Mcp Builder test

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

This package contains helpful MCP server docs but also runnable evaluation scripts that will call an external LLM (Anthropic) and require Python MCP client libraries. Before installing or running: 1) Review scripts/evaluation.py and scripts/connections.py to understand what data will be sent to external services — the evaluation deliberately forwards tool inputs/outputs to Anthropic, so any data returned by your MCP server may be transmitted off-host. 2) Install dependencies in a controlled environment (the repo includes scripts/requirements.txt but no install spec). 3) Expect to provide an Anthropic API key (e.g., ANTHROPIC_API_KEY) and possibly other credentials when running evaluations — these are not declared in the skill metadata. 4) If you plan to evaluate sensitive systems, run the harness in an isolated environment or modify it to use a local LLM / disable external calls. 5) If you want to proceed, add explicit install and environment variable documentation (or patch the SKILL.md) and audit the code for any endpoints/telemetry you don't want to expose.

Type: OpenClaw Skill Name: unique-mcp-builder-test Version: 0.1.0 The skill bundle is classified as suspicious due to significant Remote Code Execution (RCE) and Server-Side Request Forgery (SSRF) vulnerabilities present in `scripts/evaluation.py` and `scripts/connections.py`. The `evaluation.py` script is designed to execute arbitrary commands and make network requests to user-specified targets (via command-line arguments like `--command` and `--url`) for evaluating MCP servers. While this functionality is intended for evaluation, it poses a critical risk if the script is run with untrusted inputs. Additionally, `SKILL.md` instructs the AI agent to use `WebFetch` to load documentation from `raw.githubusercontent.com` and generally use 'web search and WebFetch as needed,' introducing a supply chain risk. There is no clear evidence of intentional malicious behavior within the skill bundle itself, such as data exfiltration or backdoor installation.