swagger-codegen-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_tagsA | 列出Swagger文档中所有的API分组（tags）。每次调用都会获取最新的Swagger文档。 |
| list_endpointsA | 列出指定tag下的所有API接口。每次调用都会获取最新的Swagger文档。 |
| list_servicesA | 列出所有可用的API服务及其Swagger URL。用于了解有哪些服务可用。 |
| get_endpoint_detailA | 获取单个API接口的详细信息，包括参数和响应定义。会根据path自动推断对应的服务（如/api/village/...会使用village服务）。 |
| generate_api_codeA | 生成TypeScript API代码。可以按tag生成整个模块，或按单个接口生成。会根据path自动推断对应的服务。 |
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 5 tools
Each tool targets a distinct layer: service discovery, tag listing, endpoint listing, endpoint detail, and code generation. The descriptions make the hierarchy clear, so there is no meaningful overlap between tools.
All tool names follow a consistent snake_case verb_noun pattern: list_* for enumeration, get_ for detail retrieval, and generate_ for code generation. There are no mixed naming styles or vague verbs.
Five tools is well within the ideal scope for a focused Swagger codegen server. Each tool earns its place by contributing one necessary step in the discovery-to-generation workflow.
The set covers the full discovery-to-codegen flow: services, tags, endpoints, endpoint details, and code generation. It lacks whole-service generation and direct schema/model introspection, but agents can work around these by iterating tags or relying on generated code.