Apifox Filter MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_DIR | No | 缓存目录（覆盖默认位置） | |
| OPENAPI_URL | No | OpenAPI 文档 URL（URL 模式必填，也可通过 --openapi-url 命令行参数指定） | |
| PROJECT_DIR | No | 用户项目目录（缓存将放在此目录下） | |
| APIFOX_API_BASE | No | Apifox API 基础地址（私有部署时使用） | https://api.apifox.com |
| REFRESH_ON_MISS | No | 找不到时自动刷新 | true |
| APIFOX_BRANCH_ID | No | 分支 ID | |
| REFRESH_INTERVAL | No | 定时刷新间隔（分钟），0 禁用 | 30 |
| APIFOX_MODULE_IDS | No | 模块 ID 列表（逗号分隔） | |
| APIFOX_PROJECT_ID | No | Apifox 项目 ID（Apifox 模式必填，也可通过 --project-id 命令行参数指定） | |
| APIFOX_ACCESS_TOKEN | No | Apifox 访问令牌（Apifox 模式必填） | |
| MISS_REFRESH_COOLDOWN | No | 自动刷新冷却（秒） | 60 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| smart_search_apiA | 根据自然语言描述智能搜索接口，AI 的首选搜索工具。 核心能力：
使用场景：
优先使用此工具进行语义搜索，再用 get_api_detail 获取详情 |
| search_apiA | 根据 URL 模式搜索接口，这是查找接口的首选工具。 使用场景：
支持的匹配模式：
|
| get_api_detailA | 获取单个接口的完整文档。 使用指引：
|
| list_api_by_tagB | 按标签筛选接口列表 |
| list_api_by_folderA | 按 Apifox 文件夹路径筛选接口列表，支持精确和模糊匹配 |
| list_api_foldersA | 列出所有 Apifox 接口文件夹目录结构 |
| batch_get_apisC | 批量获取多个接口的详细信息 |
| list_all_endpointsA | 列出所有接口的路径和方法（仅返回摘要信息） |
| refresh_cacheA | 刷新接口缓存，从 Apifox 重新获取最新数据 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
The two search tools (smart_search_api and search_api) have overlapping purposes—both find APIs by keywords—though descriptions attempt to differentiate semantic vs URL-pattern search. The 'preferred' vs 'primary' language adds confusion, but other tools are clearly distinct for detail, listing, and cache operations.
Most tools follow a snake_case verb_noun pattern (search_api, get_api_detail, list_api_folders, refresh_cache). Exceptions like smart_search_api and batch_get_apis deviate slightly in form but remain consistent in style and readability.
With 9 tools, the set is well-scoped for an API documentation server, covering search, detail retrieval, listing, filtering, and cache management without unnecessary bloat.
The tool surface fully covers the read-only filtering/retrieval domain: multiple search modes, single/batch detail, tag/folder filters, full endpoint listing, and cache refresh. No significant gaps for the stated purpose.