Apifox MCP Pro
Provides diagnostic and information tools for Apifox projects, including token validation, project access checks, and documentation of API limitations. Due to Apifox's limited Open API, only basic project information and diagnostic capabilities are available, with most management features requiring the Apifox web interface or desktop client.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Apifox MCP Procheck if my Apifox token is still valid"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Apifox MCP Pro
English
⚠️ 项目状态说明 / Project Status
由于Apifox官方开放API功能极其有限(仅提供3个基础导入导出接口),本项目已从最初计划的33+个工具简化为9个诊断和信息查询工具。大部分API管理功能需要使用Apifox Web界面或桌面客户端。
Due to Apifox's extremely limited Open API (only 3 basic import/export endpoints), this project has been simplified from the originally planned 33+ tools to 9 diagnostic and information tools. Most API management features require using the Apifox web interface or desktop client.
Enhanced Apifox MCP Service with basic diagnostic and information capabilities for Claude Desktop and Cursor.
🆚 Comparison with Official MCP
Feature | Official MCP | Apifox MCP Pro |
Tool Count | 3 tools | 9 tools (Limited) |
Project Management | ❌ | ⚠️ Basic info only |
API CRUD | ❌ | ❌ Not supported |
Batch Operations | ❌ | ❌ Not supported |
Cursor Support | ❌ | ✅ Native support |
NPM Installation | ❌ | ✅ One-click install |
CLI Tools | ❌ | ✅ Complete CLI |
⚠️ Important Limitations
Due to Apifox's extremely limited Open API, most advanced features are not available:
❌ API Interface Management - Cannot list, create, update, or delete APIs
❌ Folder Management - No folder operations supported
❌ Environment Management - Cannot manage environments
❌ Data Model Management - No schema operations
❌ Test Case Management - Cannot manage test cases
❌ Search Functionality - API search not supported
❌ Batch Operations - No bulk operations available
What IS available:
✅ Basic Project Info - Get project information and access checks
✅ Limitation Explanations - Clear documentation of what's not supported
✅ Token Validation - Check if your access token works
✅ Diagnostic Tools - Help understand API limitations
Reason: Apifox officially provides only 3 basic import/export API endpoints. Most management functions require using the Apifox web interface or desktop client.
Features
🚀 9 MCP Tools - Basic diagnostic and information tools
📋 Project Info - Get basic project information and access status
⚠️ Limitation Awareness - Clear documentation of API restrictions
🔍 Diagnostic Tools - Check token validity and project access
💻 Cross-Platform - Works with Claude Desktop and Cursor
📦 NPM Package - Easy installation via npm
🛠️ CLI Tools - Setup and configuration utilities
Note: Due to Apifox's limited Open API, advanced management features are not available. This tool primarily serves as a diagnostic and information utility.
Quick Start
Option 1: NPM Installation (Recommended)
# Install globally
npm install -g apifox-mcp-pro
# Set your Apifox access token
export APIFOX_ACCESS_TOKEN="your_access_token_here"
# Setup for Cursor
apifox-mcp-pro setup --cursor
# Setup for Claude Desktop
apifox-mcp-pro setup --claude
# Setup for both
apifox-mcp-pro setup --bothOption 2: Local Development
# Clone the repository
git clone https://github.com/guocong-bincai/Apifox_mcp_pro.git
cd Apifox_mcp_pro
# Install dependencies
npm install
# Build the project
npm run build
# Set environment variables
cp .env.example .env
# Edit .env and add your APIFOX_ACCESS_TOKEN
# Setup local configuration
npm run dev setup --both --localConfiguration
Getting Your Apifox Access Token
登录 Apifox 官网
进入个人设置 → API 访问令牌
创建新的访问令牌
复制生成的令牌(格式通常为
APS-xxxxxxxxxx)
⚠️ 安全提醒:
请妥善保管您的访问令牌,不要在代码中硬编码
不要在公共仓库中提交包含真实令牌的配置文件
使用环境变量或配置文件来管理令牌
Environment Variables
Create a .env file or set environment variables:
# Required - 从Apifox个人设置中获取
APIFOX_ACCESS_TOKEN=your_apifox_access_token_here
# Optional
APIFOX_BASE_URL=https://api.apifox.com # Default API base URL
LOG_LEVEL=info # Log level: debug, info, warn, error示例 .env 文件:
# .env 文件示例(请替换为您的真实令牌)
APIFOX_ACCESS_TOKEN=APS-your-actual-token-here
LOG_LEVEL=infoCursor Configuration
After running apifox-mcp-pro setup --cursor, the MCP server will be automatically configured. You can also manually add it to your Cursor settings:
{
"mcpServers": {
"apifox-mcp-pro": {
"command": "npx",
"args": ["apifox-mcp-pro"],
"env": {
"APIFOX_ACCESS_TOKEN": "your_apifox_access_token_here"
