Skip to main content
Glama
FuzzyCZX

MCP Communication Server

by FuzzyCZX
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

MCP 通信服务器

一个支持页面与客户端数据通信的MCP (Model Context Protocol) 服务器实现。

🏗️ 架构设计

本项目采用分离式架构设计：

  • MCP 服务器 (src/index.ts) - 纯粹的MCP协议服务器，提供工具和资源

  • Web 服务器 (src/web-server.ts) - 独立的HTTP/WebSocket服务器，处理静态文件和实时通信

Related MCP server: Figma MCP Server

📦 安装依赖

npm install

🚀 启动服务

方式1：分别启动（推荐用于开发）

# 编译TypeScript代码
npm run build

# 启动Web服务器 (端口3001)
npm run start:web

# 启动MCP服务器 (在另一个终端)
npm run start

方式2：同时启动两个服务

npm run build
npm run start:both

方式3：只启动Web服务器

npm run build
npm run start:web

🌐 访问地址

启动Web服务器后，可以通过以下URL访问：

  • 主页: http://localhost:3001/

  • 测试页面: http://localhost:3001/test-page.html

  • 服务器状态: http://localhost:3001/api/status

  • 连接列表: http://localhost:3001/api/connections

🛠️ MCP 工具

MCP服务器提供以下工具：

1. open_web_page

  • 功能: 在浏览器中打开指定URL

  • 参数: url (string) - 要打开的网页地址

  • 示例: 

    open_web_page("http://localhost:3001/test-page.html")

2. list_connections

  • 功能: 列出所有活跃的WebSocket连接

  • 参数: 无

  • 返回: 当前所有连接ID列表

3. get_page_data

  • 功能: 获取页面发送的数据

  • 参数: connectionId (可选) - 指定连接ID，不提供则返回所有数据

  • 返回: 页面数据的JSON格式

4. send_to_page

  • 功能: 向指定页面发送消息

  • 参数:

    • connectionId (string) - 目标连接ID

    • message (any) - 要发送的消息内容

🔄 通信流程

  1. 建立连接：网页通过WebSocket连接到 ws://localhost:3001

  2. 获取连接ID：服务器自动分配唯一连接ID

  3. 发送数据：网页发送数据到服务器（如页面状态、用户输入等）

  4. MCP交互：通过MCP工具获取数据或发送指令

  5. 实时通信：支持双向实时数据交换

📝 消息格式

页面发送到服务器

{
  "type": "page_data",
  "data": {
    "page": "test",
    "user_input": "Hello World",
    "timestamp": "2024-01-01T00:00:00Z"
  }
}

服务器发送到页面

{
  "type": "mcp_message",
  "message": {
    "command": "update_ui",
    "data": "Some data from MCP client"
  },
  "timestamp": "2024-01-01T00:00:00Z"
}

🔧 开发

监听模式开发

# 在一个终端启动TypeScript监听编译
npm run dev

# 在另一个终端启动Web服务器
npm run start:web

# MCP服务器需要手动重启来加载新代码
npm run start

添加新的MCP工具

在 src/index.ts 中使用 server.registerTool() 添加新工具。

扩展Web API

在 src/web-server.ts 中添加新的HTTP端点或WebSocket消息处理逻辑。

📁 项目结构

mcp/
├── src/
│   ├── index.ts          # MCP服务器
│   └── web-server.ts     # Web服务器
├── test-page.html        # 测试页面
├── package.json          # 项目配置
├── tsconfig.json         # TypeScript配置
└── README.md            # 说明文档

💡 使用场景

  • 网页与AI助手的实时数据交换

  • 浏览器插件与MCP客户端通信

  • 在线工具与外部服务集成

  • 实时协作应用开发

⚠️ 注意事项

  1. 确保防火墙允许3001端口访问

  2. 在生产环境中需要配置HTTPS和WSS

  3. 考虑添加身份验证和授权机制

  4. 监控WebSocket连接数量，避免资源泄露

Available Tools

2 tools
addAddition ToolC

Add two numbers

ParametersJSON Schema
NameRequiredDescriptionDefault
aYes
bYes

TDQS

C2.4/5.0
Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description 'Add two numbers' reveals nothing about behavioral traits such as error handling, performance characteristics, side effects, or return format. It's a minimal statement that doesn't add any context beyond the basic operation.

