac-sha256>

v1 is HMAC-SHA256 over the exact message t=<unix seconds>, keyed with CONDUIT_S2S_SECRET, hex-encoded. The timestamp must be within 300 seconds of the server clock. A missing or invalid header returns 401. The secret is never written to logs.

javascript
import { createHmac } from 'node:crypto';
const t = Math.floor(Date.now() / 1000);const v1 = createHmac('sha256', process.env.CONDUIT_S2S_SECRET).update(`t=${t}`).digest('hex');const xGatewayS2s = `t=${t},v1=${v1}`;

In AUTH_MODE=gateway, /mcp also requires X-Huntress-Api-Key and X-Huntress-Api-Secret. Those headers are the only credential source for that request. A request missing either header returns 401 and does not fall back to HUNTRESS_API_KEY / HUNTRESS_API_SECRET.

javascript
await fetch('http://127.0.0.1:8080/mcp', {  method: 'POST',  headers: {    'content-type': 'application/json',    accept: 'application/json, text/event-stream',    'x-gateway-s2s': xGatewayS2s,    'x-huntress-api-key': apiKey,    'x-huntress-api-secret': apiSecret,  },  body: JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'tools/list' }),});

Domains

The server uses decision-tree navigation. Start with huntress_navigate to pick a domain:

DomainTools
accountsGet account info, get current actor
agentsList agents, get agent by ID
organizationsList, get, create, update, delete organizations
incidentsIncident reports (list/get/resolve), remediations (list/get/approve/reject), escalations (list/get/resolve)
billingBilling reports, summary reports
signalsList/get security signals
usersMembership CRUD (list/get/create/update/delete)

Docker Deployment

See docker-compose.yml for full configuration. The checked-in Compose service is gateway mode. It does not set HUNTRESS_API_KEY or HUNTRESS_API_SECRET and does not use env_file, so a project .env cannot inject static vendor credentials into the container. Compose still interpolates CONDUIT_S2S_SECRET from that file and will not start when it is unset. The port is published on 127.0.0.1.

bash
cp .env.example .env# Set CONDUIT_S2S_SECRET. Leave it empty in the example; never commit a real value.CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" docker compose up -d

Single-tenant HTTP (AUTH_MODE=env) still requires the S2S secret, then uses HUNTRESS_API_KEY and HUNTRESS_API_SECRET. It is separate from the gateway Compose service:

bash
docker run -d \  -e CONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" \  -e AUTH_MODE=env \  -e HUNTRESS_API_KEY=your-key \  -e HUNTRESS_API_SECRET=your-secret \  -p 127.0.0.1:8080:8080 \  ghcr.io/wyre-ai/huntress-mcp:latest

Local HTTP without a secret is development-only. It binds 127.0.0.1 only and logs a warning:

bash
MCP_TRANSPORT=http MCP_ALLOW_INSECURE_DEV=1 npm run start:http

Development

bash
npm cinpm run build       # Build the projectnpm run dev         # Watch modenpm run test        # Run testsnpm run lint        # Type-checknpm run clean       # Remove dist/
# HTTP refuses to start until CONDUIT_S2S_SECRET is setCONDUIT_S2S_SECRET="$CONDUIT_S2S_SECRET" npm run start:http
# Local HTTP only, without a service-to-service secret (always binds 127.0.0.1)MCP_ALLOW_INSECURE_DEV=1 npm run start:http

Testing

bash
npm test            # Run test suitenpm run test:watch  # Watch mode

Contributing

See CONTRIBUTING.md for guidelines.

License

Apache 2.0 — Copyright WYRE Technology

Source: README.md at commit 946adcf

Tools

0
SourceWeft started this package once in an isolated sandbox, without credentials, to list its tools. That failed: the package type cannot run in the sandbox.

Version history

4
  1. v1.2.24LatestNov 4, 2026
  2. v1.2.23Oct 14, 2026
  3. v1.2.22Oct 8, 2026
  4. v1.2.21Sep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.