Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@pruva-mcp list my Pruva products"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Remote Model Context Protocol server for Pruva. Connect your AI assistant to your Pruva products, features, and documents over HTTPS — no install, no API keys.
https://mcp.pruva.ai/api/mcpAuthentication is handled by your MCP client over OAuth 2.1 against the Pruva backend. The first tool call opens a browser tab where you approve access; the token is then stored by your client and reused.
Related MCP server: productplan-mcp-server
claude mcp add --transport http pruva https://mcp.pruva.ai/api/mcpIn claude_desktop_config.json:
{
"mcpServers": {
"pruva": {
"type": "http",
"url": "https://mcp.pruva.ai/api/mcp"
}
}
}In .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"pruva": {
"url": "https://mcp.pruva.ai/api/mcp"
}
}
}Any MCP client that speaks Streamable HTTP with OAuth 2.1 works. Point it at the endpoint — discovery happens automatically via /.well-known/oauth-protected-resource.
Tool | Purpose |
| List your products |
| Get a product's details |
| List a product's features |
| Get a feature's details |
| Create a feature |
| Update a feature's title or status |
| List a product's documents |
| Get a document's content |
| Create a document |
| Update a document's content or path |
| Search documents by content |
| List feature relations |
| Ask the Pruva analysis agent a read-only question |
URI Template | Returns |
| Product details |
| Features list |
| Feature relations |
| Documents list |
| Single document content |
No long-lived secrets to manage — auth runs through the standard OAuth flow in your browser.
Tokens are stored by your MCP client, not by this server.
Every API call is re-validated against the Pruva backend.
Revoke access any time from your Pruva account settings.
pruva-cli — terminal companion
MIT
This server cannot be deployed
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Remote MCP server for creating and selling digital products via MoneMee. It lets AI agents create, publish, and sell digital products such as e-books, AI prompt packs, software, courses without a human touching a dashboard. Docs: https://monemee.com/mcp Sign up on Monemee to get a token.
