---
title: "Connect PyPI to Sensible - APIANT.ai"
description: "When \"New package\" fires in PyPI, your agent runs \"Add document type\" in Sensible."
canonical: "https://apiant.ai/connect/pypi-to-sensible"
---

# Connect PyPI to Sensible

When **New package** fires in [PyPI](https://apiant.ai/connections/pypi), your agent runs **Add document type** in [Sensible](https://apiant.ai/connections/sensible). Describe the whole flow and it is built, tested on every scenario and kept running.

PyPI **2** triggers PyPI **2** actions Sensible **6** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want PyPI and Sensible to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

### Set it up in your client

### Claude Code

Run this in the directory you want to work in.

`claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

Example flows

## What PyPI can start in Sensible

- When **New package** in PyPI then **Add document type** in Sensible
- When **New release** in PyPI then **Classify document** in Sensible

Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.

Everything your agent can do with PyPI and Sensible

## Triggers and actions 2 triggers · 8 actions

- Trigger

**New package**

Fires when a new package is published to PyPI, via the site-wide newest-packages RSS feed (/rss/packages.xml).

- Trigger

**New release**

Fires when a watched PyPI package publishes a new release, via that package's release RSS feed (/rss/project/{name}/releases.xml).

- Action

**Get package**

Look up a PyPI package's latest metadata, release list, and project URLs.

- Action

**Get release**

Look up metadata for one specific version of a PyPI package, including its files and known vulnerabilities.

- Action

**Add document type**

Creates a new document type in your Sensible account.

- Action

**Classify document**

Classifies a document into one of the document types defined in your Sensible account and returns the matching document type.

- Action

**Extract Document**

Starts an asynchronous extraction of structured data from a document at a URL, using the extraction queries in one of your Sensible document types. Returns the extraction id; retrieve the results with Get extraction once the status is COMPLETE, or have Sensible post them to a webhook.

- Action

**Get document type**

Get a document type's name, creation date and settings by its id.

- Action

**Get extraction**

Retrieves an extraction by its id, including its status and, once complete, the extracted document data.

- Action

**List document types**

Lists all document types in your Sensible account.

## Each app on its own

- [ **PyPI** Package metadata, release history and download files for any Python package published on the Python Package...](https://apiant.ai/connections/pypi)
- [ **Sensible** Sensible is an API that transforms documents into structured data](https://apiant.ai/connections/sensible)

Reviews

## What our customers say

## More from PyPI

- [ **PyPI to Google Chat** Google Chat is a communication software developed by Google built for teams that provides direct messages...](https://apiant.ai/connect/pypi-to-google-chat)
- [ **PyPI to Hailer** Hailer is a tool that helps people be more productive and organized together.](https://apiant.ai/connect/pypi-to-hailer)
- [ **PyPI to Hyperstack Certificates** Hyperstack helps you easily create and manage digital certificates & badges for your events or courses.](https://apiant.ai/connect/pypi-to-hyperstack-certificates)
- [ **PyPI to IP2Location** IP geolocation and intelligence. Look up location, network, proxy, and security data for any IP address...](https://apiant.ai/connect/pypi-to-ip2location)
- [ **PyPI to Meisterplan** Meisterplan is a project portfolio management tool that focuses on resource management at the portfolio...](https://apiant.ai/connect/pypi-to-meisterplan)
- [ **PyPI to Window Sticker** Original factory Monroney label PDF and full spec decode by VIN](https://apiant.ai/connect/pypi-to-window-sticker)

## More into Sensible

- [ **Google Drive to Sensible** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-sensible)
- [ **HubSpot to Sensible** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-sensible)
- [ **Salesforce to Sensible** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-sensible)
- [ **Slack to Sensible** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-sensible)
- [ **Google Sheets to Sensible** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-sensible)
- [ **Gmail to Sensible** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-sensible)

Questions

## PyPI and Sensible, answered

###

### What can start an automation from PyPI?

Any of PyPI's 2 triggers in the catalog, including New package and New release. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in Sensible when something happens in PyPI?

Any of Sensible's 6 actions, including Add document type, Classify document, Extract Document and Get document type. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Sensible to PyPI?

Sensible has no triggers in the catalog today, so automations start in PyPI. If you need the other direction, ask: your agent reads Sensible's API documentation and adds it.

###

### Do I have to build a connector for PyPI or Sensible?

No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.

###

### Can my AI client use PyPI and Sensible without building an automation?

Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.

###

### What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

###

### Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.
