Skip to main content
Glama
MCP Server Example

MCP Server Example

MCP Server Example

A simple MCP (Model Context Protocol) server for learning the core primitives: Tools, Resources, and Prompts.

Setup

Prerequisites

  • Python 3.10+

  • uv

Install

uv sync

Related MCP server: MCP AI Chat LangChain

Test

uv run mcp dev server.py

Opens a browser UI at http://localhost:6274. From there you can:

  • Tools tab: call save_note, delete_note with custom inputs

  • Resources tab: read notes://list or notes://{name}

  • Prompts tab: run summarize_notes or brainstorm with arguments

Option 2 — CLI with mcp client

List all available tools:

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | uv run python server.py

Connect to Claude Code (CLI)

Add the server to your Claude Code session:

claude mcp add learning-mcp -- uv run --directory /Users/binod/projects/mcp-example python server.py

Verify it's connected:

claude mcp list

Once added, Claude Code can call your tools directly in the chat — just ask it to, e.g. "save a note called 'ideas'".

Connect to Claude Desktop

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "learning-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory", "/Users/binod/projects/mcp-example",
        "python", "server.py"
      ]
    }
  }
}

Then restart Claude Desktop.

Use programmatically (Python)

Use the mcp library to call tools, read resources, and fetch prompts from your own code:

from mcp import ClientSession
from mcp.client.stdio import stdio_client, StdioServerParameters
import asyncio

async def main():
    server = StdioServerParameters(
        command="uv", args=["run", "python", "server.py"]
    )
    async with stdio_client(server) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()

            # Read a resource
            notes = await session.read_resource("notes://list")
            print(notes)

            # Get a prompt
            prompt = await session.get_prompt("brainstorm", {"topic": "side projects"})
            print(prompt)

asyncio.run(main())

To let Claude (via Anthropic API) call your tools, add anthropic[mcp] to your dependencies and convert the tools:

from anthropic.lib.tools.mcp import async_mcp_tool
import anthropic

client = anthropic.AsyncAnthropic()
tools = [async_mcp_tool(t, session) for t in (await session.list_tools()).tools]

runner = client.beta.messages.tool_runner(
    model="claude-opus-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Save a note called ideas"}],
    tools=tools,
)
async for message in runner:
    for block in message.content:
        if hasattr(block, "text"):
            print(block.text)

What's inside

File

Description

server.py

MCP server with tools, resources, and prompts

pyproject.toml

Project dependencies

Tools (Claude can call these)

Tool

Description

save_note(name, content)

Save a note

delete_note(name)

Delete a note

Resources (Claude can read these)

URI

Description

notes://list

List all saved notes

notes://{name}

Read a specific note

Prompts (reusable templates)

Prompt

Description

summarize_notes

Summarize all saved notes

brainstorm(topic)

Brainstorm ideas on a topic

Available Tools

4 tools
addA

Add two numbers.

Inputs: a (required), b (required). Returns: result

delete_noteC

Delete a note by name.

Inputs: name (required). Returns: result

multiplyA

Multiply two numbers.

Inputs: a (required), b (required). Returns: result

save_noteC

Save a note with a given name.

Inputs: name (required), content (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    C2.6/5.0

    Scored across 4 tools

    Disambiguation2/5

    The tools fall into two unrelated domains (arithmetic and note management) with no overlap within each domain, but the set as a whole is confusing because add/multiply and delete_note/save_note serve completely different purposes. An agent might struggle to understand why these tools are grouped together, though individual tools are distinct.

    Naming Consistency2/5

    Naming is inconsistent across the set: add and multiply use simple verbs without objects, while delete_note and save_note follow a verb_noun pattern. This mixed convention lacks a predictable pattern, making the tool set harder to navigate.

    Tool Count3/5

    With 4 tools, the count is reasonable for a small server, but it feels thin and poorly scoped because it covers two unrelated domains. For either arithmetic or note management alone, 4 tools would be appropriate, but combined, it suggests an incomplete or mismatched purpose.

    Completeness2/5

    For arithmetic, basic operations like subtraction and division are missing, leaving gaps. For note management, there's no way to list or retrieve notes, creating dead ends. The server lacks a clear domain, making completeness hard to assess, but obvious gaps exist in both inferred areas.

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A demonstration implementation of a Model Context Protocol server that provides simple mathematical tools (add, subtract) and personalized greeting resources.
      -
    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      A demonstration MCP server that provides calculator tools for arithmetic operations, personalized greeting resources, and code review prompt templates. Enables users to perform basic math calculations, generate dynamic greetings, and access reusable code review templates through the Model Context Protocol.
      MIT