Build MCP servers end-to-end — scaffold a production-ready Python or TypeScript server from API docs, implement tools, validate the MCPB bundle, embed a skill resource, and release to the mpak registry. Covers the full lifecycle from API analysis to published bundle. Use when building a new MCP server, wrapping an API as MCP, or creating an integration. Triggers include "build an MCP server", "create a server for X", "/mcpb".
Build MCP servers end-to-end: scaffold from API docs, implement tools, validate the bundle, create an embedded skill resource, and release to the mpak registry. Supports Python (FastMCP) and TypeScript (@modelcontextprotocol/sdk).
Pipeline
Work through each phase in order. Read the linked workflow file for detailed instructions. Each phase has a gate that must pass before proceeding.
1---2name: mcpb3description: Build MCP servers end-to-end — scaffold a production-ready Python or TypeScript server from API docs, implement tools, validate the MCPB bundle, embed a skill resource, and release to the mpak registry. Covers the full lifecycle from API analysis to published bundle. Use when building a new MCP server, wrapping an API as MCP, or creating an integration. Triggers include "build an MCP server", "create a server for X", "/mcpb".4license: MIT5---67# Build MCPB89Build MCP servers end-to-end: scaffold from API docs, implement tools, validate the bundle, create an embedded skill resource, and release to the mpak registry. Supports Python (FastMCP) and TypeScript (@modelcontextprotocol/sdk).1011## Pipeline1213Work through each phase in order. Read the linked workflow file for detailed instructions. Each phase has a gate that must pass before proceeding.1415- [ ] **Phase 0 — Bootstrap:** Language, service name, repo creation, template setup. Read [references/workflow/phase-0-bootstrap.md](references/workflow/phase-0-bootstrap.md)16- [ ] **Phase 1 — API Analysis:** Fetch docs, identify resources, propose tools for approval. Read [references/workflow/phase-1-api-analysis.md](references/workflow/phase-1-api-analysis.md)17- [ ] **Phase 2 — Scaffold:** Verify project structure from template. Read [references/workflow/phase-2-scaffold.md](references/workflow/phase-2-scaffold.md)18- [ ] **Phase 3 — Implement & Verify:** Write tool logic, models, client; lint, typecheck, test. Read [references/workflow/phase-3-implement-and-verify.md](references/workflow/phase-3-implement-and-verify.md)19- [ ] **Phase 4 — Validate Bundle:** Manifest, build, bundle, MTF scan, runtime. Read [references/workflow/phase-4-validate-bundle.md](references/workflow/phase-4-validate-bundle.md)20- [ ] **Phase 5 — Embed Skill:** Create in-package skill resource, wire, verify. Read [references/workflow/phase-5-embed-skill.md](references/workflow/phase-5-embed-skill.md)21- [ ] **Phase 6 — Release:** Commit, push, cut release, verify publication. Read [references/workflow/phase-6-release.md](references/workflow/phase-6-release.md)2223## References2425Load the `{lang}`-appropriate file based on the language established in Phase 0c (`PY` for Python, `TS` for TypeScript).26- `references/CONVENTIONS-PY.md` / `CONVENTIONS-TS.md` — Naming, manifest, concept mapping, build system, entry points, template substitutions27- `references/PATTERNS-PY.md` / `PATTERNS-TS.md` — Implementation order, code patterns, directory structure, test patterns, CI workflows28- `references/SKILL_FORMAT-PY.md` / `SKILL_FORMAT-TS.md` — Embedded skill resource format, file location, wiring pattern
Run npx skillmds@latest add nimblebraininc/mcpb in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Build MCP servers end-to-end — scaffold a production-ready Python or TypeScript server from API docs, implement tools, validate the MCPB bundle, embed a skill resource, and release to the mpak registry. Covers the full lifecycle from API analysis to published bundle. Use when building a new MCP server, wrapping an API as MCP, or creating an integration. Triggers include "build an MCP server", "create a server for X", "/mcpb". It is listed under AI & ML on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.
NimbleBrainInc (@nimblebraininc) published this skill. Their other Agent Skills are listed on their SkillMD profile.
NimbleBrainInc