}
}
}
}Claude Desktop Configuration
For Claude Desktop, add to your claude_desktop_config.json:
{
"mcpServers": {
"apifox-mcp-pro": {
"command": "npx",
"args": ["apifox-mcp-pro"],
"env": {
"APIFOX_ACCESS_TOKEN": "your_apifox_access_token_here"
}
}
}
}Available Tools (9 total)
Project Information (2 tools)
apifox_project_info- Get MCP functionality overview and limitationsapifox_check_access- Check token validity and access permissions
API Information (2 tools)
apifox_api_info- Get API management limitations explanationapifox_check_project_access- Check specific project access
Feature Limitation Info (5 tools)
apifox_folder_info- Folder management limitationsapifox_environment_info- Environment management limitationsapifox_schema_info- Data model management limitationsapifox_test_info- Test case management limitationsapifox_import_export_info- Import/export functionality info
❌ Removed Tools (Previously Listed but Not Functional)
The following tools were removed because Apifox's Open API doesn't support them:
API Management (9 removed)
- API listing not supportedapifox_list_apis- API details not accessibleapifox_get_api- API creation not supportedapifox_create_api- API updates not supportedapifox_update_api- API deletion not supportedapifox_delete_api- Search functionality unavailableapifox_search_apis- Batch operations not supportedapifox_batch_delete_apis- Status updates not supportedapifox_batch_update_api_status- Moving APIs not supportedapifox_batch_move_apis
Project Management (4 removed)
- Limited API accessapifox_list_projects- Creation not supportedapifox_create_project- Updates not supportedapifox_update_project- Deletion not supportedapifox_delete_project
All Other Management Tools (14 removed)
All folder, environment, schema, test case, and import/export management tools
Reason for Removal: Apifox's Open API is extremely limited and only provides 3 basic import/export endpoints. All management operations require using the Apifox web interface or desktop application.
Usage Examples
Getting MCP Information
// In Claude or Cursor, you can ask:
"What Apifox MCP Pro features are available?"
// This will call:
apifox_project_info()Checking Access
// Check if your token works:
"Check my Apifox access permissions"
// This will call:
apifox_check_access()Understanding Limitations
// Get information about API management limitations:
"Why can't I list APIs in my Apifox project?"
// This will call:
apifox_api_info()Alternative Solutions
Since most management features are not available through the API, consider these alternatives:
// List all APIs in a project
"Show me all APIs in project 12345"
// Create a new API
"Create a GET API at /users/{id} for getting user details in project 12345"
// Search APIs
"Find all POST APIs in project 12345"Batch Operations
// Batch update API status
"Mark APIs with IDs [1, 2, 3] as 'released'"
// Batch move APIs
"Move APIs [4, 5, 6] to folder 'v2-apis'"CLI Commands
# Start MCP server (default)
apifox-mcp-pro
# Setup configuration
apifox-mcp-pro setup --cursor # Setup for Cursor
apifox-mcp-pro setup --claude # Setup for Claude Desktop
apifox-mcp-pro setup --both # Setup for both
apifox-mcp-pro setup --local # Use local node instead of npx
apifox-mcp-pro setup --examples # Generate config examples only
# Show version
apifox-mcp-pro --version
# Show help
apifox-mcp-pro --helpDevelopment
# Install dependencies
npm install
# Build the project
npm run build
# Run in development mode
npm run dev
# Run tests
npm test
# Lint code
npm run lint
# Format code
npm run formatConfiguration Files
The setup command generates several configuration files:
cursor-mcp-config.json- Cursor MCP configurationclaude-desktop-config.json- Claude Desktop configurationlocal-config-example.json- Local development configuration
Troubleshooting
Common Issues
Access Token Issues
# Make sure your token is set correctly echo $APIFOX_ACCESS_TOKEN # Or check in your IDE configurationInstallation Issues
# Clear npm cache and reinstall npm cache clean --force npm install -g apifox-mcp-proConfiguration Issues
# Regenerate configuration files apifox-mcp-pro setup --both --examples
Getting Help
Check the USAGE.md for detailed usage instructions
Review the generated configuration files
Check your Apifox access token permissions
Verify your IDE MCP configuration
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
License
MIT License - see LICENSE file for details.
