# mcp-argocd

> MCP server for the Argo CD REST API. It gives AI assistants 37 tools, 7 resources, and 7 prompts to triage application status, sync, roll back, inspect drift, read logs, and manage ApplicationSets, clusters, projects, and repositories.

MCP server that wraps the Argo CD REST API. Works with Argo CD 3.3+ on any install (OSS, Akuity, OpenShift GitOps). Needs an API token; no cluster access. Built with FastMCP, httpx, and Pydantic.

- **Install**: `uvx mcp-argocd`
- **Version**: 0.1.0
- **Python**: >=3.10
- **License**: MIT
- **Protocol**: MCP 2026-07-28 (MCP 2.0); compatible with 2025-11-25 clients; built on FastMCP 4.x
- **Transport**: stdio (default), streamable-http (recommended for remote), SSE (deprecated by the 2026-07-28 spec)
- **Registry**: `io.github.vish288/mcp-argocd`
- **Required env vars**: `ARGOCD_URL` (base URL including any path prefix), `ARGOCD_TOKEN` (bearer token)
- **Optional env vars**: `ARGOCD_READ_ONLY` (disable writes), `ARGOCD_TIMEOUT` (request timeout), `ARGOCD_SSL_VERIFY` (SSL verification), `ARGOCD_APP_NAMESPACE` (default appNamespace)

## Documentation

- [README](https://github.com/vish288/mcp-argocd#readme): canonical reference for setup, env vars, all 37 tools, 7 resources, 7 prompts
- [PyPI](https://pypi.org/project/mcp-argocd/): install via `pip install mcp-argocd` or `uvx mcp-argocd`
- [GitHub](https://github.com/vish288/mcp-argocd): source code, issue tracker, development setup
- [MCP Registry](https://registry.modelcontextprotocol.io): discover and install MCP servers

## Optional

- [Changelog](https://github.com/vish288/mcp-argocd/releases): per-version release notes
- [MCP Specification](https://modelcontextprotocol.io/docs): protocol spec for tools, resources, and prompts
- [FastMCP](https://github.com/jlowin/fastmcp): Python framework this server is built on
