← Back to Skills Marketplace
146
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install xiaozhi-mcp-openclaw-official
Description
按小智官方 MCP 接入方式，把小智 AI 设备通过 MCP 接到 OpenClaw / OpenAI-compatible 后端。适用于已经有小智 MCP 接入点（wss://api.xiaozhi.me/mcp/?token=...）的场景。提供一个 `openclaw_query(message)` MCP...
Usage Guidance
This package is a small bridge that will forward MCP messages to a model backend and return replies. Before installing: (1) Understand that you must provide MCP_ENDPOINT and OPENAI_KEY (these are secrets); the registry metadata incorrectly omits them — treat that as a red flag. (2) Change OPENAI_BASE from the code's default (https://openclaw.994938.xyz/v1) to a backend you trust; leaving the default will send your API key and queries to that third-party host. (3) Treat MCP_ENDPOINT carefully — it likely contains a token in the URL; don't share .env files. (4) Review .env.example and the code locally to confirm behavior and remove any default endpoints you don't trust. (5) Consider running the bridge in a restricted environment/network and monitoring outgoing connections. If you cannot verify the maintainer or the default backend domain, avoid installing or use only with dummy credentials and behind network controls.
Capability Analysis
Type: OpenClaw Skill
Name: xiaozhi-mcp-openclaw-official
Version: 1.0.2
The bundle implements a bridge (mcp_pipe.py) that connects a remote WebSocket endpoint (MCP_ENDPOINT) to a local MCP server process, piping stdin/stdout/stderr between them. This architecture allows a remote service (XiaoZhi AI) to drive local tool execution, which is functionally similar to a reverse shell and grants the remote endpoint control over local process communication. While this aligns with the stated purpose of hardware integration, the use of a remote-to-local pipe and a hardcoded third-party backend (https://openclaw.994938.xyz/v1 in openclaw_mcp.py) represents a significant security risk.
Capability Assessment
Purpose & Capability
The repository and SKILL.md claim to bridge a XiaoZhi MCP endpoint to an OpenAI/OpenClaw-compatible backend; the two Python files implement that bridge (websocket -> subprocess -> HTTP requests to a model backend). This is coherent with the stated purpose. However, the registry metadata lists 'required env vars: none' while the SKILL.md and code clearly require MCP_ENDPOINT, OPENAI_BASE, OPENAI_KEY and MODEL — a mismatch that may mislead users about what secrets are needed.
Instruction Scope
Runtime instructions limit behavior to connecting to a provided MCP websocket, launching the mcp script, and forwarding queries to a model backend. The code does not attempt to read unrelated system files or credentials. Two points to note: (1) exception/error text from backend calls is included in user-facing replies which could leak internal errors; (2) mcp_pipe.py spawns a subprocess and proxies raw messages between websocket and the MCP script — this is expected for this bridge but grants the script full ability to send/receive MCP messages.
Install Mechanism
No install script downloads arbitrary code; the package is instruction-only with a requirements.txt. Installation is via pip install -r requirements.txt (standard). There are no remote archive downloads or obscure install URLs.
Credentials
The code needs sensitive environment values (MCP_ENDPOINT which typically embeds a token, OPENAI_KEY) — these are appropriate for a bridge but the registry metadata fails to declare them. More importantly, OPENAI_BASE defaults to 'https://openclaw.994938.xyz/v1' in code: a third-party domain is embedded as a default backend without explanation. If a user leaves defaults unchanged, their API key and all forwarded messages could be sent to that external service. This default backend choice is unexpected and increases risk.
Persistence & Privilege
The skill is not marked always:true and does not request persistent platform privileges. It doesn't attempt to modify other skills or system-wide agent settings. It runs as a transient bridge process.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xiaozhi-mcp-openclaw-official - After installation, invoke the skill by name or use
/xiaozhi-mcp-openclaw-official - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Rename skill display name to 小智AI-Xiaozhi Mcp Openclaw Official.
v1.0.1
Add bilingual Chinese/English README and SKILL documentation.
v1.0.0
Initial release: official XiaoZhi MCP bridge for OpenClaw/OpenAI-compatible backends, with openclaw_query tool and minimal deployment instructions.
Metadata
Frequently Asked Questions
What is Xiaozhi Mcp Openclaw Official?
按小智官方 MCP 接入方式，把小智 AI 设备通过 MCP 接到 OpenClaw / OpenAI-compatible 后端。适用于已经有小智 MCP 接入点（wss://api.xiaozhi.me/mcp/?token=...）的场景。提供一个 `openclaw_query(message)` MCP... It is an AI Agent Skill for Claude Code / OpenClaw, with 146 downloads so far.
How do I install Xiaozhi Mcp Openclaw Official?
Run "/install xiaozhi-mcp-openclaw-official" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Xiaozhi Mcp Openclaw Official free?
Yes, Xiaozhi Mcp Openclaw Official is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Xiaozhi Mcp Openclaw Official support?
Xiaozhi Mcp Openclaw Official is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Xiaozhi Mcp Openclaw Official?
It is built and maintained by joe12801 (@joe12801); the current version is v1.0.2.
More Skills