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

Conciseness5/5

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

The description is extremely concise with a single sentence 'Add two numbers' that directly states the purpose without any waste. It's front-loaded and appropriately sized for a simple tool, though this conciseness comes at the cost of completeness.

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?

Given the tool's simplicity (2 parameters, no annotations, no output schema), the description is incomplete. It doesn't cover behavioral aspects, parameter semantics, or usage guidelines. While the operation is straightforward, the description lacks necessary context for an AI agent to understand how to invoke it effectively beyond the basic schema.

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?

The schema description coverage is 0%, meaning the input schema provides no descriptions for parameters 'a' and 'b'. The description 'Add two numbers' adds no meaning beyond what the schema already implies from property names and types. It doesn't explain what 'a' and 'b' represent, their constraints, or usage examples.

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

Purpose4/5

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

The description 'Add two numbers' clearly states the tool's purpose with a specific verb ('Add') and resource ('two numbers'). It's unambiguous about what the tool does, though it doesn't explicitly distinguish from the sibling tool 'open_web_page' since they serve completely different domains (mathematics vs. web navigation).

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any context, prerequisites, or exclusions for usage. The sibling tool 'open_web_page' is unrelated, so no comparison is needed, but there's still no usage context provided.

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

open_web_page打开网页A

在IDE中打开一个新的网页窗口显示指定的URL，并自动等待接收页面发送的WebSocket数据

ParametersJSON Schema
NameRequiredDescriptionDefault
timeoutMsNo等待数据的超时时间（毫秒），默认10秒
urlYes
waitForDataNo是否等待页面发送数据，默认为true

TDQS

A3.7/5.0
Behavior3/5

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

With no annotations provided, the description carries full burden and partially succeeds. It discloses that the tool opens a web page in an IDE and waits for WebSocket data, which are key behavioral traits. However, it doesn't mention potential side effects, error conditions, or what happens after timeout/WebSocket receipt.

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

Conciseness5/5

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

The description is a single, efficient sentence that front-loads the core functionality (opening web pages) and adds the WebSocket waiting behavior. Every word earns its place with no redundancy or unnecessary elaboration.

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

Completeness3/5

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

For a tool with 3 parameters, no annotations, and no output schema, the description provides adequate basic functionality explanation but lacks details about return values, error handling, or IDE-specific constraints. It's minimally viable but has clear gaps in behavioral context.

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

Parameters4/5

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

With 67% schema description coverage (2 of 3 parameters documented in schema), the description adds meaningful context by explaining that the tool '自动等待接收页面发送的WebSocket数据' which clarifies the purpose of the waitForData parameter. This compensates well for the partial schema coverage.

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

Purpose5/5

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

The description clearly states the specific action ('在IDE中打开一个新的网页窗口显示指定的URL') and distinguishes it from the sibling tool 'add' by specifying it opens web pages in an IDE environment. It goes beyond the title by adding the WebSocket data waiting functionality.

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

Usage Guidelines2/5

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

No guidance is provided about when to use this tool versus alternatives. The description doesn't mention any prerequisites, constraints, or comparison with other tools that might open web pages or handle WebSocket data differently.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedadd
    • First observedopen_web_page
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.7/5.0
Disambiguation5/5

The two tools have completely distinct purposes: one performs a mathematical operation (adding numbers), while the other handles web page interaction (opening a URL and managing WebSocket data). There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.

Naming Consistency2/5

The naming is inconsistent: 'add' uses a simple verb without a noun, while 'open_web_page' follows a verb_noun pattern. This mixed convention lacks a predictable structure, though both names are readable. The inconsistency could cause minor confusion in a larger set.

Tool Count2/5

With only 2 tools, the server feels thin for a 'Communication Server' domain, which typically implies broader functionality like messaging, notifications, or data exchange. The tools cover basic math and web display but lack operations for communication workflows, making the count insufficient for the apparent scope.

Completeness1/5

The server is severely incomplete for a communication domain. It lacks core operations such as sending/receiving messages, managing connections, or handling events. The existing tools (add and open_web_page) do not align with communication tasks, leaving significant gaps that would cause agent failures in typical use cases.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

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/FuzzyCZX/MCP'

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