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

MSPbots Connector

The MCP Gateway built for MSPs: visible, controlled, and your data stays where it belongs.

Get started at connect.mspbots.ai →

MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.

Hosted service: connect.mspbots.ai · Free to use.

Why Connector

Quick start

1. Sign up at connect.mspbots.ai.

2. Connect your vendors. Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.

3. Set access. Create roles and decide which tools each role may call. Nothing is allowed until you allow it.

4. Add your MCP URL to your AI client. Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.

5. Ask your AI to do real work, and watch every call appear in the audit log.

Features

Unified gateway

• One MCP URL for all your AI clients

• 150+ connectors across the MSP stack

• Custom MCP servers supported, free

• Authorization happens on each vendor's own page; the AI never sees passwords or tokens

• Bring your own credentials: use the vendor API keys you already have

• Multiple accounts per app; connect once, reuse across AI clients

• Tool search: finds the right action for the task

• One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically

Visibility

• Audit log for every tool call (who, which vendor, when)

• Usage dashboard: call volume, top vendors, error rate, per-user activity

• Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)

• Optional recording of tool arguments and result summaries (off by default, enabled per organization)

Control

• Per-role, per-tool allowlist, deny by default

• owner / admin / member roles

• SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace

Security

• Credentials encrypted one record at a time (AES-256-GCM, per-record key)

• AI clients authenticate with OAuth 2.1 + PKCE

• Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.

• Static egress IP for customer firewall and API allowlisting

Pricing

Free.

Links: connect.mspbots.ai · mspbots.ai

Related MCP server: Inforcer MCP Server

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.

Tools

All tools return a JSON string. List tools take limit (default 10, max 200; larger values are capped) 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.