# Mintlify MCP connector

The Mintlify connector lets Claude, ChatGPT, Cursor and other AI clients publish documentation updates, preview changes, hand rewrites to the Mintlify agent, and review reader feedback, searches and page views, all inside each person's own access.

Source: https://elaichi.ai/connectors/mintlify/

## Facts

| | |
| --- | --- |
| Application | Mintlify |
| Category | Knowledge Management |
| AI tools | 16 |
| Authentication | Connects with an API key |
| Needs your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent |
| Tools advertised by name | Yes |

## What you can ask once Mintlify is connected

- Summarize this week's Mintlify feedback by page.
- Which Mintlify search queries returned nothing useful?
- Show page views and unique visitors for the API guides.

## Connect Mintlify in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Mintlify.
2. Optionally set Share with, then press Connect.
3. Paste a Mintlify API key. One person generates a token in Mintlify and pastes it once. Everyone else works through Share with, and never sees it.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Mintlify tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Connect Mintlify to Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Connect Mintlify to ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web today. The plugin directory lives at chatgpt.com/plugins.

## Connect Mintlify to Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Connect Mintlify to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Only Read is granted by default, which is not enough to call a Mintlify tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone.

## What teams do with Mintlify through Elaichi

### Publish a docs update and confirm it landed

Documentation. Kick off a Mintlify project update after the latest changes are ready, then check the status by ID a few minutes later instead of refreshing the dashboard.

### Preview a change before it goes live

Documentation. Spin up a Mintlify preview so a reviewer can read the new page as visitors will see it, and share the link in the same conversation.

### Hand a rewrite to the Mintlify agent

Developer Relations. Start a Mintlify agent job to rework a guide, send it follow-up instructions as the draft takes shape, and check on the job until it is done.

### Find the pages readers are struggling with

Support. Pull the feedback left on each Mintlify page, group the complaints, and turn the worst offenders into a fix list for the week.

### See what visitors search for and cannot find

Product. List recent Mintlify search queries and documentation searches to spot the features people look for that have no page yet.

### Report on documentation traffic each month

Marketing. Gather Mintlify page views, unique visitors and assistant conversations into a monthly summary of which topics drew the most readers.

## Frequently asked questions

### How do I connect Mintlify to Claude?

Connect Mintlify in Elaichi by pasting in a Mintlify API key from your project settings, then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate. Once connected, Claude can publish updates, create previews and read feedback and analytics from your Mintlify docs.

### Does Mintlify work with ChatGPT and Cursor as well as Claude?

Yes. You connect Mintlify once in Elaichi and the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. Each client signs in over OAuth, so nobody pastes the Mintlify API key anywhere else.

### What can an AI agent actually do with my Mintlify data?

An agent connected to Mintlify can start a documentation update and check whether it finished, create a preview of a change, and hand a rewrite to the Mintlify agent with follow-up instructions. It can also read the content of a page, list reader feedback by page, list search queries, page views, unique visitors and assistant conversations, and ask the Mintlify assistant a question. It cannot delete pages or change project settings, because this connector does not cover those actions.

### Does connecting Mintlify give the AI access to my whole documentation project?

Access follows the Mintlify API key that was used to connect, and the AI can only reach the projects that key can reach. Elaichi can narrow that further, for example by allowing analytics and feedback while blocking updates and previews, but it never widens what the key already allows. Everything the AI does in Mintlify is recorded against the person who asked for it.

### Can my team share one Mintlify connection?

Yes. One person connects Mintlify in Elaichi and shares the connection with a team, and nobody else ever sees or handles the Mintlify API key. Each teammate still signs in as themselves, so the audit log names the actual person who published an update or read the feedback.

### Can I stop an agent from publishing or changing things in Mintlify?

Yes. Restrictions in Elaichi work per action, so you can let people read Mintlify feedback, searches and page views while blocking project updates, previews and agent jobs. A blocked action is never shown to Claude, ChatGPT or Cursor at all, so no prompt can trigger it.

### What happens to a Mintlify connection when someone leaves?

Offboarding a person in Elaichi ends their access to Mintlify at once, across every client they used. If they had shared a Mintlify connection with a team, it keeps working for everyone else. Disconnecting Mintlify once in Elaichi removes it from Claude, ChatGPT, Cursor and every other connected client.

## All 16 Mintlify tools

Every tool below is callable through https://api.elaichi.ai/mcp once Mintlify is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Create a Mintlify project update** (Create). Queue a deployment update for a Mintlify documentation project from its configured deployment branch. Returns statusId that can be used to track update progress.
- **Get single Mintlify project update status by ID** (Get). Get the status of a triggered project update in mintlify by its status ID. Returns: status (queued, in_progress, success, failure), projectId, summary, and logs. Required: id.
- **Create a Mintlify project preview** (Create). Create or update a preview deployment for a specific branch in mintlify. Returns: statusId (for tracking progress) and previewUrl. Required: branch.
- **Create a Mintlify agent job** (Create). Create an agent job in mintlify for a specific project.
- **Get single Mintlify agent job by ID** (Get). Get a mintlify agent job by id within a specific project. Required: id.
- **Create a Mintlify agent job message** (Create). Create a message for a Mintlify agent job. Required: job_id.
- **List all Mintlify feedback** (List). List feedback entries from Mintlify analytics for a given project. Returns an array of feedback records from the analytics data.
- **List all Mintlify feedback by page** (List). List feedback aggregated by page for a Mintlify project. Returns feedback data grouped per page from the analytics dataset.
- **List all Mintlify assistant conversations** (List). List assistant conversations for a Mintlify project. Returns conversation data from the analytics assistant endpoint.
- **List all Mintlify assistant caller stats** (List). List assistant caller statistics for a Mintlify project. Returns analytics data about assistant callers associated with the specified project.
- **List all Mintlify search queries** (List). List search queries recorded in mintlify analytics for a given project. Returns search query data from the analytics dataset.
- **List all Mintlify page views** (List). List page view analytics for a mintlify project. Returns an array of page view records from the analytics data.
- **List all Mintlify unique visitors** (List). List unique visitors analytics for a Mintlify project. Returns visitor data from the analytics endpoint.
- **Create a Mintlify assistant message** (Create). Send a message to the Mintlify assistant for a specific domain. Required: `domain`.
- **List all Mintlify documentation searches** (List). Search Mintlify documentation for a given domain. Returns matching documentation results for the specified domain. Required: domain.
- **Get single Mintlify page content by ID** (Get). Get page content from Mintlify via the discovery API for a given domain. Required: domain.
