Design and validate MCP server tools when standard integrations need schemas, safe auth, resources, prompts, and Inspector-ready verification.
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./Skills/backend-platform/mcp-builder/SKILL.mdFor Cookbook-derived MCP, Responses API, and tool-orchestration checks, use Infrastructure/references/openai-cookbook-expert-lens-pack.md and Infrastructure/references/openai-cookbook-skill-expertise-map.md.
Start here for routing, safety, workflow, and validation.
Read when: MCP work needs integration-pattern, data-reliability, schema, idempotency, or auth-boundary lenses: Infrastructure/references/software-literature-expert-lens-pack.md and the MCP Builder row in Infrastructure/references/software-literature-skill-expertise-map.md.
Read when: MCP work needs Cookbook-derived tool orchestration, structured-output, or secure-quality-gate checks: Infrastructure/references/openai-cookbook-expert-lens-pack.md and Infrastructure/references/openai-cookbook-skill-expertise-map.md.
Use Infrastructure/references/software-literature-expert-lens-pack.md and Infrastructure/references/software-literature-skill-expertise-map.md for integration-boundary and protocol contract lenses.
Use references/contract.yaml for the machine-readable contract.
Use references/evals.yaml for benchmark and quality gates.
Use references/task-profile.json for evaluator thresholds.
Use Infrastructure/references/deferred-skill-context/backend-platform-mcp-builder/ for legacy examples, scripts, assets, or long-form details.
jscraik/Agent-Skills
2920192
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.