Skip to main content
Glama
small-tou

MCP Test Server

by small-tou
OverviewSchemaRelated ServersScoreDiscussions
TypeScript

MCP 测试项目

这是一个基于 Model Context Protocol (MCP) TypeScript SDK 的测试项目，用于演示和测试 MCP 的不同机制，包括 Resources、Tools 和 Prompts。

项目特性

📄 Resources (资源)

  • 用户列表 (test://users) - 获取所有用户数据

  • 待办事项 (test://todos) - 获取所有待办事项数据

  • 配置信息 (test://config) - 系统配置信息

  • 系统日志 (test://logs) - 查看系统操作日志

🔧 Tools (工具)

  • add_user - 添加新用户

  • search_users - 搜索用户（支持按姓名、邮箱和角色筛选）

  • create_todo - 创建待办事项

  • calculate - 执行数学计算（支持表达式和基本运算）

💬 Prompts (提示模板)

  • user_analysis - 用户数据分析提示

  • todo_summary - 待办事项摘要提示

  • system_report - 系统状态报告提示

  • code_review - 代码审查提示模板

Related MCP server: MCP AI Chat LangChain

快速开始

1. 安装依赖

npm install

2. 构建项目

npm run build

3. 启动 MCP 服务器

npm start

4. 运行测试客户端

在另一个终端中运行：

npm test

项目结构

mcp-test-project/
├── src/
│   ├── index.ts          # MCP 服务器主文件
│   └── test-client.ts    # 测试客户端
├── dist/                 # 编译后的文件
├── package.json
├── tsconfig.json
└── README.md

使用示例

Resources 示例

// 列出所有资源
const resources = await client.listResources();

// 读取用户资源
const usersResource = await client.readResource({ 
  uri: "test://users" 
});

Tools 示例

// 添加用户
const result = await client.callTool({
  name: "add_user",
  arguments: {
    name: "张三",
    email: "zhangsan@example.com",
    role: "admin"
  }
});

// 计算
const calcResult = await client.callTool({
  name: "calculate",
  arguments: {
    expression: "10 + 5 * 2"
  }
});

Prompts 示例

// 获取用户分析提示
const userAnalysis = await client.getPrompt({
  name: "user_analysis",
  arguments: {
    user_id: "1",
    analysis_type: "detailed"
  }
});

// 获取代码审查提示
const codeReview = await client.getPrompt({
  name: "code_review",
  arguments: {
    language: "typescript",
    code_snippet: "function hello() { return 'world'; }",
    focus_areas: "代码质量、性能"
  }
});

测试数据

项目包含以下测试数据：

用户数据

[
  { "id": 1, "name": "张三", "email": "zhangsan@example.com", "role": "admin" },
  { "id": 2, "name": "李四", "email": "lisi@example.com", "role": "user" },
  { "id": 3, "name": "王五", "email": "wangwu@example.com", "role": "user" }
]

待办事项数据

[
  { "id": 1, "title": "完成MCP测试项目", "completed": false, "userId": 1 },
  { "id": 2, "title": "学习TypeScript", "completed": true, "userId": 2 },
  { "id": 3, "title": "测试MCP功能", "completed": false, "userId": 1 }
]

开发脚本

  • npm run build - 编译 TypeScript 代码

  • npm start - 启动 MCP 服务器

  • npm run dev - 构建并启动服务器

  • npm test - 运行测试客户端

  • npm run clean - 清理构建文件

MCP 协议说明

Model Context Protocol (MCP) 是一个标准化协议，用于在大型语言模型和外部数据源/工具之间建立安全、可控的连接。

核心概念

  1. Resources - 静态数据或文档，模型可以读取但不能修改

  2. Tools - 模型可以调用的函数，用于执行操作或获取动态数据

  3. Prompts - 可重用的提示模板，支持参数化

技术栈

许可证

MIT License

参考链接

Available Tools

4 tools
add_userC

添加新用户

ParametersJSON Schema
NameRequiredDescriptionDefault
emailYes邮箱地址
nameYes用户姓名
roleNo用户角色user

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. '添加新用户' implies a write/mutation operation, but it doesn't specify permissions required, whether the operation is idempotent, what happens on duplicate emails, or error conditions. This leaves significant gaps for a tool that creates users.

