agentleFS
darkweb19darkweb19/skills/mcp-server-builder/SKILL.md

mcp-server-builder

Skill0 starsChanged 31 days agoApache-2.0View on GitHub

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.

17 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to design and ship production-ready MCP servers from API contracts instead of hand-written one-off tool wrappers.

    line 12
  2. Distinctive:

    Start from a valid OpenAPI spec.

    line 37
  3. Distinctive:

    Add endpoint-specific runtime logic.

    line 40
  4. Distinctive:

    Run validator before integration tests:

    line 59
  5. Distinctive:

    Keep tool contracts stable even if transport/runtime changes.

    line 71
  6. Distinctive:

    Keep secrets in env vars, not tool schemas

    line 77
  7. Distinctive:

    Prefer outbound host allowlists over open proxies

    line 78
  8. Distinctive:

    Use additive-only changes.

    line 79

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Start from a valid OpenAPI spec.
  2. Generate tool manifest + starter server code.
  3. Review naming and auth strategy.
  4. 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
  • 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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.