Skip to main content

Peliqan

Connect Gripp to Claude with MCP

Recent videos

Peliqan data platform

All-in-one Data Platform

Built-in data warehouse, superior data activation capabilities, and AI-powered development assistance.

Connect Gripp to Claude, ChatGPT, Cursor or any MCP-compatible AI assistant in minutes with Peliqan’s no-code Peliqan MCP server. In this tutorial, you enable the Gripp MCP server in Peliqan, so your AI can query live Gripp data – projects, hours, quotes, invoices, purchasing and leave – without manual exports or API setup.

How to connect Gripp to Claude

  1. 1First, connect Gripp in Peliqan. Add the Gripp connector and sign in once. Peliqan then stores your credentials and keeps the data in sync.
  2. 2Next, add Peliqan to Claude. In Claude, go to Settings → Connectors → Add custom connector. Give it a name, paste https://mcp.eu.peliqan.io/mcp as the URL, click Add, then log in and approve. ChatGPT, Cursor, Gemini and other MCP clients work the same way: add the same endpoint in their connector or MCP settings.
  3. 3Finally, just ask. Question your Gripp data in plain language, and your AI answers from your own data.

What you can do with Gripp + AI

  • Ask questions about your Gripp data in plain English, then get live answers in your AI chat
  • Explore projects, hours, tasks, task phases, costs, quotes, quote phases, invoices, payments, contracts, purchase invoices, purchase orders, purchase payments, products, companies, contacts, employees, employment contracts, absence requests, yearly leave budgets, departments, ledger accounts and journal entries without exporting a single CSV
  • Combine Gripp with the other tools you connect through Peliqan, all in one conversation
  • Let your AI draft the follow-up: the summary, the note or the email, written from the numbers it just read

Example prompts once Gripp MCP is enabled

  • “Which projects are over their hour budget, and by how much?”
  • “What is the margin per project once hours, costs and purchase invoices are counted?”
  • “Which quotes are older than 30 days and still open, and what amount is on the table?”

About the Gripp MCP server

Model Context Protocol (MCP) is the open standard that lets AI assistants work with external tools and data. In short, the Peliqan Gripp MCP server is a hosted, MCP-compliant endpoint that exposes your Gripp data to AI clients such as Claude, ChatGPT, Cursor and Gemini. It covers 31 tables your AI can read. As a result, you install nothing and maintain nothing on your side. Because Peliqan holds your Gripp connector login rather than your AI, access stays governed and secure, and questions are answered from the synced copy in your Peliqan data warehouse.

Works with Claude, ChatGPT, Cursor and more

The Peliqan Gripp MCP connector works with Claude, Claude Code, ChatGPT, Gemini, Cursor and VS Code (Copilot), as well as any other MCP-compatible client. As a result, you can switch AI tools whenever you like. To learn more, visit the Peliqan MCP server page, or browse all Peliqan connectors.

Ready to connect Gripp to Claude, ChatGPT or Cursor? Get started with Peliqan.

FAQs

It is a hosted, MCP-compliant endpoint that exposes your Gripp data to AI clients such as Claude, ChatGPT and Cursor. You connect Gripp once in Peliqan and point your AI client at a single URL, so there is nothing to install or host on your side.

No. Connecting Gripp is a sign-in, and adding the endpoint to your AI client is a paste. There is no server to host, no config file to hand-edit and no API keys to manage.

Questions are answered from the synced copy in your Peliqan data warehouse rather than by calling Gripp for every request, so ordinary reporting questions do not consume your Gripp API quota.

Not today. The Peliqan Gripp connector is read only: your AI can read 31 tables and answer from them, but it cannot change anything in Gripp. It can still draft the note, the summary or the email for you to send.

Get instant access to all your company data

Connect 300+ sources, serve any BI tool, and give every AI agent one governed endpoint to read, and write back where the app supports it.