# Superlazy Mcp

> Build MCP servers with minimal tokens. Use when creating or modifying an MCP (Model Context Protocol) server integrating any external API or service, in TypeScript or Python.

- **Type:** Skill
- **Install:** `agentstack add skill-starchybomb-superlazy-superlazy-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [StarchyBomb](https://agentstack.voostack.com/s/starchybomb)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** https://github.com/StarchyBomb/superlazy/tree/main/skills/superlazy-mcp

## Install

```sh
agentstack add skill-starchybomb-superlazy-superlazy-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Superlazy MCP Builder

SUPERLAZY mode: output ≤3 lines (questions / user-actions / ✅❌); minimal code, full quality; do the work, never narrate it.

## Defaults (proceed silently)
- TypeScript + official `@modelcontextprotocol/sdk` (Python + FastMCP only if the project is already Python).
- Transport: stdio for local; streamable HTTP with stateless JSON for remote.
- Docs beat memory: fetch `https://modelcontextprotocol.io/sitemap.xml`, then needed pages with `.md` suffix; SDK README from its GitHub raw. Do this before writing code, silently.

## Tool design rules
- Comprehensive API coverage first; workflow-convenience tools only when the API composition is genuinely painful.
- Names: `service_verb_noun` (`github_create_issue`). Action-oriented, consistent prefix.
- Schemas: Zod (TS) / Pydantic (Py), constraints + descriptions + examples on every field; `outputSchema`/`structuredContent` where supported.
- Every listing tool paginates and filters — tools return focused data, not dumps.
- Errors are actionable: what failed + what the agent should do next.
- Annotations on every tool: `readOnlyHint`, `destructiveHint`, `idempotentHint`, `openWorldHint`.
- Shared infra once: API client + auth, error helper, response formatter. DRY.

## Verify before ✅
TS: `npm run build` exit 0. Py: `python -m py_compile`. Then exercise the server (MCP Inspector or direct calls) — at least one real call per tool category. Evidence per superlazy-verify.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [StarchyBomb](https://github.com/StarchyBomb)
- **Source:** [StarchyBomb/superlazy](https://github.com/StarchyBomb/superlazy)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-starchybomb-superlazy-superlazy-mcp
- Seller: https://agentstack.voostack.com/s/starchybomb
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.