mcp-builder
Analysis
This is an instruction-only MCP server building guide with no executable code, install step, or required credentials; the only notable points are its use of external documentation fetches and references to local guide files not included in the manifest.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Use WebFetch to load: `https://modelcontextprotocol.io/llms-full.txt`
The guide relies on live external documentation and also asks for SDK README files from GitHub. This is expected for an MCP-building guide, but external content becomes part of the implementation context.
[📋 View Best Practices](./reference/mcp_best_practices.md) ... [🐍 Python Implementation Guide](./reference/python_mcp_server.md) ... [⚡ TypeScript Implementation Guide](./reference/node_mcp_server.md)
SKILL.md references local reference files, while the provided file manifest lists only SKILL.md. This indicates missing supporting documentation in the reviewed artifact set.