Mcp Builder

If you're building an MCP server and want to avoid the usual trap of wrapping every API endpoint into a thin tool, this walks you through a workflow-first approach. It pushes you to identify the actual tasks an agent needs to complete, design a minimal tool surface with high-signal outputs, and build shared infrastructure like auth and pagination before you write schemas. The emphasis on corrective error messages and evaluation scripts is smart. It includes best practices docs and Python/TypeScript implementation references. Useful if you're past hello world and want your server to actually work in production with real context limits.

skills.sh installs: 194
GitHub stars: 131
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add dkyazzentwatwa/chatgpt-skills --skill mcp-builder --agent claude-code

Installs into .claude/skills of the current project.

Files

MCP Builder

Build MCP servers around user workflows, not raw API endpoints.

Workflow

Read the target API docs and identify the workflows an agent must complete end to end.
Design a small tool surface with high-signal outputs, clear identifiers, and actionable errors.
Implement shared infrastructure first: auth, request helpers, pagination, truncation, and formatting.
Add tool schemas and docstrings that make correct usage obvious.
Evaluate the server with realistic tasks before expanding scope.

Principles

Prefer workflow tools over thin endpoint wrappers.
Return concise, high-signal responses by default.
Use human-readable identifiers whenever possible.
Make error messages corrective: tell the agent what to try next.
Design for limited context and large datasets.

Resources

references/mcp_best_practices.md for design principles that apply to every server.
references/python_mcp_server.md for Python implementation patterns.
references/node_mcp_server.md for TypeScript implementation patterns.
scripts/connections.py and scripts/evaluation.py as repo-local helpers.