Put your Librari contract data to work in the AI you already use

Free (1 connector), Pro, Max, Team, and Enterprise plans. No API keys, no config files.

1. Go to Customize › Connectors.
2. Click + then Add custom connector.
3. Enter a name (use Librari) and paste the server URL: https://www.thelibrari.com/api/mcp
4. Click Add, then sign in to Librari and choose Allow access.

To use it in a chat, click + in the composer, choose Connectors, and toggle Librari on. On Team and Enterprise plans, an Owner adds the connector first via Organization Settings › Connectors, then members connect individually.

Plus, Pro, Business, Enterprise, or Education plan, on the web. Developer Mode is in beta. On Plus and Pro, custom connectors are read-only, which is exactly what Librari is.

1. In ChatGPT, open Settings › Apps & Connectors (labeled Connectors on some accounts) › Advanced and turn on Developer Mode.
2. Back in Settings › Apps & Connectors, choose Create (or Add custom connector).
3. Paste the server URL as the MCP Server URL: https://www.thelibrari.com/api/mcp. Set authentication to OAuth, and leave the Client ID and Client Secret fields empty.
4. ChatGPT sends you to Librari, sign in and choose Allow access.
5. In any chat, open the tools menu (+) and turn on Librari.

On Business, Enterprise, or Education: custom connectors are managed by a workspace Owner or Admin on the web. Under Workspace settings › Apps, an admin turns on Developer Mode (enabled per admin), chooses Create, adds Librari with the server URL above and OAuth (leave credentials blank), then Publishes it to the workspace. Members can't add it themselves until an admin publishes it.

If it asks for a Client ID: that only happens when a credential gets typed in by hand. Clear the Client ID and Client Secret fields and connect with the address alone, Librari registers ChatGPT for you.

Connect once in the Gemini web app; it then works on mobile too.

Who can use it: people with Gemini Spark (included with Google AI Ultra) who are 18 or older, in the US, signed in with a personal Google Account (not work or school), with Keep Activity turned on. English only for now.

1. On a computer, go to gemini.google.com.
2. Open Settings & help › Connected Apps (it may sit under Personal Intelligence › Connected Apps).
3. Under Custom apps for Spark, click Add a custom app.
4. Enter the server URL, then click Next: https://www.thelibrari.com/api/mcp
5. Sign in to Librari and approve. Librari registers itself automatically, so the Advanced features fields stay empty.

For developers using Gemini from the terminal. Add this to ~/.gemini/settings.json (or your project's .gemini/settings.json). The key librari is the connector's name, you can change it if you prefer:

{
  "mcpServers": {
    "librari": {
      "httpUrl": "https://www.thelibrari.com/api/mcp"
    }
  }
}

Restart Gemini CLI and run /mcp to authorize in your browser and confirm the connection.

Add this to ~/.cursor/mcp.json (global) or a project's .cursor/mcp.json. The key librari is the connector's name, you can change it if you prefer:

{
  "mcpServers": {
    "librari": {
      "url": "https://www.thelibrari.com/api/mcp"
    }
  }
}

Or in Cursor Settings › Tools & MCP (older versions: Settings › Features › MCP), choose New MCP Server, give it the name Librari, and paste the URL. A green dot means you're connected.

Run this in your terminal (librari is the name you're giving the connector):

claude mcp add --transport http librari https://www.thelibrari.com/api/mcp

Then run /mcp inside a session to finish the OAuth sign-in.

Point your client at the server URL and authenticate with OAuth 2.0. When asked for a name, use Librari. No API keys needed, signing in is all it takes:

https://www.thelibrari.com/api/mcp

Librari's MCP server exposes read-only tools for searching and retrieving contract data.