Skip to content
hive-mcp

Security policy

hive-mcp holds a login to a Hive account and can control the heating in someone’s home, so security reports are taken seriously and handled as a priority.

Supported versions

Section titled “Supported versions”

Security fixes go into the latest release. Please upgrade to the newest version before reporting.

Version Supported
Latest release ✅
Older releases ❌

Reporting a vulnerability

Section titled “Reporting a vulnerability”

Please don’t report security vulnerabilities in public issues, discussions or pull requests.

Report them privately through GitHub’s private vulnerability reporting: go to the repository’s Security tab and click Report a vulnerability.

Please include:

  • A description of the issue and its impact
  • Steps to reproduce, or a proof of concept
  • The affected version(s) and configuration, such as transport, HIVE_ALLOW_WRITES and toolsets
  • Any suggested fix, if you have one

Please don’t include real passwords, tokens or token files. Use the mock Hive in the test suite where you can.

What to expect

Section titled “What to expect”
  • An acknowledgement within 3 working days.
  • An initial assessment within 7 days, including whether the report is accepted and a rough timeline.
  • A fix released as soon as practical, with a GitHub security advisory and credit to you, unless you’d rather stay anonymous.

Please give us a reasonable amount of time to fix the issue before you disclose it publicly.

Scope

Section titled “Scope”

In scope:

  • Bypassing MCP_AUTH_TOKEN, MCP_ALLOWED_HOSTS, or the write or toolset gating. An example would be changing the heating through the raw API tool without HIVE_ALLOW_WRITES.
  • Leaking the Hive password, tokens or the remembered device’s secret through tool output, logs or files
  • Weaknesses in the login, such as the SRP implementation, the device registration, or handling the token file in a way that exposes it
  • Getting the server to send SMS codes or make login attempts that could lock an account, without the user asking
  • Vulnerabilities in the Docker image or the release pipeline

Out of scope:

  • Issues that need an attacker who already holds a valid MCP_AUTH_TOKEN and uses only the tools that configuration allows. That’s intended behaviour.
  • Prompt injection that leads the model to call tools the configuration allows. This is a known limitation of AI assistants. docs/security.md explains how to limit the impact.
  • Vulnerabilities in Hive, its app, its API or its login service. Report those to Hive (Centrica) directly. hive-mcp is unofficial and not affiliated with them.

For guidance on deploying hive-mcp securely, see docs/security.md.