stellary-mcp

Stellary remote MCP

Stellary is an AI-native project piloting SaaS. This skill teaches an agent to use the hosted Model Context Protocol server. The application and server implementation are proprietary and are not distributed from this repository.

• Product site: https://stellary.co
• MCP docs: https://stellary.co/docs/mcp/
• Official registry id: io.github.Anymfah/stellary-project-management
• Endpoint: https://api.stellary.co/mcp
• Transport: Streamable HTTP (GET/POST, stateless; no Mcp-Session-Id required)
• Auth: OAuth 2.1 with PKCE and refresh-token rotation; personal access tokens remain available for compatible clients
• Not supported: local npx/stdio servers or Dockerized copies of the backend

If Stellary MCP tools are already available in this session, use them. Do not invent a local server or wrapper package.

Connect when tools are missing

1. Configure the client with https://api.stellary.co/mcp and start its OAuth connection flow.
2. Ask the user to sign in to Stellary, choose a workspace, and authorize Me, one or more active agents, or both.
3. If several identities were authorized, call stellary_list_identities and pass the selected opaque reference in actingAs. Never invent or persist an identity reference beyond the connection that returned it.

Claude Code:

claude mcp add stellary \
  --transport streamable-http \
  https://api.stellary.co/mcp

Cursor / JSON clients:

{
  "mcpServers": {
    "stellary": {
      "url": "https://api.stellary.co/mcp"
    }
  }
}

For a client that cannot complete remote OAuth, create a dedicated PAT from Account settings → API tokens. Start with projects:read and pilotage:read, add write scopes only when needed, and keep the secret in the client's secret store. Gemini CLI uses httpUrl (not url) for Streamable HTTP:

{
  "mcpServers": {
    "stellary": {
      "httpUrl": "https://api.stellary.co/mcp",
      "headers": {
        "Authorization": "Bearer ${STELLARY_TOKEN}"
      }
    }
  }
}