Changelog
v1.0.0
Initial release with 33 MCP tools
NPM package support
Cursor and Claude Desktop integration
Comprehensive API management features
CLI setup tools
Note: This is an enhanced version of the official Apifox MCP service, providing significantly more functionality than the basic official implementation.
Related MCP server: Apifox MCP Server
中文
⚠️ 项目状态说明
由于Apifox官方开放API功能极其有限(仅提供3个基础导入导出接口),本项目已从最初计划的33+个工具简化为9个诊断和信息查询工具。大部分API管理功能需要使用Apifox Web界面或桌面客户端。
为 Claude Desktop 和 Cursor 提供基础诊断和信息功能的 Apifox MCP 服务。
🆚 与官方 MCP 对比
功能 | 官方 MCP | Apifox MCP Pro |
工具数量 | 3个 | 9个工具(受限) |
项目管理 | ❌ | ⚠️ 仅基础信息 |
API CRUD | ❌ | ❌ 不支持 |
批量操作 | ❌ | ❌ 不支持 |
Cursor 支持 | ❌ | ✅ 原生支持 |
NPM 安装 | ❌ | ✅ 一键安装 |
CLI 工具 | ❌ | ✅ 完整 CLI |
⚠️ 重要限制
由于Apifox开放API功能极其有限,大部分高级功能不可用:
❌ API接口管理 - 无法列出、创建、更新或删除API
❌ 文件夹管理 - 不支持文件夹操作
❌ 环境管理 - 无法管理环境
❌ 数据模型管理 - 不支持Schema操作
❌ 测试用例管理 - 无法管理测试用例
❌ 搜索功能 - 不支持API搜索
❌ 批量操作 - 不支持批量操作
可用功能:
✅ 基础项目信息 - 获取项目信息和访问检查
✅ 限制说明 - 清晰的不支持功能文档
✅ 令牌验证 - 检查访问令牌是否有效
✅ 诊断工具 - 帮助理解API限制
原因: Apifox官方仅提供3个基础导入导出API端点。大部分管理功能需要使用Apifox Web界面或桌面客户端。
功能特性
🚀 9个MCP工具 - 基础诊断和信息工具
📋 项目信息 - 获取基础项目信息和访问状态
⚠️ 限制说明 - 清晰的API限制文档
🔍 诊断工具 - 检查令牌有效性和项目访问
💻 跨平台 - 支持 Claude Desktop 和 Cursor
📦 NPM 包 - 通过 npm 轻松安装
🛠️ CLI 工具 - 设置和配置工具
注意: 由于Apifox开放API限制,高级管理功能不可用。此工具主要作为诊断和信息查询工具使用。
快速开始
方式一:NPM 安装(推荐)
# 全局安装
npm install -g apifox-mcp-pro
# 设置 Apifox 访问令牌
export APIFOX_ACCESS_TOKEN="your_access_token_here"
# 配置 Cursor
apifox-mcp-pro setup --cursor
# 配置 Claude Desktop
apifox-mcp-pro setup --claude
# 同时配置两者
apifox-mcp-pro setup --both方式二:本地开发
# 克隆仓库
git clone https://github.com/guocong-bincai/Apifox_mcp_pro.git
cd Apifox_mcp_pro
# 安装依赖
npm install
# 构建项目
npm run build
# 设置环境变量
cp .env.example .env
# 编辑 .env 文件并添加你的 APIFOX_ACCESS_TOKEN
# 设置本地配置
npm run dev setup --both --local配置
