# Mcp Server Design

> Design FastMCP 3 tools, providers, transforms, authorization, background work, output contracts, and human approval boundaries for a production server.

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

## Install

```sh
agentstack add skill-batteryshark-skill-tap-mcp-server-design
```

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

## About

# Design a FastMCP Server

1. Inventory users, component count, data sources, trust boundaries, latency, long-running work, and irreversible or external effects.
2. Run `bin/mcp-server-design PATH` to inventory existing FastMCP concerns and read [references/architecture-decisions.md](references/architecture-decisions.md).
3. Keep domain logic library-first. Use providers to source components, transforms to shape the exposed catalog, and middleware for request execution concerns.
4. Prefer ordinary directly exposed tools for a small catalog. Use Tool Search for on-demand discovery, and experimental Code Mode only when server-side Python composition justifies its sandbox and extra dependency.
5. Make output match consumers: typed structured data for programmatic composition, concise content for model reading, and Apps when an interactive UI materially helps. Do not impose a universal text-only rule.
6. Put authorization and visibility on components, authenticate HTTP deployments, keep secrets server-side, and require preview/approval for irreversible, financial, external-communication, permission, or sensitive-data actions.
7. Use task support for genuinely long-running work and explicit timeouts for bounded calls. Keep interactive OAuth and unreliable network work out of startup.
8. Verify schemas, catalog exposure, permissions, output shape, task behavior, and side-effect gates.

Use [agents/architecture-reviewer.md](agents/architecture-reviewer.md) for a threat- and token-budget-aware review.

## Source & license

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

- **Author:** [batteryshark](https://github.com/batteryshark)
- **Source:** [batteryshark/skill-tap](https://github.com/batteryshark/skill-tap)
- **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-batteryshark-skill-tap-mcp-server-design
- Seller: https://agentstack.voostack.com/s/batteryshark
- 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%.