xiaohongshu-mcp vs ha-mcp

Two of the top projects in MCP servers, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.

33rd of 12 in MCP servers

xiaohongshu-mcp

MCP server that lets AI clients post, search and comment on Xiaohongshu

#44th of 12 in MCP servers

ha-mcp

MCP server that lets AI assistants configure and control Home Assistant

Verdict

xiaohongshu-mcp ranks higher, 85 to 80. Of the 4 score parts we measure for both, xiaohongshu-mcp leads on 1, ha-mcp on 2 and 1 is even.

  • Adoptionxiaohongshu-mcp leads by 38 points, 79 to 41: a wide gap.
  • FreshnessEven at 100.
  • Maintenanceha-mcp leads by 16 points, 99 to 83: a wide gap.
  • Agent-readyha-mcp leads by 15 points, 85 to 70: a wide gap.

Pick xiaohongshu-mcp if you are

Developers connecting an AI assistant to Xiaohongshu for posting and research

  • Covers publishing, search, comments, likes, favorites and profiles as MCP tools
  • Prebuilt binaries for macOS arm64, Windows x64 and Linux x64, plus Docker images

Pick ha-mcp if you are

Home Assistant users who want MCP clients to manage their smart home

  • 87 tools covering automations, dashboards, helpers, areas, backups, traces and device registry
  • In-process integration works on OS, Supervised, Container and Core installs
xiaohongshu-mcp vs ha-mcp: score parts and facts
What we comparexiaohongshu-mcpha-mcp
Score parts, out of 100
Adoption79, popular41, known
MomentumNot scored for this kindNot scored for this kind
Freshness100, active100, active
Maintenance83, healthy99, healthy
Agent-ready70, partly85, ready
Facts from GitHub and the README
Stars17.1k7.1k
LicenseApache-2.0 (permissive)MIT (permissive)
Last commitNov 2026Nov 2026
Last releaseNov 2026Nov 2026
LanguageGoPython
DockerYesYes
GPUNot neededNot needed
arm64 or Apple SiliconMentionedMentioned

xiaohongshu-mcp

A Go MCP server that drives a headless browser to operate a logged-in Xiaohongshu account. It exposes 13 tools over streamable HTTP at /mcp: publish image or video posts (with tags, scheduling, visibility), search with filters, read feeds, post details and comments, reply, like, favorite and fetch user profiles. Works with Claude Code, Cursor, VS Code, Gemini CLI and Cline.

Who it is for: Developers connecting an AI assistant to Xiaohongshu for posting and research

Strengths

  • Covers publishing, search, comments, likes, favorites and profiles as MCP tools
  • Prebuilt binaries for macOS arm64, Windows x64 and Linux x64, plus Docker images
  • Optional Bearer token auth via AUTH_TOKEN and optional proxy via XHS_PROXY
  • README gives config snippets for Claude Code, Cursor, VS Code, Gemini CLI and Cline

Weaknesses

  • Automates the web UI, so site changes or risk controls can break posting
  • One account cannot stay logged in on other web clients without kicking the MCP session
  • No prebuilt binary for macOS Intel or Linux ARM64
  • Auth is off by default; the noVNC GUI image has no password and must not be public
  • no GPU
  • Docker + Compose
  • Needs Headless browser (about 150MB, auto-downloaded on first run), Xiaohongshu account
  • port 18060

ha-mcp

ha-mcp exposes 87 tools over the Model Context Protocol so clients such as Claude, ChatGPT and Cursor can search entities, control devices, and create or edit automations, scripts, helpers and dashboards in Home Assistant. It is built on FastMCP and installs as an in-process HACS/Marketplace integration, a Home Assistant app (add-on), Docker, or uvx/PyPI. Safety features include read-only mode, per-tool disabling and automatic edit backups.

Who it is for: Home Assistant users who want MCP clients to manage their smart home

Strengths

  • 87 tools covering automations, dashboards, helpers, areas, backups, traces and device registry
  • In-process integration works on OS, Supervised, Container and Core installs
  • Read Only Mode, per-tool enable/disable and automatic backups before edits
  • Setup Wizard generates config for 15+ clients; demo server available to try first

Weaknesses

  • Integration requires Home Assistant 2026.8.0 or newer
  • Acts with an administrator token; a leaked token or secret URL grants broad access
  • stdio transport has known connection problems; README recommends it only for demos
  • Several install paths exist; running more than one per client causes connection hangs
  • no GPU
  • Docker + Compose
  • Needs Home Assistant 2026.8.0+, Home Assistant administrator access token, FastMCP
  • Models: Claude, ChatGPT, Gemini CLI, Open WebUI, Cursor
  • port 9584

More in MCP servers

Building with these?

We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.