MCP.so
登录

AppDog MCP Server

@rodolphebarbanneau

基本信息

分类

其他

许可证

MIT

传输方式

stdio

作者

rodolphebarbanneau

关于 AppDog MCP Server

Compose and generate effortlessly MCP servers from any OpenAPI specifications

AppDog MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块,请前往代码仓库查看安装说明。

代码仓库

AppDog MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is AppDog?

AppDog is a Python package that automatically generates fully typed async API clients and ready-to-use MCP (Model Context Protocol) servers from any OpenAPI specification. It simplifies working with OpenAPI-based APIs and managing multiple API clients in a single project with version locking.

How to use AppDog?

Install with uv add appdog, then use the CLI: initialize a project with appdog init, add an API client with appdog add NAME --uri URI, list clients with appdog list, show details with appdog show, and generate an MCP server with appdog mcp install. Generated clients are imported directly (e.g., import appdog.petstore) and can be used with async context managers.

Key features of AppDog

  • Generates fully typed async Python clients from OpenAPI specs
  • Creates ready-to-use MCP servers for API integrations
  • Manages multiple API clients with version locking
  • Simple CLI for adding, removing, and managing APIs
  • Supports custom authentication via environment variables or headers
  • Allows filtering methods and tags during client generation

Use cases of AppDog

  • Generate a typed client and MCP server for a public REST API in minutes
  • Compose multiple OpenAPI-based APIs into a single MCP server for AI agents
  • Quickly prototype API integrations with Claude Desktop via MCP

常见问题

1

What runtime does AppDog require?

AppDog is a Python package installable via `uv add appdog` and supports Python 3.8+ (as shown on PyPI).

2

What MCP transports does AppDog support?

AppDog supports both `stdio` and `sse` transports, selectable with `--transport` when running `appdog mcp run`.

3

Are there known limitations?

Yes. Claude Desktop does not yet handle resource templates (resources with parameters). Windows users must manually edit the generated Claude configuration for MCP install (see related issue).

4

How does AppDog store project configuration?

Project settings and API client specifications are stored in an `apps.yaml` file, with a lock file `apps.lock` containing specs and hashes.

5

How can I manage API credentials?

Credentials are configured via environment variables in the format `APPDOG_<CLIENT_NAME>_TOKEN` or `APPDOG_<CLIENT_NAME>_API_KEY`.

评论

其他 分类下的更多 MCP 服务器