MCP server builder
Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers.
How to use it
Claude Code
- Run the line below. It pulls the whole folder into
~/.claude/skills/mcp-server-builder, including the files SKILL.md points to. - Describe your job in plain words. Claude Code follows the skill from there.
npx degit alirezarezvani/claude-skills/engineering/skills/mcp-server-builder#main ~/.claude/skills/mcp-server-builderFor one project only, change the path to .claude/skills/mcp-server-builder. This skill also uses openapi.json — copying SKILL.md alone won't be enough. See the folder on GitHub.
Claude (web or desktop app)
- On this page open ⋯ → Download .md.
- Save it as SKILL.md in a folder, zip the folder, then Customize → Skills → + → Create skill → Upload a skill.
- Pick the file and Save. Claude shows the name and description and runs a security scan.
- Check the skill is switched on.
- Start a new chat and describe your job in plain words. The AI follows the skill from there.
ChatGPT or another app
- ChatGPT: make a Project and paste it into Instructions.
- Neither? Paste it at the top of a new chat — it works for that chat.
Not working?
- Check which app you pasted it into — the steps above name the right one.
- Some skills need the paid tier of Claude or ChatGPT.
Paste into Claude, ChatGPT or Cursor.
Source of MCP server builder
Show the full text101 lines
| name | description |
|---|---|
| mcp-server-builder | Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript support, schema validation, safe evolution. Use when exposing an existing API as an MCP server, building tool integrations for Claude or Codex or Cursor, or scaffolding an MCP project from scratch. |
MCP Server Builder
Tier: POWERFUL · Category: Engineering · Domain: AI / API Integration
Overview
Use this skill to design and ship production-ready MCP servers from API contracts instead of hand-written one-off tool wrappers. It focuses on fast scaffolding, schema quality, validation, and safe evolution.
The workflow supports both Python and TypeScript MCP implementations and treats OpenAPI as the source of truth.
Core Capabilities
- Convert OpenAPI paths/operations into MCP tool definitions
- Generate starter server scaffolds (Python or TypeScript)
- Enforce naming, descriptions, and schema consistency
- Validate MCP tool manifests for common production failures
- Apply versioning and backward-compatibility checks
- Separate transport/runtime decisions from tool contract design
When to Use
- You need to expose an internal/external REST API to an LLM agent
- You are replacing brittle browser automation with typed tools
- You want one MCP server shared across teams and assistants
- You need repeatable quality checks before publishing MCP tools
- You want to bootstrap an MCP server from existing OpenAPI specs
Key Workflows
1. OpenAPI to MCP Scaffold
- Start from a valid OpenAPI spec.
- Generate tool manifest + starter server code.
- Review naming and auth strategy.
- Add endpoint-specific runtime logic.
python3 scripts/openapi_to_mcp.py \
--input openapi.json \
--server-name billing-mcp \
--language python \
--output-dir ./out \
--format text
Supports stdin as well:
cat openapi.json | python3 scripts/openapi_to_mcp.py --server-name billing-mcp --language typescript
2. Validate MCP Tool Definitions
Run validator before integration tests:
python3 scripts/mcp_validator.py --input out/tool_manifest.json --strict --format text
Checks include duplicate names, invalid schema shape, missing descriptions, empty required fields, and naming hygiene.
3. Runtime Selection
- Choose Python for fast iteration and data-heavy backends.
- Choose TypeScript for unified JS stacks and tighter frontend/backend contract reuse.
- Keep tool contracts stable even if transport/runtime changes.
4. Harden for Production
Key items before publishing:
- Keep secrets in env vars, not tool schemas
- Prefer outbound host allowlists over open proxies
- Use additive-only changes; never rename tool names in-place
Full hardening guidance: references/production-hardening-guide.md.
