mcp-builder is agent-read markdown (skill) from lstr-1/skills: Use when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool discoverability/performance. Guides through research → implementation → test → eval phases with TypeScript-first guidance matching our stack. Trigger on phrases like "build an MCP server", "expose X as an MCP tool", "write MCP tools for Y", "integrate Z via MCP"..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# MCP Server Development
Adapted from [anthropics/skills/mcp-builder](https://github.com/anthropics/skills/tree/main/skills/mcp-builder). MCP-server quality is measured by how well it lets LLMs accomplish real-world tasks — not by endpoint count.
> **Compliance (DSGVO Art. 28 / EU AI Act Art. 5):** MCP-Tools, die Inhalte an entfernte Endpunkte
> übertragen, MÜSSEN eine Auftragsverarbeitungsvereinbarung (AVV) für diesen Endpunkt voraussetzen.
> Tool-Schemas MÜSSEN Secrets und personenbezogene Daten aus Argumenten ausschließen. Keine
> MCP-Tools, die natürliche Personen bewerten oder sensible Attribute inferieren. Siehe
> `references/compliance.md`.
## Stack default for our projects
- **Language:** TypeScript (matches our stack; static typing + Zod schemas + good LLM code-gen)
- **Transport:** `stdio` for local tools, **Streamable HTTP (stateless JSON)** for remote
- **SDK:** [`@modelcontextprotocol/sdk`](https://github.com/modelcontextprotocol/typescript-sdk)
- **Package manager:** pnpm (never npm/yarn in our repos)
## Phase 1 — Research & Plan
### 1.1 Design principles
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_hq2ga43emepnmkuk
GET https://markdownregistry.com/api/v1/resolve?ref=lstr-1/skills/mcp-builder
GET https://markdownregistry.com/api/v1/blob/63537e9e010bb5f5cf055c329f3ba9109d3dfd65acb1dbca206dd760b8840342
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
lstr-1/skills · create-skill/SKILL.md · Use when the user wants to create, design, or generate a new AI agent skill (SKILL.md) from a problem description. This…
lstr-1/skills · monitor-startup-dach/SKILL.md · Fetch the top-25 posts from r/StartupDACH/hot.json, classify each into six deterministic German intent clusters…
lstr-1/skills · nlm-meta-study/SKILL.md · Create scientific meta-studies on any topic using Gemini Notebook (NotebookLM). Invoke for systematic reviews…
lstr-1/skills · orchestrator/skills/architecture/SKILL.md · Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities…
lstr-1/skills · orchestrator/skills/autopilot/SKILL.md · Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan →…
lstr-1/skills · orchestrator/skills/bootstrap/SKILL.md · Use this skill when scaffolding the minimum repository structure required by orchestrator. Invoked automatically by the…
lstr-1/skills · orchestrator/skills/brainstorm/SKILL.md · Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue…
lstr-1/skills · orchestrator/skills/claude-md-drift-check/SKILL.md · Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository…
lstr-1/skills · orchestrator/skills/daily/SKILL.md · Use this skill when creating today's daily note in the Meta-Vault (03-daily/YYYY-MM-DD.md) with valid…
lstr-1/skills · orchestrator/skills/debug/SKILL.md · Use when encountering any bug, test failure, build break, or unexpected behavior — runs a 4-phase systematic debugging…
anthropics/skills · skills/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
thinkinaixyz/deepchat · resources/skills/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
davepoon/buildwithclaude · plugins/all-skills/skills/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
letta-ai/skills · tools/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
razshy/wiggle · mnt-skills/examples/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
naveedharri/benai-skills · plugins/all-skills/skills/mcp-builder/SKILL.md · Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external…
kanevry/session-orchestrator · .codex-plugin/skills/mcp-builder/SKILL.md · Use when creating a new MCP (Model Context Protocol) server, extending an existing one, or debugging tool…