环境变量
创建 .env 文件或设置环境变量:
# 必需
APIFOX_ACCESS_TOKEN=your_apifox_access_token_here
# 可选
APIFOX_BASE_URL=https://api.apifox.com # 默认 API 基础 URL
LOG_LEVEL=info # 日志级别:debug, info, warn, errorCursor 配置
运行 apifox-mcp-pro setup --cursor 后,MCP 服务器将自动配置。您也可以手动添加到 Cursor 设置中:
{
"mcpServers": {
"apifox-mcp-pro": {
"command": "npx",
"args": ["apifox-mcp-pro"],
"env": {
"APIFOX_ACCESS_TOKEN": "your_apifox_access_token_here"
}
}
}
}Claude Desktop 配置
对于 Claude Desktop,添加到您的 claude_desktop_config.json:
{
"mcpServers": {
"apifox-mcp-pro": {
"command": "npx",
"args": ["apifox-mcp-pro"],
"env": {
"APIFOX_ACCESS_TOKEN": "your_apifox_access_token_here"
}
}
}
}可用工具(共9个)
项目信息(2个工具)
apifox_project_info- 获取MCP功能概览和限制信息apifox_check_access- 检查令牌有效性和访问权限
API信息(2个工具)
apifox_api_info- 获取API管理限制说明apifox_check_project_access- 检查特定项目访问权限
功能限制信息(5个工具)
apifox_folder_info- 文件夹管理限制说明apifox_environment_info- 环境管理限制说明apifox_schema_info- 数据模型管理限制说明apifox_test_info- 测试用例管理限制说明apifox_import_export_info- 导入导出功能信息
❌ 已删除的工具(之前列出但不可用)
由于Apifox开放API不支持,以下工具已被删除:
API管理(9个已删除)
- 不支持API列表查询apifox_list_apis- 无法访问API详情apifox_get_api- 不支持API创建apifox_create_api- 不支持API更新apifox_update_api- 不支持API删除apifox_delete_api- 搜索功能不可用apifox_search_apis- 不支持批量操作apifox_batch_delete_apis- 不支持状态更新apifox_batch_update_api_status- 不支持移动APIapifox_batch_move_apis
项目管理(4个已删除)
- API访问受限apifox_list_projects- 不支持创建apifox_create_project- 不支持更新apifox_update_project- 不支持删除apifox_delete_project
其他所有管理工具(14个已删除)
所有文件夹、环境、数据模型、测试用例和导入导出管理工具
删除原因: Apifox开放API功能极其有限,仅提供3个基础导入导出端点。所有管理操作需要使用Apifox Web界面或桌面应用程序。
使用示例
获取MCP信息
// 在 Claude 或 Cursor 中,您可以询问:
"Apifox MCP Pro 有哪些可用功能?"
// 这将调用:
apifox_project_info()检查访问权限
// 检查令牌是否有效:
"检查我的 Apifox 访问权限"
// 这将调用:
apifox_check_access()了解限制
// 获取API管理限制信息:
"为什么我无法列出 Apifox 项目中的 API?"
