MCP Tool Surface Design Prompt
Turns an app description into a minimal, safe MCP tool and resource surface.
/ quick answer
Run before writing a single line of MCP server code. Turns an app description into a minimal, safe MCP tool and resource surface.
You are an MCP server architect. Given the application below, design the smallest useful capability surface.
Return:
1. TOOLS — table: name, one-line description, input schema fields, read/write, destructive?, approval required?
2. RESOURCES — URI pattern, what it returns, when the agent should pull it.
3. EXCLUDED — capabilities you deliberately left out, and why.
4. SECURITY — authorisation checks each tool must perform server-side, injection risks, output redaction rules.
5. NAMING REVIEW — flag any name a model could confuse with another.
Rules: no generic query/exec/http tools. Max 8 tools. Every write tool needs an approval rule.
Application: {{APP}}
Users and roles: {{ROLES}}
Systems it touches: {{SYSTEMS}}1. TOOLS — search_orders | find orders for a customer | {email, status} | read | no | no .../ frequently asked
What does the MCP Tool Surface Design Prompt prompt do?
Run before writing a single line of MCP server code.
Which AI models work with this prompt?
It is model-agnostic: it works with any capable general model. Replace the bracketed variables with your own context before running it.
How do I use this prompt?
1) Copy the prompt with the copy button. 2) Replace every bracketed variable with your real details. 3) Paste it into your AI assistant. 4) Compare the answer with the example output and ask for changes if needed.
What output should I expect?
1. TOOLS — search_orders | find orders for a customer | {email, status} | read | no | no ...
/ continue exploring
Related concepts
The vocabulary this page depends on.
- →MCP Server
An MCP server exposes tools, resources and prompts from one system so any MCP-compatible AI client can use them over a standard protocol.
- →MCP Client
An MCP client is the AI-side host that discovers servers, lists their tools and routes the model's calls to them.
- →MCP Tools
MCP tools are typed, described functions an AI model can call — the unit of capability that decides whether an agent is useful or dangerous.
- →MCP Transport (stdio vs Streamable HTTP)
MCP runs either as a local stdio process or as a remote streamable HTTP endpoint — the choice decides auth, deployment and who can reach it.
Related workflows
Turn this into a repeatable process.
- →Build an MCP Server for Your Own App
Expose your product's capabilities to every AI client with one server.
- →Audit MCP Tool Security
A checklist that catches the failure modes unique to model-driven tool calls.
Related tool stacks
The tools that run it in production.
- →MCP Integration Stack
Build, deploy and secure MCP servers that real AI clients can use.
Related prompts
Reusable prompts for this job.
- →MCP Tool Designer Prompt
Turn a plain-English capability list into a clean MCP tool schema.
- →Prompt Improver Prompt
Iterate a weak prompt into a strong one using best practices.
- →Strategic Analyst Prompt
Turn a business situation into a McKinsey-style strategic memo.
- →Buyer Persona Builder Prompt
Generate a detailed persona from a product description and target market.
Related use cases
How people apply it, and what came out.
- →Sales Team Queries the CRM from Claude via MCP
One MCP server replaced three brittle chatbot integrations.
Comparisons & alternatives
Pick between the options.
- →MCP vs Native Function Calling
Function calling is per-app plumbing; MCP is a portable protocol so one integration serves every client.