Prompts

MCP Prompts

What Are MCP Prompts?

MCP prompts are reusable, parameterized prompt templates that AI assistants can discover and invoke. They provide structured guidance for common architecture analysis tasks.

Benefits:

Discoverability — Clients can list available prompts without hardcoding
Consistency — Standardized workflows across different AI assistants
Composability — Prompts can reference MCP tools and resources

Available Prompt

`architecture_review`

Purpose: Agent architecture review with a guided checklist — runs analysis and produces a structured report with scores, findings, and recommendations.

Parameters:

project_path (required) — Path to the project
focus_area (optional) — reliability, governance, safety, coordination, or all (default)

Workflow:

Run analyze_architecture({ project_path })
Interpret agent architecture metrics and findings (reliability, governance, safety, coordination)
Generate a report with:
- Executive summary (pass/fail, overall health score)
- Key findings (prioritized by severity)
- Actionable recommendations
- Trade-offs and next steps

Example invocation:

get_prompt({
  "name": "architecture_review",
  "arguments": {
    "project_path": ".",
    "focus_area": "safety"
  }
})

How to Use Prompts

Discover prompts:
```
list_prompts()
```

Fetch a prompt template:

get_prompt({
  "name": "architecture_review",
  "arguments": { "project_path": "." }
})

Execute the prompt: The server returns a structured prompt with embedded tool calls. The AI assistant executes it and formats results for the user.

Why MCP Prompts?

Prompts provide a higher-level abstraction than tools:

Feature	Tools	Prompts
Granularity	Low-level (run single analysis)	High-level (multi-step workflow)
Composition	Manual (AI chains tools)	Automatic (server defines workflow)
Consistency	Varies by AI	Standardized
Discoverability	AI must know about tools	AI discovers prompts

Use tools when: You need a single analysis (e.g. analyze_architecture)

Use prompts when: You need a guided, multi-step workflow (e.g. agent architecture review)

Tools — Low-level MCP tools
Workflows — Example tool compositions (manual)
Advanced — Custom tool composition patterns
CLI Comparison — CLI equivalents for workflows