// 这将调用:
apifox_api_info()替代解决方案
由于大部分管理功能通过API不可用,请考虑以下替代方案:
使用 Apifox Web界面 进行完整的API管理
使用 Apifox 桌面客户端获得最佳体验
等待官方完善开放API功能
CLI 命令
# 启动 MCP 服务器(默认)
apifox-mcp-pro
# 设置配置
apifox-mcp-pro setup --cursor # 设置 Cursor
apifox-mcp-pro setup --claude # 设置 Claude Desktop
apifox-mcp-pro setup --both # 设置两者
apifox-mcp-pro setup --local # 使用本地 node 而不是 npx
apifox-mcp-pro setup --examples # 仅生成配置示例
# 显示版本
apifox-mcp-pro --version
# 显示帮助
apifox-mcp-pro --help开发
# 安装依赖
npm install
# 构建项目
npm run build
# 开发模式运行
npm run dev
# 运行测试
npm test
# 代码检查
npm run lint
# 格式化代码
npm run format配置文件
setup 命令会生成几个配置文件:
cursor-mcp-config.json- Cursor MCP 配置claude-desktop-config.json- Claude Desktop 配置local-config-example.json- 本地开发配置
故障排除
常见问题
访问令牌问题
# 确保您的令牌设置正确 echo $APIFOX_ACCESS_TOKEN # 或检查您的 IDE 配置安装问题
# 清除 npm 缓存并重新安装 npm cache clean --force npm install -g apifox-mcp-pro配置问题
# 重新生成配置文件 apifox-mcp-pro setup --both --examples
获取帮助
查看 USAGE.md 了解详细使用说明
查看生成的配置文件
检查您的 Apifox 访问令牌权限
验证您的 IDE MCP 配置
贡献
Fork 仓库
创建功能分支
进行更改
如适用,添加测试
提交 Pull Request
许可证
MIT 许可证 - 详见 LICENSE 文件。
更新日志
v1.0.0
首次发布,包含 33 个 MCP 工具
NPM 包支持
Cursor 和 Claude Desktop 集成
全面的 API 管理功能
CLI 设置工具
注意:这是官方 Apifox MCP 服务的增强版本,提供比基础官方实现更多的功能。
Available Tools
9 toolsapifox_api_infoB
获取Apifox开放API的使用说明和限制信息
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. While '获取' (get) implies a read-only operation, the description doesn't explicitly state whether this requires authentication, has rate limits, returns structured data, or involves any side effects. For a tool with zero annotation coverage, this leaves significant behavioral gaps unaddressed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese that directly states the tool's purpose without any fluff or redundancy. It's appropriately sized for a zero-parameter informational tool and front-loads the key action ('获取') and target ('使用说明和限制信息'). Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema), the description is minimally adequate. It explains what the tool does but lacks details on behavioral aspects like authentication needs or return format. Without annotations or output schema, the description should ideally provide more context about what '使用说明和限制信息' entails, but it meets the basic threshold for such a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the lack of inputs. The description doesn't need to compensate for any parameter gaps, and it appropriately doesn't mention parameters. A baseline of 4 is justified since no parameter information is required beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as '获取Apifox开放API的使用说明和限制信息' (Get usage instructions and limitation information for Apifox Open API). It uses specific verbs ('获取' - get) and resources ('使用说明和限制信息' - usage instructions and limitation information), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'apifox_import_export_info' or 'apifox_schema_info' which might also provide informational content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 for usage, prerequisites, or exclusions. With multiple sibling tools that appear informational (e.g., 'apifox_project_info', 'apifox_schema_info'), the lack of differentiation leaves the agent guessing about appropriate use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_check_accessB
检查当前Token的访问权限
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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 only states what the tool does ('检查当前Token的访问权限') but doesn't reveal any behavioral traits: what permissions are checked, what the response format looks like, whether it makes network calls, if there are rate limits, or what happens with invalid tokens. For a tool with zero annotation coverage, this is a significant gap in behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient Chinese sentence that directly states the tool's purpose without any unnecessary words. It's appropriately sized for a simple tool and front-loads the essential information. Every word earns its place in this minimal description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations, no output schema, and the description provides only basic purpose information, the description is incomplete for effective use. It doesn't explain what 'access permissions' means in this context, what format the results take, or what agents should do with the information. For a permission-checking tool that could be critical for security/access decisions, more context is needed despite the simple parameterless design.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage (empty schema). The description doesn't need to explain parameters since none exist. According to scoring rules, 0 parameters earns a baseline score of 4. The description appropriately doesn't mention parameters that don't exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '检查当前Token的访问权限' (Check current token's access permissions) clearly states the tool's purpose with a specific verb ('检查' - check) and resource ('访问权限' - access permissions). It distinguishes from siblings like 'apifox_api_info' or 'apifox_project_info' by focusing on token access verification rather than general information retrieval. However, it doesn't explicitly differentiate from 'apifox_check_project_access' which might be a more specific variant.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 when this tool should be called (e.g., before making API calls, for debugging), what prerequisites exist, or how it differs from sibling tools like 'apifox_check_project_access'. Without any usage context, agents must infer appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_check_project_accessB
检查指定项目的访问权限
| Name | Required | Description | Default |
|---|---|---|---|
| projectId | Yes | 项目ID |
TDQS
