---
title: "Connect Getgrist to Wikipedia - APIANT.ai"
description: "When \"New record\" fires in Getgrist, your agent runs \"Find pages by search term\" in Wikipedia."
canonical: "https://apiant.ai/connect/getgrist-to-wikipedia"
---

# Connect Getgrist to Wikipedia

When **New record** fires in [Getgrist](https://apiant.ai/connections/getgrist), your agent runs **Find pages by search term** in [Wikipedia](https://apiant.ai/connections/wikipedia). Describe the whole flow and it is built, tested on every scenario and kept running.

Getgrist **1** trigger Getgrist **6** actions Wikipedia **8** actions

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

## What do you want Getgrist and Wikipedia 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 Getgrist can start in Wikipedia

- When **New record** in Getgrist then **Find pages by search term** in Wikipedia
- When **New record** in Getgrist then **Get page HTML** in Wikipedia

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 Getgrist and Wikipedia

## Triggers and actions 1 trigger · 14 actions

- Trigger

**New record**

Polling trigger: fires when a new record appears in a table.

- Action

**Delete record**

Delete records of a table.

- Action

**Get document**

Describe a document.

- Action

**List columns**

List columns in a table.

- Action

**List records**

Fetch records from a table.

- Action

**List tables**

List tables in a document.

- Action

**List workspaces**

List workspaces and documents within an org.

- Action

**Convert HTML to wikitext**

Convert rendered HTML back into raw wikitext markup.

- Action

**Convert wikitext to HTML**

Convert raw wikitext markup into rendered HTML.

- Action

**Find pages by search term**

Search for pages matching a search term and return matching titles with excerpts.

- Action

**Get citation data**

Get formatted citation data for an article in a given citation style.

- Action

**Get page HTML**

Get the latest rendered HTML content of a page.

- Action

**Get page summary**

Get a page's title, extract/description, thumbnail, and basic metadata.

- Action

**Get random page**

Get a random page's summary from the wiki.

- Action

**List page media**

List the media files (images, audio, video) used on a page.

## Each app on its own

- [ **Getgrist** Spreadsheet-database platform for building data apps with relational tables, forms, and a REST API for...](https://apiant.ai/connections/getgrist)
- [ **Wikipedia** The MediaWiki Action API is the read and write interface behind Wikipedia and other MediaWiki wikis.](https://apiant.ai/connections/wikipedia)

Reviews

## What our customers say

## More from Getgrist

- [ **Getgrist to Anthropic** Anthropic builds Claude, a family of large language models.](https://apiant.ai/connect/getgrist-to-anthropic)
- [ **Getgrist to Google Address Validation** API that validates, standardizes, and geocodes mailing addresses for accuracy.](https://apiant.ai/connect/getgrist-to-google-address-validation)
- [ **Getgrist to Short Menu** Short Menu is a tool for creating short links.](https://apiant.ai/connect/getgrist-to-short-menu)
- [ **Getgrist to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/getgrist-to-hubspot)
- [ **Getgrist to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/getgrist-to-salesforce)
- [ **Getgrist to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/getgrist-to-slack)

## More into Wikipedia

- [ **HubSpot to Wikipedia** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-wikipedia)
- [ **Salesforce to Wikipedia** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-wikipedia)
- [ **Slack to Wikipedia** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-wikipedia)
- [ **Google Sheets to Wikipedia** Google Sheets](https://apiant.ai/connect/google-sheets-to-wikipedia)
- [ **Gmail to Wikipedia** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-wikipedia)
- [ **Google Calendar to Wikipedia** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-wikipedia)

Questions

## Getgrist and Wikipedia, answered

###

### What can start an automation from Getgrist?

Any of Getgrist's 1 trigger in the catalog, including New record. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in Wikipedia when something happens in Getgrist?

Any of Wikipedia's 8 actions, including Convert HTML to wikitext, Convert wikitext to HTML, Find pages by search term and Get citation data. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Wikipedia to Getgrist?

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

###

### Do I have to build a connector for Getgrist or Wikipedia?

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 Getgrist and Wikipedia 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.
