Bring! MCP Server

Bring! MCP Server

MCP server for the Bring! shopping list API, enabling management of shopping lists via natural language.

Category
Visit Server

README

Bring! MCP Server

A small Model Context Protocol server for the Bring! shopping list API.

It exposes Bring! shopping lists to MCP clients such as Claude Desktop, Cursor, or any client that can launch a stdio MCP server.

Available tools

  • get_lists — list all Bring! shopping lists and their UUIDs
  • get_list — fetch one shopping list and show to-buy plus recently completed items
  • add_item — add or update an item on a list
  • remove_item — remove an item from a list
  • complete_item — move an item to Recently Purchased (complete it in Bring!)
  • batch_update — apply bulk operations (ADD, COMPLETE, or REMOVE) to multiple items

Available resources

  • bring://lists — JSON index of every shopping list
  • bring://lists/{listUuid} — JSON contents of a single list (purchase + recently sections)

Clients such as Claude Desktop expose these in their "attach resource" picker.

Available prompts

  • meal_plan — plan a meal and stage missing ingredients on a target list
  • weekly_groceries — draft a balanced weekly grocery list and stage it on a target list

Requirements

  • Python 3.11+
  • A Bring! account
  • Environment variables for your Bring! login

Installation

git clone https://github.com/arithmetic-zz/bring-mcp-server.git
cd bring-mcp-server
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt

Configuration

Set these environment variables:

export BRING_EMAIL="your@email.com"
export BRING_PASSWORD="your-password"

Or create a local .env file:

BRING_EMAIL=your@email.com
BRING_PASSWORD=your-password

.env is ignored by Git. Do not commit real Bring! credentials.

Run

python3 server.py

The server communicates over stdio, so it is normally launched by an MCP client instead of being run interactively.

Claude Desktop integration

{
  "mcpServers": {
    "bring": {
      "command": "python",
      "args": ["/path/to/bring-mcp-server/server.py"],
      "env": {
        "BRING_EMAIL": "your@email.com",
        "BRING_PASSWORD": "your-password"
      }
    }
  }
}

If you use the virtual environment from the installation steps, set command to /path/to/bring-mcp-server/.venv/bin/python.

Development

python3 -m py_compile server.py
python3 -m unittest discover -s tests -v

GitHub Actions runs the same compile and unit-test checks on Python 3.11, 3.12, and 3.13 for pushes and pull requests.

Notes

  • The server keeps one authenticated Bring client per process and reuses the HTTP session.
  • get_list follows the current bring-api response shape: active items are under purchase, completed/recent items under recently.
  • save_item (used by add_item) is an upsert — adding an item that already exists updates it rather than creating a duplicate.
  • complete_item moves items to the "Recently Purchased" list; it does not check items off in place.
  • Known Bring/API/input errors are caught, logged, and translated into short user-facing messages.

License

MIT

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured