Google Meet MCP connector

Two steps. In Elaichi, choose Google Meet and connect it, which opens Google's own sign-in screen where you approve access with your Google account; there is no client ID or secret to generate and no application to register. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Sign in when Claude asks and your Google Meet meetings, transcripts, and participant lists are available.

Yes. Once Google Meet is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Google Meet once and every client you use can reach it.

With Google Meet connected, an agent can look up past meetings, read their transcripts line by line, see who joined and when, and check people in your Google Meet directory. That means it can summarize a call, pull out the action items, tell you who attended a review, or find the meeting where a decision was made. This connector reads Google Meet; it does not schedule, change, or delete meetings.

No. Access follows the person who signed in, so an agent working through your Google Meet connection sees only the meetings, transcripts, and participant lists your own Google account can already see. Elaichi can narrow that further, for example hiding transcripts and leaving only attendance, but it can never widen it beyond what Google Meet grants you.

Yes. One person connects Google Meet in Elaichi and shares it with a team, and nobody else ever handles a Google credential or approves anything in Google. Each teammate still signs in to Elaichi as themselves, so every question asked of Google Meet is logged under the name of the person who asked it.

This connector only reads Google Meet: it lists meetings, transcripts, participants, and users, and cannot create, change, or delete anything, so there is nothing destructive to worry about. Restrictions in Elaichi still apply per action, so you can, for example, allow attendance lookups but block transcripts. A blocked action is never advertised to the AI client, so no prompt can reach it.

Offboarding a person in Elaichi ends their access to Google Meet through every connected client at once. If they had shared their Google Meet connection with a team, it keeps working for everyone else on that team. Disconnecting Google Meet once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.

Yes. Google Meet is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

Yes. Both let Claude, ChatGPT or Cursor use Google Meet. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Google Meet call.

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Google Meet: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.