What runtime does AppDog require?
AppDog is a Python package installable via `uv add appdog` and supports Python 3.8+ (as shown on PyPI).
@rodolphebarbanneau
Basic information
Compose and generate effortlessly MCP servers from any OpenAPI specifications
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
AppDog is a Python package installable via `uv add appdog` and supports Python 3.8+ (as shown on PyPI).
AppDog supports both `stdio` and `sse` transports, selectable with `--transport` when running `appdog mcp run`.
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).
Project settings and API client specifications are stored in an `apps.yaml` file, with a lock file `apps.lock` containing specs and hashes.
Credentials are configured via environment variables in the format `APPDOG_<CLIENT_NAME>_TOKEN` or `APPDOG_<CLIENT_NAME>_API_KEY`.
MCP Toolbox for Databases is an open source MCP server for databases.
Painless E2E Automation for Mobile and Web

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
🚀 The fast, Pythonic way to build MCP servers and clients.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments