Huntress MCP Server

An MCP server for the Huntress API (v1), the managed security (EDR / ITDR / SIEM) platform MSPs use to protect their clients. It lets an AI agent read the account, organizations, agents (protected endpoints), incident reports and their remediations, escalations, signals, users, invoices and summary reports and, on explicit request, resolve incidents and escalations, approve or reject remediations, and manage organizations and users.

• Transport: MCP Streamable HTTP at POST /mcp, health probe at GET /health

• Stateless and multi-tenant: credentials arrive on every request as HTTP headers and are never stored; every tool is listed from the first tools/list

• Python 3.12, uv, FastMCP, httpx

• License: Apache-2.0, Copyright 2026 MSPbots.ai

Authentication headers

Where to get them: in the Huntress portal open API Credentials and generate a key pair. Keep the secret when it is shown; it is needed together with the key.

How they are sent to Huntress: every call goes to https://api.huntress.io/v1/... with HTTP Basic authentication (key:secret).

A request to /mcp without both headers gets HTTP 401 naming the missing one.

Related MCP server: defender-xdr

Tools

All tools return a JSON string. List tools take limit (default 10, max 500) and page_token and return {count, has_more, next_page_token}; pass next_page_token back as page_token for the next page. write marks tools that change data; confirm marks tools that also need confirm: true.

Errors come back as a JSON envelope instead of an exception:

{"error": {"code": "unauthorized", "message": "Huntress returned HTTP 401 for agents: Unauthorized", "retryable": false}}

code is one of not_configured, unauthorized, not_found, invalid_argument, rate_limited, upstream_error. Reads are retried with backoff on 429, 5xx and network errors; writes only on 429. Huntress allows about 60 API requests per minute.

Run locally

uv sync
uv run python -m huntress_mcp          # listens on 0.0.0.0:8080

or with Docker:

docker build --platform linux/amd64 -t huntress-mcp:dev .
docker run --rm -p 8080:8080 huntress-mcp:dev

Configuration (environment variables, all optional): MCP_HTTP_HOST (default 0.0.0.0), MCP_HTTP_PORT (default 8080), LOG_LEVEL (default INFO). Credentials are never read from the environment.

Testing example

# list tools
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Huntress-Api-Key: your-api-key" \
  -H "X-Huntress-Api-Secret: your-api-secret" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# open critical incidents
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Huntress-Api-Key: your-api-key" \
  -H "X-Huntress-Api-Secret: your-api-secret" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"huntress_incidents_list","arguments":{"status":"sent","severity":"critical"}}}'

Unit tests (no network access needed):

uv run pytest

Delivery notes

• Tool count (32). Kept as is because the tool names are an existing contract.

• Billing reports are invoices. The Huntress API has no /billing_reports endpoint; older versions called it, so both billing tools failed. huntress_billing_reports_list / _get now read /invoices, keeping their names.

• Confirmation for high-impact actions. Approving remediations (they run on endpoints), changing a user's permission level and deleting organizations or users take confirm: true and otherwise return a "not done" result.

• Rejecting remediations sends useful (required by the API, default false) and accepts the optional reason code; approving accepts manual_completion_remediation_ids.

• Updates use PATCH with only the fields given; an update with no fields is rejected locally.

License

Apache License 2.0 - see LICENSE and NOTICE.