mcp-builder
Guide for building high-quality MCP servers in Python (FastMCP) or Node/TypeScript (MCP SDK).
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for mcp-builder, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official skill for creating Model Context Protocol servers that expose external APIs as well-designed agent tools. Covers a four-phase workflow (research, design, implement, evaluate) with guidance on tool naming, context management, actionable errors, and testing. Guides code generation for FastMCP/TypeScript MCP servers and their tool schemas.
Key features and capabilities
- Four-phase MCP server workflow
- Tool naming, pagination, and error-message best practices
- FastMCP (Python) and TypeScript MCP SDK support
Use cases
- Wrap a REST API as an MCP server
- Design agent-friendly tools for an external service