Combining Capabilities

The real power of MCP comes from combining tools, resources, and prompts into cohesive systems.

A Complete Example: Knowledge Base Server

Let's build a knowledge base server that combines all MCP capabilities:

from mcp.server import Server
from mcp.types import Tool, Resource, Prompt, TextContent

server = Server(name="knowledge-base")

# 1. RESOURCES: Expose documents
@server.list_resources()
async def list_resources():
    docs = await db.get_all_documents()
    return [
        Resource(
            uri=f"doc://{doc.id}",
            name=doc.title,
            description=f"Document: {doc.title}",
            mimeType="text/markdown"
        )
        for doc in docs
    ]

@server.read_resource()
async def read_resource(uri: str):
    doc_id = uri.replace("doc://", "")
    doc = await db.get_document(doc_id)
    return [TextContent(type="text", text=doc.content)]

# 2. TOOLS: Search and modify
@server.list_tools()
async def list_tools():
    return [
        Tool(
            name="search_knowledge",
            description="Search the knowledge base",
            inputSchema={
                "type": "object",
                "properties": {
                    "query": {"type": "string"},
                    "limit": {"type": "integer", "default": 5}
                },
                "required": ["query"]
            }
        ),
        Tool(
            name="add_document",
            description="Add a new document to the knowledge base",
            inputSchema={
                "type": "object",
                "properties": {
                    "title": {"type": "string"},
                    "content": {"type": "string"},
                    "tags": {"type": "array", "items": {"type": "string"}}
                },
                "required": ["title", "content"]
            }
        )
    ]

# 3. PROMPTS: Standardized interactions
@server.list_prompts()
async def list_prompts():
    return [
        Prompt(
            name="summarize_topic",
            description="Summarize all documents on a topic",
            arguments=[
                PromptArgument(name="topic", required=True)
            ]
        )
    ]

Workflow: AI Using All Capabilities

Here's how an AI might use this server:

1. Read resource to get full document content
2. Call tool to search for related documents
3. Use prompt to structure the summary request

User: "Summarize our AI security policies"

AI Actions:
1. search_knowledge(query="AI security policies") → Gets doc IDs
2. read_resource("doc://policy-123") → Gets full content
3. read_resource("doc://policy-456") → Gets more content
4. Summarizes based on documents

Resource + Tool Coordination

Design resources and tools to work together:

# Resource: Read-only view
Resource(uri="user://123", name="User 123 Profile")

# Tool: Modify user
Tool(name="update_user", description="Update user profile")

Best Practices

Practice	Reason
Clear separation	Resources for reading, tools for actions
Consistent URIs	Makes resources predictable
Related naming	user://123 with update_user tool
Document relationships	Explain in descriptions

Now let's apply these patterns in a hands-on lab. :::