Skip to main content
Glama
zhangzhefang-github

MCP Add Server

MCP Add Server

A minimal Model Context Protocol (MCP) server that provides a simple add(a, b) tool. This project serves as a basic example of an MCP server implementation.

npm version

Features

  • Implements a Model Context Protocol compliant server.

  • Provides a single tool: add(a, b) which returns the sum of two numbers.

  • Available on npm for easy installation and use.

Related MCP server: Basic Math MCP Server

实际运行效果 (Showcase)

下图展示了 mcp-add-servermcp.so 服务发现平台上的配置信息,以及一个兼容 MCP 的聊天机器人 (例如 Cherry Studio) 成功调用本服务器的 add 工具来执行加法运算的场景:

MCP Add Server in Action

  • 左侧: mcp-add-servermcp.so 上的信息,展示了其概述和启动配置。

  • 右侧: 一个 MCP 客户端 (例如 Cherry Studio 这样的聊天机器人) 接收到用户关于加法的请求后,调用了 @zhefang/mcp-add-server 提供的 add 工具,并正确返回了计算结果。

这清晰地演示了遵循 Model Context Protocol 的服务器和客户端之间如何无缝集成和协作。

Prerequisites

  • Node.js (version 18.x.x or higher recommended)

  • npm (comes with Node.js)

Installation

The easiest way to use this MCP server is with npx:

npx @zhefang/mcp-add-server

Global Installation

For frequent use, install globally:

npm install -g @zhefang/mcp-add-server

Then run:

mcp-add-server

Development Setup

  1. Clone the repository:

    git clone https://github.com/zhangzhefang-github/mcp-add-server.git
    cd mcp-add-server
  2. Install dependencies:

    npm install
  3. Run locally:

    npm start

Usage

There are several ways to run the mcp-add-server:

1. Using npx (Recommended for most users):

npx @zhefang/mcp-add-server

This command will download the latest version of @zhefang/mcp-add-server and execute it.

2. Global installation (for frequent use):

npm install -g @zhefang/mcp-add-server
mcp-add-server

3. Running from a cloned repository:

After cloning the repository and installing dependencies:

npm start

4. Local linking for development: In the project's root directory:

npm link
mcp-add-server

Once the server is running, it will be available to MCP clients via stdio transport.

Client Example

The src/client.js file demonstrates how to connect to the server:

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";

const transport = new StdioClientTransport({
  command: "npx",
  args: ["@zhefang/mcp-add-server"]
});

// Connect and use the add tool
await client.connect(transport);
const result = await client.callTool({
  name: "add",
  arguments: { a: 10, b: 5 }
});
console.log("计算结果:", result);

Example Tool Call (JSON)

{
  "tool_name": "add",
  "arguments": {
    "a": 5,
    "b": 3
  }
}

The server responds with:

{
  "content": [
    {
      "type": "text", 
      "text": "结果是:8"
    }
  ]
}

Running Tests

(When tests are added, describe how to run them here)

npm test

(Currently, npm test will output "Error: no test specified". Update the test script in package.json when tests are added.)

Project Structure

mcp-add-server/
├── .git/               # Git directory
├── .gitignore          # Specifies intentionally untracked files that Git should ignore
├── .cursor/            # Cursor specific files (if any)
├── node_modules/       # Project dependencies
├── src/                # Source code
│   └── server.js       # Main server logic
├── bin.js              # Executable for the server
├── LICENSE             # Project license
├── package-lock.json   # Records exact versions of dependencies
├── package.json        # Project metadata and dependencies
└── README.md           # This file

Contributing

Contributions are welcome! Please feel free to submit a pull request or open an issue.

License

This project is licensed under the MIT License.

Available Tools

1 tool
addD
ParametersJSON Schema
NameRequiredDescriptionDefault
aYes第一个加数
bYes第二个加数

TDQS

D1/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

TDQS

D1.7/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap with other tools. The single tool 'add' stands alone without any ambiguity in purpose.

Naming Consistency5/5

A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'add' is straightforward and follows a simple verb pattern.

Tool Count2/5

A single tool is generally too few for most server purposes, as it limits functionality and scope. Without a description, it's unclear if this minimal set is justified, but typically one tool feels thin and incomplete.

Completeness1/5

With only one tool and no description, it is impossible to assess coverage of any domain. The surface is severely incomplete, lacking any context or additional operations that might be expected for a coherent toolset.

Maintenance

ActivityInactive
ResponsivenessSyncing

Related MCP Connectors

Related MCP Servers

  • F
    license
    B
    quality
    D
    maintenance
    A simple server that provides basic mathematical operations (sum and subtraction) through the Model Context Protocol.
    2
    1
  • A
    license
    Not graded
    quality
    D
    maintenance
    A minimal, production-ready MCP server with a simple addition calculator tool that demonstrates integration with the Model Context Protocol.
    15
    1
    MIT
  • F
    license
    B
    quality
    Not graded
    maintenance
    A minimal Model Context Protocol server that provides a simple tool for adding two integers. It serves as a demonstration of the official Python MCP SDK and is designed for local execution via stdio.
    1

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zhangzhefang-github/mcp-add-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server