huntress

MCP server for Huntress API integration

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio dynamicendpoints-huntress-mcp-server node path/to/huntress-server/build/index.js \
  --env HUNTRESS_API_KEY="your_api_key_here" \
  --env HUNTRESS_API_SECRET="your_api_secret_here"

How to use

Huntress MCP Server exposes a programmatic interface to interact with the Huntress API. It provides MCP tools for common security workspace tasks, including account management (e.g., retrieving current account information), organization management (listing and inspecting organizations), agent management (listing and inspecting agents), and incident management (listing and inspecting incidents). The server supports HTTP/SSE transport and can be accessed via an MCP-compatible client to discover tools and invoke them. When deployed in HTTP/SSE mode, clients communicate with the root MCP endpoint to discover available tools and perform calls, with a separate health endpoint for container orchestration. Environment-based credentials are loaded lazily, and requests are rate-limited to 60 per minute to align with Huntress API quotas.

How to install

Prerequisites:

Node.js (LTS) and npm installed
Basic familiarity with MCP tooling and Smithery (optional)

Manual installation steps:

Clone the repository git clone https://github.com/your-org/huntress-mcp-server.git cd huntress-mcp-server
Install dependencies npm install
Create a .env file based on the example and insert your Huntress credentials HUNTRESS_API_KEY=your_api_key_here HUNTRESS_API_SECRET=your_api_secret_here
Build the server npm run build
Run the server (stdio/Node.js execution) node path/to/huntress-server/build/index.js

Optional Smithery deployment (container-based):

Install Smithery CLI and deploy following Smithery docs
In Smithery config, map environment variables to HUNTRESS_API_KEY and HUNTRESS_API_SECRET
Use container deployment with HTTP streaming (SSE) as described in the README

Additional notes

Tips and notes:

Ensure HUNTRESS_API_KEY and HUNTRESS_API_SECRET are kept secure and not committed to version control
The server supports both HTTP and SSE transport; in container mode you’ll typically use the HTTP endpoint (e.g., http://localhost:3000/) and the /health endpoint for health checks
Rate limiting is enforced at 60 requests per minute; design your MCP workflow to stay within this quota
Tool discovery can be used without authentication, but actual tool calls require valid credentials
If upgrading MCP SDK or dependencies, test in a development environment before deploying to production

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.