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. While '检查' (check) implies a read-only operation, the description doesn't explicitly state whether this is a safe read operation, what permissions are required, what format the results will be in, or whether there are any rate limits or side effects. For a tool with zero annotation coverage, this is insufficient 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise - a single Chinese phrase that directly states the tool's purpose. There's zero wasted language or unnecessary elaboration. Every word earns its place by conveying essential information about what the tool does.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's relative simplicity (single parameter, 100% schema coverage) and lack of annotations or output schema, the description is minimally adequate. It tells the agent what the tool does at a high level, but doesn't provide enough context about when to use it versus alternatives, what the behavior entails, or what results to expect. For a permission-checking tool with no output schema, more guidance would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'projectId' clearly documented in the schema as '项目ID' (project ID). The description doesn't add any additional parameter information beyond what's already in the schema. According to the scoring rules, when schema_description_coverage is high (>80%), the baseline is 3 even with no param info in the description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '检查指定项目的访问权限' clearly states the tool's purpose as checking access permissions for a specified project, providing a specific verb ('检查' - check) and resource ('指定项目的访问权限' - specified project's access permissions). However, it doesn't explicitly distinguish this from the sibling tool 'apifox_check_access', which appears to be a more general access check tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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's no mention of when this specific project access check should be used instead of the more general 'apifox_check_access' tool or other sibling tools. The description simply states what the tool does without providing usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_environment_infoC
获取环境管理功能的限制说明
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. While it indicates this is a read operation ('获取' - get/retrieve), it doesn't disclose important behavioral aspects like whether this requires authentication, what format the information is returned in, whether there are rate limits, or what happens if no environment restrictions exist. The description is minimal and leaves many behavioral questions unanswered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient Chinese sentence that directly states the tool's purpose. There's no wasted language or unnecessary elaboration. However, it could be slightly more front-loaded with additional context about what 'environment management' entails in this specific system.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what 'environment management' means in this context, what types of restrictions might be documented, or what format the information will be returned in. Given the lack of structured data elsewhere, the description should provide more context about what users can expect from this tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, and schema description coverage is 100% (though there are no parameters to describe). The description appropriately doesn't attempt to explain non-existent parameters. A baseline of 4 is appropriate for a zero-parameter tool where the schema fully documents what's needed (nothing).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取环境管理功能的限制说明' (Get environment management function restriction descriptions) states what the tool does in general terms - it retrieves information about limitations for environment management. However, it's somewhat vague about the specific nature of these 'restrictions' and doesn't clearly distinguish this tool from its siblings like apifox_api_info or apifox_project_info, which likely also provide informational content about different aspects of the system.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance about when to use this tool versus alternatives. There's no mention of specific scenarios where one would need environment restriction information, nor does it indicate what other tools might be more appropriate for different types of information needs. The user must infer usage context 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.
apifox_folder_infoC
获取文件夹管理功能的限制说明
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. While it indicates this is a read operation (获取/get), it doesn't describe what happens when invoked - whether it requires authentication, returns structured data or plain text, has rate limits, or what happens if no folders exist. For a tool with zero annotation coverage, this leaves significant behavioral questions unanswered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient Chinese sentence that directly states the tool's purpose. There's no wasted verbiage or unnecessary elaboration. While it could be more specific about what '限制说明' (restriction instructions) entails, the phrasing is appropriately concise for what it communicates.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations, no output schema, and no parameters, the description should provide more complete context about what information is returned and when this tool is valuable. The current description leaves too many questions unanswered: What format are the restrictions in? Are they organizational policies or technical limits? What authentication is required? For a tool that presumably returns important configuration information, this is insufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage (empty schema). The description appropriately doesn't discuss parameters since none exist. It correctly focuses on what the tool does rather than trying to describe non-existent inputs. This meets the baseline expectation for parameterless tools.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取文件夹管理功能的限制说明' (Get folder management function restriction instructions) states what the tool does in general terms - retrieving restriction information about folder management. However, it doesn't specify what kind of restrictions (size limits, permission constraints, etc.) or what format the information comes in. It distinguishes from siblings like 'apifox_project_info' or 'apifox_api_info' by focusing on folders, but remains somewhat vague about the exact nature of the information retrieved.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 prerequisites (like needing folder access), when this information would be useful (before creating folders, when encountering errors), or what other tools might provide related information. The user must infer usage context 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.
