test

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use whe...

This skill includes working code that will call an external LLM (Anthropic/Claude) and an evaluation harness that instructs the agent to print detailed summaries of tool inputs and outputs. Yet the skill metadata declares no required environment variables or API keys. Before installing or enabling this skill: - Treat it as suspicious until you confirm what credentials it needs. The evaluation script likely requires an Anthropic API key (or similar) to function; do not provide secret keys unless you audit the code and accept the risk. - Audit the scripts (evaluation.py and connections.py) yourself: look for where network calls are made and where data is logged or returned. The EVALUATION_PROMPT explicitly asks for tool inputs/outputs and summaries: that can expose secrets returned by tools. - If you plan to run evaluations, only run them against test/read-only environments containing non-sensitive data, and never point the harness at production systems or supply real account tokens. - Consider asking the skill author to: (1) declare required env vars (e.g., ANTHROPIC_API_KEY) in the metadata, (2) remove or make optional any prompts that require verbatim tool input/output logging, and (3) limit what is printed in reports to non-sensitive metadata. If you cannot verify these changes or audit the code yourself, avoid enabling the skill with real credentials or running it against live services.

Type: OpenClaw Skill Name: test-11 Version: 2.0.0 The skill bundle is a comprehensive toolkit for developing and evaluating Model Context Protocol (MCP) servers. It includes detailed markdown guides (SKILL.md and reference files) and Python scripts (scripts/connections.py, scripts/evaluation.py) for connecting to and testing MCP servers using the Anthropic API. The code utilizes the official 'mcp' and 'anthropic' libraries, following standard patterns for MCP client/server interaction. No malicious behavior, such as data exfiltration or unauthorized access, was detected. The capability to execute local commands via the stdio transport is a core feature of the protocol and is appropriately exposed through user-controlled CLI arguments in the evaluation script. The instructions provided to the AI agent are well-aligned with the stated purpose of building and testing high-quality integrations.