Chatgpt-skills mcp-builder
Plan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.
install
source · Clone the upstream repo
git clone https://github.com/dkyazzentwatwa/chatgpt-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/dkyazzentwatwa/chatgpt-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/mcp-builder" ~/.claude/skills/dkyazzentwatwa-chatgpt-skills-mcp-builder && rm -rf "$T"
manifest:
mcp-builder/SKILL.mdsource content
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
for design principles that apply to every server.references/mcp_best_practices.md
for Python implementation patterns.references/python_mcp_server.md
for TypeScript implementation patterns.references/node_mcp_server.md
andscripts/connections.py
as repo-local helpers.scripts/evaluation.py
Deliverables
- A concrete tool inventory tied to user workflows.
- Strict input/output schemas.
- Evaluation prompts or scripts that confirm the server is usable by an agent.