Script Interfaces
python3 scripts/openapi_to_mcp.py --help- Reads OpenAPI from stdin or
--input - Produces manifest + server scaffold
- Emits JSON summary or text report
- Reads OpenAPI from stdin or
python3 scripts/mcp_validator.py --help- Validates manifests and optional runtime config
- Returns non-zero exit in strict mode when errors exist
Reference Material
- references/production-hardening-guide.md — auth & safety design, versioning strategy, common pitfalls, best practices, architecture decisions, contract quality gates, testing strategy, deployment practices, security controls
- references/openapi-extraction-guide.md
- references/python-server-template.md
- references/typescript-server-template.md
- references/validation-checklist.md
- README.md
| 1 | |
| 2 | name "mcp-server-builder" |
| 3 | description "Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers. Python and TypeScript support, schema validation, safe evolution. Use when exposing an existing API as an MCP server, building tool integrations for Claude or Codex or Cursor, or scaffolding an MCP project from scratch." |
| 4 | |
| 5 | |
| 6 | # MCP Server Builder |
| 7 | |
| 8 | **Tier:** POWERFUL · **Category:** Engineering · **Domain:** AI / API Integration |
| 9 | |
| 10 | ## Overview |
| 11 | |
| 12 | Use this skill to design and ship production-ready MCP servers from API contracts instead of hand-written one-off tool wrappers. It focuses on fast scaffolding, schema quality, validation, and safe evolution. |
| 13 | |
| 14 | The workflow supports both Python and TypeScript MCP implementations and treats OpenAPI as the source of truth. |
| 15 | |
| 16 | ## Core Capabilities |
| 17 | |
| 18 | Convert OpenAPI paths/operations into MCP tool definitions |
| 19 | Generate starter server scaffolds (Python or TypeScript) |
| 20 | Enforce naming, descriptions, and schema consistency |
| 21 | Validate MCP tool manifests for common production failures |
| 22 | Apply versioning and backward-compatibility checks |
| 23 | Separate transport/runtime decisions from tool contract design |
| 24 | |
| 25 | ## When to Use |
| 26 | |
| 27 | You need to expose an internal/external REST API to an LLM agent |
| 28 | You are replacing brittle browser automation with typed tools |
| 29 | You want one MCP server shared across teams and assistants |
| 30 | You need repeatable quality checks before publishing MCP tools |
| 31 | You want to bootstrap an MCP server from existing OpenAPI specs |
| 32 | |
| 33 | ## Key Workflows |
| 34 | |
| 35 | ### 1. OpenAPI to MCP Scaffold |
| 36 | |
| 37 | Start from a valid OpenAPI spec. |
| 38 | Generate tool manifest + starter server code. |
| 39 | Review naming and auth strategy. |
| 40 | Add endpoint-specific runtime logic. |
| 41 | |
| 42 | |
| 43 | python3 scripts/openapi_to_mcp.py \ |
| 44 | --input openapi.json \ |
| 45 | --server-name billing-mcp \ |
| 46 | --language python \ |
| 47 | --output-dir ./out \ |
| 48 | --format text |
| 49 | |
| 50 | |
| 51 | Supports stdin as well: |
| 52 | |
| 53 | |
| 54 | cat openapi.json | python3 scripts/openapi_to_mcp.py --server-name billing-mcp --language typescript |
| 55 | |
| 56 | |
| 57 | ### 2. Validate MCP Tool Definitions |
| 58 | |
| 59 | Run validator before integration tests: |
| 60 | |
| 61 | |
| 62 | python3 scripts/mcp_validator.py --input out/tool_manifest.json --strict --format text |
| 63 | |
| 64 | |
| 65 | Checks include duplicate names, invalid schema shape, missing descriptions, empty required fields, and naming hygiene. |
| 66 | |
| 67 | ### 3. Runtime Selection |
| 68 | |
| 69 | Choose **Python** for fast iteration and data-heavy backends. |
| 70 | Choose **TypeScript** for unified JS stacks and tighter frontend/backend contract reuse. |
| 71 | Keep tool contracts stable even if transport/runtime changes. |
| 72 | |
| 73 | ### 4. Harden for Production |
| 74 | |
| 75 | Key items before publishing: |
| 76 | |
| 77 | Keep secrets in env vars, not tool schemas |
| 78 | Prefer outbound host allowlists over open proxies |
| 79 | Use additive-only changes; never rename tool names in-place |
| 80 | |
| 81 | Full hardening guidance: [references/production-hardening-guide.md]. |
| 82 | |
| 83 | ## Script Interfaces |
| 84 | |
| 85 | `python3 scripts/openapi_to_mcp.py --help` |
| 86 | Reads OpenAPI from stdin or `--input` |
| 87 | Produces manifest + server scaffold |
| 88 | Emits JSON summary or text report |
| 89 | `python3 scripts/mcp_validator.py --help` |
| 90 | Validates manifests and optional runtime config |
| 91 | Returns non-zero exit in strict mode when errors exist |
| 92 | |
| 93 | ## Reference Material |
| 94 | |
| 95 | [references/production-hardening-guide.md] — auth & safety design, versioning strategy, common pitfalls, best practices, architecture decisions, contract quality gates, testing strategy, deployment practices, security controls |
| 96 | [references/openapi-extraction-guide.md] |
| 97 | [references/python-server-template.md] |
| 98 | [references/typescript-server-template.md] |
| 99 | [references/validation-checklist.md] |
| 100 | [README.md] |
| 101 |
Discussion
Browse more free Claude skills or everything in Development.