← Back to Skills Marketplace
Mcp Integration
by
lunarpulse
· GitHub ↗
· v0.1.1
9084
Downloads
18
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install openclaw-mcp-plugin
Description
Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.).
Usage Guidance
Install only for trusted/admin agents and only with MCP servers you control or explicitly trust. Prefer read-only or least-privilege credentials, restrict which agents can use the mcp tool, require confirmation for database writes or sensitive data access, and review/redact diagnostic reports before sharing them publicly or with support.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-mcp-plugin
Version: 0.1.1
The OpenClaw MCP Integration plugin is designed to connect to external Model Context Protocol (MCP) servers and expose their tools to AI agents. The code (src/index.js, src/http-transport.js) implements the client-side logic for this, making network requests to configurable URLs. All documentation (SKILL.md, README.md, etc.) provides instructions for using the plugin and contains no evidence of prompt injection attempts, data exfiltration, or other malicious instructions directed at the AI agent. While connecting to external services inherently carries risks if those services are untrusted, the plugin itself does not exhibit intentional harmful behavior. The configuration schema (config/openclaw.plugin.json) mentions a 'stdio' transport with 'command' and 'env' fields, which would be a high-risk capability, but the current implementation (src/index.js) only supports 'http' transport, rendering these fields inert.
Capability Assessment
Credentials
Network access to arbitrary configured MCP URLs is central to the skill, but the examples include database queries and cross-service workflows that may expose customer, business, or operational data unless the deployment is tightly scoped.
Install Mechanism
Installation is a normal OpenClaw extension plus npm dependencies, and package.json contains no install script or unexpected lifecycle hook; users should still review the external package dependencies and the repository source they clone.
Instruction Scope
SKILL.md tells agents to always list available tools and to chain calls, while the runtime returns external tool descriptions, schemas, and results as ordinary text; the guidance mentions trusted servers and confirmations but does not enforce per-server or per-tool allowlists, provenance labeling, or confirmation for sensitive calls.
Persistence & Privilege
The plugin persists as an OpenClaw extension and starts with the OpenClaw service, connecting to configured servers at startup; no code-level root escalation, scheduled task, backdoor, or destructive persistence was found, and sudo appears only in optional firewall troubleshooting documentation.
Purpose & Capability
The artifacts consistently describe and implement a generic MCP bridge that lists and calls tools from configured servers, including database and API connectors; this is purpose-aligned but high-impact because one exposed tool can route arbitrary agent-supplied arguments to sensitive external systems.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-mcp-plugin - After installation, invoke the skill by name or use
/openclaw-mcp-plugin - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.1
Initial release of openclaw-mcp-plugin.
- Adds core plugin implementation with unified `mcp` tool and `list`/`call` actions.
- Provides example configuration and transport modules.
- Includes usage guide and integration documentation.
- Supports discovery and invocation of tools from configured MCP servers.
v0.1.0
Initial release of the mcp-integration skill for Model Context Protocol (MCP):
- Enables AI agents to discover and execute external tools from MCP servers (legal databases, APIs, database connectors, weather services, etc.).
- Provides a unified `mcp` tool with `list` (tool discovery) and `call` (tool execution) actions.
- Details multi-step workflows for chaining tool calls and maintaining context between steps.
- Includes guidance for error handling, parameter validation, and response parsing.
- Comprehensive usage guide, reference documentation, and real-world example links included.
Metadata
Frequently Asked Questions
What is Mcp Integration?
Use Model Context Protocol servers to access external tools and data sources. Enable AI agents to discover and execute tools from configured MCP servers (legal databases, APIs, database connectors, weather services, etc.). It is an AI Agent Skill for Claude Code / OpenClaw, with 9084 downloads so far.
How do I install Mcp Integration?
Run "/install openclaw-mcp-plugin" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Mcp Integration free?
Yes, Mcp Integration is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Mcp Integration support?
Mcp Integration is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Mcp Integration?
It is built and maintained by lunarpulse (@lunarpulse); the current version is v0.1.1.
More Skills