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 - a single phrase that directly states the tool's purpose without any unnecessary words. It's front-loaded and wastes no space, 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.

Completeness2/5

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

For a user creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what the tool returns, what permissions are needed, how conflicts are handled, or other important behavioral aspects that an agent needs to use this tool effectively.

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

Parameters3/5

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

Schema description coverage is 100%, with all parameters (email, name, role) well-documented in the schema itself. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline for adequate coverage without adding value.

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 '添加新用户' (Add new user) clearly states the verb ('add') and resource ('user'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'search_users' or 'create_todo', which would require more specific context about what distinguishes user creation from other operations.

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 like 'search_users' or other sibling tools. There's no mention of prerequisites, typical use cases, or exclusions, leaving the agent to infer usage from the tool name alone.

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

calculateC

执行数学计算

ParametersJSON Schema
NameRequiredDescriptionDefault
aNo第一个数字
bNo第二个数字
expressionNo数学表达式，如 '2 + 3 * 4'
operationNo基本运算操作

TDQS

C2.5/5.0
Behavior1/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. The description '执行数学计算' doesn't reveal any behavioral traits such as side effects, error handling, performance characteristics, or output format. It's a minimal statement that fails to inform the agent about how the tool behaves beyond its basic function.

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 phrase '执行数学计算', which is front-loaded and wastes no words. It efficiently states the purpose without unnecessary elaboration, making it easy to parse quickly.

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

Completeness2/5

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

Given the complexity (4 parameters, no annotations, no output schema), the description is incomplete. It doesn't address how parameters interact (e.g., using 'expression' vs. 'operation' with 'a' and 'b'), what the tool returns, or any error conditions. For a tool with multiple input options and no structured output, more context is needed to guide effective use.

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

Parameters3/5

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

The input schema has 100% description coverage, with clear parameter descriptions (e.g., '第一个数字' for 'a', '数学表达式' for 'expression'). The description adds no additional meaning beyond what the schema provides, as it doesn't explain parameter relationships, constraints, or usage examples. Baseline score of 3 is appropriate since the schema does the heavy lifting.

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

Purpose3/5

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

The description '执行数学计算' (perform mathematical calculation) states a general purpose but is vague. It doesn't specify what kind of calculations, what resources are involved, or how it differs from potential alternatives. While it indicates the domain (mathematics), it lacks specificity about scope or method.

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 on when to use this tool versus alternatives. The description doesn't mention prerequisites, constraints, or comparison with sibling tools (e.g., add_user, create_todo, search_users), which are unrelated but highlight the lack of context. Usage is implied only by the general purpose.

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

create_todoC

创建待办事项

ParametersJSON Schema
NameRequiredDescriptionDefault
titleYes待办事项标题
userIdYes用户ID

TDQS

C2.6/5.0
Behavior2/5

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. '创建待办事项' implies a write operation (creation), but it doesn't disclose any behavioral traits such as permissions required, whether it's idempotent, error handling, or what happens on success/failure. This is a significant gap for a mutation tool with zero annotation coverage.

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

Conciseness4/5

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

The description is a single phrase '创建待办事项', which is highly concise and front-loaded with the core action. It wastes no words, though it could benefit from slightly more context to improve clarity without sacrificing brevity.

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

Completeness2/5

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

Given the complexity of a creation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the tool returns, error conditions, or any behavioral context, making it inadequate for an agent to fully understand how to use this tool effectively.

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

Parameters3/5

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

The description adds no meaning beyond what the input schema provides. Schema description coverage is 100%, with clear documentation for both parameters ('title' and 'userId'), so the baseline score of 3 is appropriate as the schema handles the parameter semantics adequately without additional value from the description.

