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 ...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.
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.