pruva-mcp
Remote MCP server for Pruva, enabling AI assistants to manage products, features, and documents over HTTPS with OAuth authentication.
README
pruva-mcp
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.
Endpoint
https://mcp.pruva.ai/api/mcp
Authentication 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.
Setup
Claude Code
claude mcp add --transport http pruva https://mcp.pruva.ai/api/mcp
Claude Desktop
In claude_desktop_config.json:
{
"mcpServers": {
"pruva": {
"type": "http",
"url": "https://mcp.pruva.ai/api/mcp"
}
}
}
Cursor
In .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"pruva": {
"url": "https://mcp.pruva.ai/api/mcp"
}
}
}
Other clients
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.
Tools
| Tool | Purpose |
|---|---|
pruva_list_products |
List your products |
pruva_get_product |
Get a product's details |
pruva_list_features |
List a product's features |
pruva_get_feature |
Get a feature's details |
pruva_create_feature |
Create a feature |
pruva_update_feature |
Update a feature's title or status |
pruva_list_documents |
List a product's documents |
pruva_get_document |
Get a document's content |
pruva_create_document |
Create a document |
pruva_update_document |
Update a document's content or path |
pruva_search_documents |
Search documents by content |
pruva_list_feature_relations |
List feature relations |
pruva_ask |
Ask the Pruva analysis agent a read-only question |
Resources
| URI Template | Returns |
|---|---|
pruva://products/{productId} |
Product details |
pruva://products/{productId}/features |
Features list |
pruva://products/{productId}/relations |
Feature relations |
pruva://products/{productId}/documents |
Documents list |
pruva://products/{productId}/documents/{path} |
Single document content |
Security
- 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.
Links
- Pruva
- pruva-cli — terminal companion
- Model Context Protocol
Issues
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.