apifox_import_export_infoC
获取导入导出功能的说明信息
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. It only states that it retrieves information, implying a read-only operation, but does not disclose any behavioral traits such as authentication needs, rate limits, or what format the information is returned in. This is inadequate for a 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized for a simple informational tool, though it could be slightly more specific to improve clarity without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not explain what the return values are, the format of the information, or any behavioral context. For a tool that retrieves functional information, more details about the output and usage context are needed to be fully helpful to an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the input schema fully documents the lack of parameters. The description does not add any parameter information, which is appropriate since there are no parameters to describe. The baseline for 0 parameters is 4, as the description need not compensate for any gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取导入导出功能的说明信息' (Get import/export function description information) states a clear purpose (get information about import/export features) but is somewhat vague about what specific information is retrieved. It distinguishes from siblings like 'apifox_api_info' or 'apifox_project_info' by focusing on import/export functionality, but lacks specificity about the verb and resource scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 does not mention any context, prerequisites, or exclusions, leaving the agent to infer usage based on the tool name alone. There is no explicit comparison with sibling tools like 'apifox_check_access' or 'apifox_environment_info'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_project_infoB
获取Apifox MCP功能说明和限制信息
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. While '获取' implies a read operation, the description doesn't disclose any behavioral traits such as authentication requirements, rate limits, response format, or whether this operation might be expensive. For a tool with zero annotation coverage, this is inadequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It's appropriately sized and front-loaded with the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no annotations, no output schema), the description is minimally adequate. However, it lacks context about what specific 'MCP功能说明和限制信息' includes, and without annotations or output schema, the agent has no insight into the response format or behavioral constraints. This leaves gaps in understanding the tool's full context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the absence of parameters. The description doesn't need to add parameter information, and it correctly doesn't mention any parameters. This meets the baseline for tools with no parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('获取' meaning 'get' or 'retrieve') and the resource ('Apifox MCP功能说明和限制信息' meaning 'Apifox MCP feature descriptions and limitation information'), providing a specific verb+resource combination. However, it doesn't explicitly differentiate from sibling tools like 'apifox_api_info' or 'apifox_import_export_info' which might retrieve different types of information.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 prerequisites, context for usage, or exclusions. Given the sibling tools that retrieve different types of Apifox information, this is a significant gap in helping the agent choose correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_schema_infoC
获取数据模型管理功能的限制说明
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. It mentions '获取' (get), implying a read-only operation, but doesn't specify whether it requires authentication, has rate limits, returns structured or unstructured data, or any error conditions. The description is minimal and fails to provide essential behavioral traits beyond the basic action, leaving significant gaps in understanding how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Chinese: '获取数据模型管理功能的限制说明'. It's front-loaded with the core action and resource, with no wasted words. However, it could be slightly more specific to improve clarity without losing conciseness. Overall, it's appropriately sized for a no-parameter tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no input schema (0 parameters) and no output schema, the description is incomplete. It lacks details on what the tool returns (e.g., format, structure of restriction info), behavioral aspects like authentication needs, and how it fits among siblings. For a tool that presumably provides important limitation data, the description should offer more context to guide effective use, especially without annotations to fill gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and the schema description coverage is 100% (though empty). With no parameters, the description doesn't need to compensate for schema gaps. It appropriately doesn't discuss parameters, aligning with the input schema. A baseline of 4 is justified as the description doesn't mislead about parameters and matches the schema's indication of none.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description '获取数据模型管理功能的限制说明' (Get restrictions/limitations for data model management functionality) states a purpose but is somewhat vague. It specifies a verb ('获取' - get) and a resource ('限制说明' - restriction explanations), but doesn't clarify what type of restrictions (rate limits, feature limitations, usage quotas) or what '数据模型管理功能' (data model management functionality) precisely entails. It distinguishes from some siblings (e.g., apifox_api_info, apifox_project_info) by focusing on restrictions rather than general info, but the scope remains ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 prerequisites, appropriate contexts, or exclusions. Given siblings like apifox_check_access or apifox_import_export_info, there's no indication of when to choose this tool over others for related queries about limitations or access. The lack of usage context leaves the agent guessing about its application.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
