nobrokerhood-mcp
Enables pre-approving deliveries and visitors at your gate via the NoBrokerHood resident app, so you or an LLM can automate gate access.
README
nobrokerhood-mcp
A CLI and MCP server for pre-approving deliveries and visitors at your gate via the NoBrokerHood resident app — so you (or an LLM on your behalf) can say "let the Zepto guy in" instead of opening the app.
This is an unofficial client. It is not affiliated with or endorsed by NoBrokerHood.
Install
pip install git+https://github.com/smtchahal/nobrokerhood-mcp.git
(Not yet published to PyPI.)
Authentication
There's no OAuth flow — the client authenticates the same way the mobile app does, with a captured session. Proxy the NoBrokerHood app once (e.g. with mitmproxy or Charles Proxy) and pull the following out of a request:
NBH_USER_ID,NBH_SOCIETY_ID,NBH_DEVICE_ID— from theuserId/societyId/deviceIdrequest headersNBH_REMEMBER_ME,NBH_JSESSIONID— from theremember-me/JSESSIONIDcookies
Copy .env.example to .env and fill these in (or export them directly — the client reads plain environment variables, nothing loads .env for you).
These sessions are long-lived but not eternal; if you start getting auth errors, recapture them.
CLI usage
nbh pre-approve zepto --apartment-id <id>
nbh pre-approve dominos --apartment-id <id> --hours 4
nbh pre-approve amazon --apartment-id <id> --out "25/04/2026 23:59" --vehicle TWO_WHEELER
nbh cancel <visit-id> --apartment-id <id>
nbh list --apartment-id <id>
nbh visits --apartment-id <id>
nbh user-info
Run nbh <command> --help for the full flag list. ~100 delivery brands (Zepto, Blinkit, Swiggy, Dominos, Amazon, couriers, home services, ...) have built-in default approval windows — see nobrokerhood.companies.KNOWN_COMPANIES. Unknown brands default to a 1-hour window.
MCP server
Registers six tools: pre_approve, cancel_visit, list_expected, list_visits, get_user_multiprofile_info, known_companies.
Add to your MCP client config (e.g. .mcp.json for Claude Code):
{
"mcpServers": {
"nobrokerhood": {
"command": "nobrokerhood-mcp",
"env": {
"NBH_USER_ID": "...",
"NBH_SOCIETY_ID": "...",
"NBH_DEVICE_ID": "...",
"NBH_REMEMBER_ME": "...",
"NBH_JSESSIONID": "..."
}
}
}
}
This runs the server over stdio with no authorization layer — appropriate for local use, where the MCP client is the only thing that can spawn the process.
Self-hosting over HTTP
If you want to expose this server remotely (e.g. behind a tunnel, for use from claude.ai instead of a local client), nobrokerhood.server exposes a build_server() factory instead of a fixed server instance, so you can bring your own authorization:
from nobrokerhood.server import build_server
mcp = build_server(
host="0.0.0.0",
port=8000,
streamable_http_path="/mcp",
token_verifier=my_token_verifier, # implement mcp.server.auth.provider.TokenVerifier
auth=my_auth_settings, # mcp.server.auth.settings.AuthSettings
)
mcp.run(transport="streamable-http")
This package intentionally does not ship an authorization implementation — how you authenticate callers to your server is a separate concern from how this client authenticates to NoBrokerHood.
Library usage
from nobrokerhood import NobrokerhoodClient
client = NobrokerhoodClient() # reads NBH_* env vars
client.pre_approve("Zepto", apartment_id="...")
See nobrokerhood/client.py for the full API (pre_approve, cancel_visit, list_expected, list_visits, register_device, get_user_multiprofile_info, get_home_content).
Development
pip install -e ".[dev]"
pre-commit install
pytest
License
MIT — see LICENSE.
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.