Skip to main content
Glama

How to connect Petpooja to Claude Code, ChatGPT and any AI agent

Yes, Claude, ChatGPT and other AI agents can work in your Petpooja account. Petpooja has no official app in ChatGPT or Claude. Cotlet.dev connects your own signed-in Petpooja account to any AI agent, so you ask in plain words and the AI checks your sales reports and updates your menu for you.

What you can ask

Show me yesterday's total sales for my Koramangala outlet and the top 5 selling items.

Change the price of Paneer Butter Masala to ₹320 and Butter Naan to ₹60 on the dine-in menu.

Compare this Saturday's sales with last Saturday, split by dine-in, takeaway and delivery.

Mark Mutton Biryani as out of stock for the rest of today.

Add Mango Lassi at ₹120 under Beverages, then tell me which category sold the least last week.

Related MCP server: shopify-store-mcp

Connect in 2 minutes

Get your API key at https://cotlet.dev/app and export it as COTLET_API_KEY.

Claude Code

claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"

ChatGPT

Settings → Apps → add connector URL https://cotlet.dev/mcp/v1, then sign in with Cotlet.dev. No API key needed.

Cursor

Copy .cursor/mcp.json from this repo into your project:

{
  "mcpServers": {
    "cotlet": {
      "url": "https://cotlet.dev/mcp/v1",
      "headers": {
        "Authorization": "Bearer ${COTLET_API_KEY}"
      }
    }
  }
}

Run it locally (stdio)

This repo is a real MCP server. It speaks MCP over stdio, lists its Petpooja tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.

{"mcpServers":{"petpooja":{"command":"uvx","args":["petpooja-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}

Or with Docker:

docker build -t petpooja-mcp .
docker run -i --rm -e COTLET_API_KEY petpooja-mcp

Tools: petpooja_guide, petpooja_status, petpooja_open, petpooja_read, petpooja_click, petpooja_type, petpooja_close. Without COTLET_API_KEY a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".

Command line

Python 3.10+, nothing else to install. From PyPI:

pip install petpooja-mcp        # or run it once: uvx petpooja-mcp connect
petpooja-mcp connect

Or straight from this repo:

export COTLET_API_KEY="your-key"
python3 petpooja_agent.py connect   # ready config for Claude Code, Cursor, ChatGPT
python3 petpooja_agent.py status    # is Petpooja ready in your Cotlet.dev account
python3 petpooja_agent.py guide     # Petpooja screens and sign-in link
python3 petpooja_agent.py read      # open Petpooja, read the page, close the browser
python3 petpooja_agent.py tools     # list Cotlet.dev tools
python3 petpooja_agent.py serve     # start the stdio MCP server (same as no argument)

Questions from Petpooja users

Does Petpooja have an API?

Petpooja publishes no public API documentation or self-serve API keys for restaurants. Its integrations go through a partner contact with Petpooja. You don't need that to use AI: Cotlet.dev works in your own signed-in Petpooja account, so your AI agent can check sales reports and update menu items directly.

How do I connect Petpooja to ChatGPT?

Add Cotlet.dev as an app in ChatGPT (Settings → Apps, connector URL https://cotlet.dev/mcp/v1), sign in to Petpooja once in your Cotlet.dev Cloud Browser, and ask ChatGPT in plain words. No code and no Petpooja API key.

Is there a way to use Claude with Petpooja?

Yes. In Claude Code run the one-line claude mcp add command above; in the Claude app add https://cotlet.dev/mcp/v1 as a custom connector. Claude then works in your own Petpooja account.

Is there a Petpooja MCP server?

Petpooja has no official MCP server. Cotlet.dev is a hosted MCP server that works in Petpooja for you, 24/7, with Claude, ChatGPT, Cursor, Codex, n8n, Make and Zapier.

Find it on

Also works with


More: https://cotlet.dev/integrations/petpooja-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=petpooja

Start free: https://cotlet.dev/signup?app=petpooja&utm_source=github&utm_medium=readme&utm_campaign=petpooja

Available Tools

7 tools
petpooja_clickB

Click a numbered element on the current Petpooja page.

Inputs: element (required).

petpooja_closeA

Close the Petpooja browser session when the work is done, so credits stop running.

Inputs: no named parameters.

petpooja_guideA

How to work in Petpooja (check sales reports and update menu items): its screens and the sign-in link. Call this first.

Inputs: task.

petpooja_openB

Open a Petpooja page in your signed-in Cloud Browser (default https://billing.petpooja.com) to work with check sales reports and update menu items.

Inputs: url.

petpooja_readA

Read the current Petpooja page: its text and numbered buttons, links and fields.

Inputs: element.

petpooja_statusA

Check that your Cotlet.dev account and Petpooja are ready: account, credits and Petpooja connection.

Inputs: no named parameters.

petpooja_typeC

Type text into a numbered field on the current Petpooja page.

Inputs: text (required), element (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: session lifecycle (status/open/close), onboarding (guide), and page interaction (read/click/type). There is no overlap that would cause an agent to misselect between tools.

    Naming Consistency4/5

    All tools use the same petpooja_ prefix and snake_case, making the set predictable. Minor inconsistency: most names are verbs (open, read, click, type, close), while guide and status are nouns.

    Tool Count5/5

    Seven tools is a well-scoped set for a browser-automation server. Every tool earns its place across session setup, guidance, and basic page interaction.

    Completeness4/5

    The set covers the essential browser lifecycle and interaction primitives: open a page, read it, click, type, and close. More advanced interaction helpers (scroll, wait, screenshot, or explicit navigation) are absent but can mostly be worked around via open/read.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to manage WooCommerce stores, including products, orders, customers, categories, coupons, attributes, variations, order notes, refunds, reports, payment gateways, meta data, reviews, settings, data, posts, and system status through natural language.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to manage Shopify stores via natural language, with tools for products, orders, inventory, customers, and analytics.
      11 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to query a retail and food-service point-of-sale database through predefined business tools for sales summaries, top products, margins, stagnant inventory, cash reconciliation, and optional stock adjustments, returning formatted markdown answers.
      MIT