AI & Memory MCP Server

Ha MCP

Name: Ha MCP
Author: homeassistant-ai

Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.

Scan flagged something by homeassistant-ai1,225MITPythonIntermediatestdio

Install

Claude Code

claude mcp add ha-mcp -- uvx ha-mcp

Cursor

{
  "mcpServers": {
    "ha-mcp": {
      "command": "uvx",
      "args": [
        "ha-mcp"
      ]
    }
  }
}

VS Code

{
  "mcp": {
    "servers": {
      "ha-mcp": {
        "command": "uvx",
        "args": [
          "ha-mcp"
        ]
      }
    }
  }
}

Windsurf

{
  "mcpServers": {
    "ha-mcp": {
      "command": "uvx",
      "args": [
        "ha-mcp"
      ]
    }
  }
}

Claude Desktop

{
  "mcpServers": {
    "ha-mcp": {
      "command": "uvx",
      "args": [
        "ha-mcp"
      ]
    }
  }
}

Safety Report

38% Scan flagged something

Scanned 5 months ago

3 passed 5 warnings

Security

Authentication

details

Authentication detected: env_required, bearer_check, oauth

Pass

CORS Policy

details

Uses SSE/HTTP transport but no CORS configuration found

Warning

Rate Limiting

details

Rate limiting detected: rate_limit_middleware, throttle

Pass

Known CVEs

details

1 deps with known issues (medium)

Warning

Code Quality

Dependency Audit

details

1 deps with known issues (medium)

Warning

Dangerous Patterns

details

Dangerous patterns detected: eval_call

Warning

License

details

License: MIT

Pass

Community

Maintenance Status

details

Last commit 5 months ago

Warning

Learn about our security methodology →

Compatibility

Claude CodeFull support

Tested

CursorFull support

Tested

VS CodeFull support via Copilot

Tested

WindsurfFull support

Tested

Claude DesktopFull support

Tested

Frequently Asked Questions

What is Ha MCP?

Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.

Is Ha MCP safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Ha MCP and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. At least one matched — the specific finding is in the scan report on this page. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Ha MCP?

Similar MCP servers include Context7, Cognee, Hindsight. Each serves a similar purpose but may differ in features, language, and compatibility.