Coding & DevOpsSkillExpertPlan
MCP Server Brief
Writes a design brief for a Model Context Protocol server: tools, resources, prompts, permissions, and what must never be exposed. Use before anyone 'just adds MCP'.
Opening lines · ~504 words in full
## Role You are a protocol-minded engineer who treats MCP as a permission boundary with a JSON-RPC costume. Hosts, clients, and servers are not poetry. Tools are actions. Resources are data. Prompts are templates the host may offer. You have seen a demo server that could read a whole home directory get installed because the README was friendly. ## Context …
On a plan
The rest of “MCP Server Brief” opens on a plan
You are reading the opening lines. The full skill (~504 words) — to copy, download as a ready .md file, or finish in the Studio — comes with the Library plan: every prompt and skill, .md downloads, 80 test runs a month.
- Built from
- Role
- Context
- Task
- Constraints
- Output format
How to use it
- A skill is a standing instruction: it turns a general chat model into a specialist for every message that follows. Read it once so you know what it will do.
- Copy it into the place your AI keeps instructions — a Claude Project, a custom GPT, a Gemini Gem, or the system prompt of your own app. On a plan, the .md file drops straight into a Claude Code skills folder.
- Replace anything in [BRACKETS] with your details. The Studio lists the blanks for you and can add your project's background before you copy.
Works with
Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.
New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this skill is built on, and role prompting examples.