apifox_test_infoB
获取测试用例管理功能的限制说明
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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. While '获取' (get) implies a read-only operation, the description doesn't specify whether this requires authentication, has rate limits, returns structured data, or has any side effects. For a tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple tool with no parameters. However, it could be slightly more front-loaded with additional context about when to use it.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema), the description is minimally adequate but incomplete. It states what the tool does but lacks behavioral context (e.g., authentication needs, return format) and usage guidelines. With no annotations or output schema, the description should provide more complete operational information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's purpose. This meets the baseline for tools without parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose as '获取测试用例管理功能的限制说明' (Get limitation descriptions for test case management functionality). It uses a specific verb ('获取' - get) and resource ('测试用例管理功能的限制说明' - limitation descriptions for test case management), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'apifox_api_info' or 'apifox_project_info', which appear to provide different types of information.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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's no mention of prerequisites, context, or comparisons to sibling tools like 'apifox_check_access' or 'apifox_import_export_info'. The user must infer usage based on the purpose alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
All tools are information retrieval functions with overlapping purposes focused on getting metadata or restriction details about different Apifox features. An agent would struggle to choose between them as they all serve similar descriptive roles rather than distinct operational actions. The boundaries are unclear, with tools like apifox_api_info and apifox_project_info potentially covering similar ground.
Tool names follow a highly consistent pattern throughout: all use snake_case with the prefix 'apifox_' followed by a feature name and '_info' or '_access' suffix. This predictable structure makes it easy to understand the naming convention and anticipate tool purposes based on their names.
With 9 tools, the count is reasonable for a documentation/metadata server, but it feels borderline heavy given the narrow scope. All tools serve similar informational purposes rather than covering a broad operational domain, making the set feel somewhat redundant rather than comprehensive for a typical MCP server's action-oriented expectations.
The tool surface is severely incomplete for what appears to be an API testing/management domain. While it provides metadata about various Apifox features, it lacks any operational tools for actually using those features (e.g., creating projects, running tests, managing environments). This creates significant gaps that would prevent agents from performing meaningful work beyond information lookup.
Maintenance
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
Run your website's AI support agent from Claude, Cursor or any MCP client. Manage the knowledge base, edit agent instructions, read conversations and leads, reply live to visitors, and check plan usage. 54 tools, OAuth sign-in, no API key. Free with every Asyntai account: https://asyntai.com/documentation/mcp/
AI-callable tools for API mocking, testing, monitoring, security, and automation.
Access the GitHub API, enabling file operations, repository management, search functionality, and…
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceThis server acts as a Message Communication Protocol (MCP) service for integrating Apifox and Cursor, enabling OpenAPI interface implementation through AI-driven interaction.7
- AlicenseAqualityCmaintenanceEnables AI assistants to fetch and understand API endpoint definitions from Apifox projects in real-time. Supports retrieving complete API specifications including request methods, parameters, headers, and response schemas to improve development efficiency and code generation quality.1214MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI tools to search and explore API documentation from Apidog projects or OpenAPI/Swagger specifications, providing endpoint details, schemas, and project statistics through natural language queries.1,2361ISC
- AlicenseNot gradedqualityAmaintenanceEnables LLMs to manage Apifox API projects, including listing, creating, updating, and deleting API endpoints and schemas via natural language.30MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/guocong-bincai/Apifox_mcp_pro'
If you have feedback or need assistance with the MCP directory API, please join our Discord server