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

Purpose3/5

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

The description '创建待办事项' (Create todo) states a clear verb+resource combination, indicating it creates a todo item. However, it doesn't distinguish this tool from potential siblings like 'add_user' or 'calculate' beyond the obvious domain difference, and it lacks specificity about what kind of todo system or context it operates in.

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. There are no explicit instructions on prerequisites, context, or comparisons to sibling tools like 'add_user' or 'search_users', leaving the agent to infer usage based solely on the tool name and parameters.

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

search_usersC

搜索用户

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes搜索关键词
roleNo按角色筛选

TDQS

C2.2/5.0
Behavior1/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure but provides none. It doesn't indicate whether this is a read-only operation, what permissions might be required, whether results are paginated or limited, what happens with empty queries, or how results are sorted. For a search tool with zero annotation coverage, this represents a complete lack of behavioral context.

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

Conciseness4/5

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

The description is extremely concise - just two Chinese characters. While this represents efficient communication, it's arguably under-specified rather than appropriately concise. However, given the scoring framework, it earns points for being front-loaded with the core purpose and having zero wasted words, though it lacks the structure of a more complete description.

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

Completeness2/5

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

Given the tool's complexity (search operation with filtering), lack of annotations, and absence of an output schema, the description is insufficiently complete. It doesn't explain what the search returns, how results are formatted, whether there are limitations on search scope, or any error conditions. For a search tool that likely returns structured user data, this minimal description leaves critical gaps in understanding.

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

Parameters3/5

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

The schema description coverage is 100%, with both parameters ('query' and 'role') having descriptions in the schema. The tool description adds no additional parameter information beyond what's already documented in the schema. According to the scoring rules, when schema coverage is high (>80%), the baseline is 3 even with no parameter info in the description.

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

Purpose2/5

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

The description '搜索用户' (Search users) states the general purpose but is vague and tautological - it essentially restates the tool name 'search_users' in Chinese. It doesn't specify what kind of search this performs (exact match, partial, fuzzy), what user attributes are searched, or how results are returned. While it indicates the verb (search) and resource (users), it lacks the specificity needed for clear agent understanding.

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?

There is no guidance on when to use this tool versus alternatives. The description doesn't mention any prerequisites, limitations, or comparison with sibling tools like 'add_user'. An agent wouldn't know if this is for finding existing users before adding new ones, or if there are specific scenarios where this search is appropriate versus other user-related operations.

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. 4 tool updatesv1.0.0
    • First observedadd_user
    • First observedcalculate
    • First observedcreate_todo
    • First observedsearch_users
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.7/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: add_user and search_users handle user management, calculate performs mathematical operations, and create_todo manages tasks. There is no overlap or ambiguity between these domains, making tool selection straightforward.

Naming Consistency4/5

Three tools follow a consistent verb_noun pattern (add_user, create_todo, search_users), but 'calculate' deviates by using only a verb without a noun. This minor inconsistency slightly reduces predictability, though the naming remains readable and functional.

Tool Count3/5

With only 4 tools, the server feels thin and under-scoped for a general 'Test Server' purpose, lacking coverage in areas like updates, deletions, or broader operations. While each tool is distinct, the count is borderline low for typical server functionality.

Completeness2/5

The tool set is severely incomplete for user and task management domains. For users, there is no update_user or delete_user, and for todos, no get_todo, update_todo, or delete_todo. This creates significant gaps that will likely cause agent failures in common workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

  • MCP Server Demo

    bollam1818
    F
    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.
    -

  • Demo MCP Server

    thechandanbhagat
    F
    license
    Not graded
    quality
    D
    maintenance
    A demonstration server designed to showcase core Model Context Protocol (MCP) primitives including tools, resources, and prompts for presentations. It provides functional examples like text analysis and financial calculations to illustrate how AI models interact with external functions and data.
    5
    -

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/small-tou/mcp-test'

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