agentleFS
Sign inStart free
BAKUGOS1BAKUGOS1/SkilledAgents-Toolkit/skills/codex/mcp-builder/SKILL.md

mcp-builder

Skill0 starsChanged 5 months agoMITView on GitHub

MCP server design, implementation, and review workflow for Model Context Protocol integrations. Use when building or auditing MCP servers, tools, resources, prompts, connectors, external API integrations, tool schemas, authentication boundaries, error handling, pagination, or agent-facing workflow tools in Python, TypeScript, or another runtime.

186 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • ComposioHQSkill

    codebase-migrate

    Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.

    Also in 5 projects that use this

  • truongtv22Skill

    Problem-Solving Techniques

    Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.

    Also in 5 projects that use this

  • ArogyaReddySkill

    skill-share

    A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.

    Also in 26 projects that use this

  • AnthropicSkill

    academy-guide

    Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

    Also in 8 projects that use this

  • +2 more from Leodorareluctant259

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill to build MCP servers that are useful to agents in real workflows, not just thin API wrappers.

    line 10
  2. Distinctive:

    Verify current MCP docs before relying on protocol details, SDK APIs, or transport behavior.

    line 14
  3. Distinctive:

    Prefer clear, discoverable tool names with consistent prefixes.

    line 16
  4. Distinctive:

    Keep auth, secrets, destructive actions, and production writes behind explicit safeguards.

    line 19
  5. Distinctive:

    Add tests or smoke checks for connection, happy path, invalid input, auth failure, pagination, and rate-limit behavior.

    line 28
  6. Distinctive:

    Document setup, environment variables, and example prompts.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 170 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 Builder

Overview

Use this skill to build MCP servers that are useful to agents in real workflows, not just thin API wrappers. It is adapted from useful patterns in Anthropic's Apache-2.0 mcp-builder skill.

First Principles

  • Verify current MCP docs before relying on protocol details, SDK APIs, or transport behavior.
  • Design tools around tasks agents need to complete.
  • Prefer clear, discoverable tool names with consistent prefixes.
  • Return focused data with pagination/filtering instead of huge responses.
  • Make errors actionable: tell the agent what failed, why, and what to try next.
  • Keep auth, secrets, destructive actions, and production writes behind explicit safeguards.

Design Workflow

  1. Identify the external service, target users, and top workflows.
  2. List required read tools, write tools, resources, and prompts.
  3. Define tool schemas with strict inputs, clear descriptions, and safe defaults.
  4. Decide which operations need confirmation or dry-run behavior.
  5. Implement the smallest useful server using the project's existing runtime.
  6. Add tests or smoke checks for connection, happy path, invalid input, auth failure, pagination, and rate-limit behavior.
  7. Document setup, environment variables, and example prompts.

Tool Quality Checklist

  • Names are action-oriented and easy to search.
  • Descriptions explain when to use the tool and what it returns.
  • Inputs are typed, minimal, and validated.
  • Outputs are structured and not overlong.
  • Errors include next steps.
  • Secrets never appear in logs or responses.
  • Destructive tools require explicit confirmation.
  • The server can be run locally and verified with a simple client.

Final Handoff

Report tools/resources added, auth/env requirements, verification performed, remaining risks, and any MCP docs consulted.

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.

Check your setup, free