# Google Docs MCP connector Connecting Google Docs to Elaichi lets Claude, ChatGPT, Cursor, and any MCP client find, read, create, and edit Google Docs documents as the person who signed in, with every change recorded in an audit log. Source: https://elaichi.ai/connectors/googledocs/ ## Facts | | | | --- | --- | | Application | Google Docs | | Category | Knowledge Management | | AI tools | 6 | | Authentication | Connects over OAuth | | 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 Google Docs is connected - Summarize the documents created in the handbook folder this week. - Draft a launch brief document from last week's meeting notes. - List documents I have edited since Monday with their titles. ## Connect Google Docs in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Google Docs. 2. Optionally set Share with, then press Connect. 3. Approve it in Google Docs. Google Docs's own window opens. Whoever approves it decides what this connection can reach. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Google Docs tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Google Docs 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 Google Docs 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 Google Docs 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 Google Docs 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 Google Docs 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 Google Docs through Elaichi ### Draft a proposal from call notes Sales. After a discovery call, ask the agent to turn your notes into a new proposal document in Google Docs, laid out under the headings your team already uses. ### Keep help articles current after a fix Support. When a workaround changes, ask the agent to find the right Google Docs article and rewrite the affected steps so the desk stops sending customers outdated instructions. ### Turn a brief into a first draft Marketing. Point the agent at a campaign brief in Google Docs and have it create a draft blog post or launch announcement in a new document, ready for a human edit. ### Answer policy questions from the handbook People. Ask what the parental leave policy says and get the answer pulled from the actual handbook document in Google Docs, with the wording as it currently stands. ### Summarize a long meeting document Operations. Drop in a meeting notes document and ask for the decisions and open actions, so people who missed the session get a short readout instead of ten pages. ### Find every document that mentions a vendor Legal. Ask which Google Docs documents reference a particular supplier or contract term, then open the right one and check the clause before renewal. ## Frequently asked questions ### How do I connect Google Docs to Claude? First, connect Google Docs in Elaichi. Google Docs connects over OAuth, so you sign in with your own Google account in the usual pop-up window, and there is no client ID or secret to generate and no application to register. Then open Claude, go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Claude asks you to sign in to Elaichi, and Google Docs is ready to use. ### Does Google Docs work with ChatGPT and Cursor as well as Claude? Yes. Once Google Docs 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 Docs once, and every client you add afterward picks it up without a second setup. ### What can an AI agent actually do with my Google Docs data? With Google Docs connected, an agent can list the documents you have access to, open a specific document and read its full text, create a new document, and make edits to an existing one such as inserting, replacing, or restructuring text. In practice that means asking for a summary of a long document, drafting a proposal from your notes, or updating a help article after a process changes. It works only with documents your Google account can already open. ### Does connecting Google Docs give the AI access to every document in my Google workspace? No. When Google Docs is connected through Elaichi, the agent works inside the access of the person who signed in, so it can only see documents that person could already open in Google Docs, and sharing rules on each document still apply. Elaichi can narrow that access further, for example by allowing reading but not editing, but it can never widen it beyond what the person already has. ### Can my team share one Google Docs connection? Yes. One person connects Google Docs in Elaichi and shares the connection with a team, and nobody else on that team ever handles a credential or signs in to Google separately. Each person still signs in to Elaichi as themselves, so every read or edit in Google Docs is recorded against the individual who made it, not against a shared account. ### Can I stop an agent from changing or overwriting things in Google Docs? Yes. Restrictions in Elaichi work per action, so you can let an agent search and read Google Docs documents while blocking it from creating or editing them. A blocked action is never shown to Claude, ChatGPT, Cursor, or any other client at all, so no prompt, however worded, can reach it. ### What happens to a Google Docs connection when someone leaves? When a person is offboarded in Elaichi, their access to Google Docs through Elaichi ends at once, across every client they used. A shared Google Docs connection keeps working for everyone else on the team, so nobody has to reconnect. If you ever want to remove Google Docs entirely, disconnecting it once in Elaichi removes it from every client at the same time. ## All 6 Google Docs tools Every tool below is callable through https://api.elaichi.ai/mcp once Google Docs is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Google Docs documents** (List). List Google Drive documents (Google Docs files). Returns an array of file objects including id, name, and mimeType, filtered to documents only. - **Get single Google Docs document by ID** (Get). Get a single Google Drive document by id. Returns the full file metadata object. Required: id. - **Create a Google Docs document** (Create). Create a new Google Docs document. Returns the created document object including its document id and title. Required: title. - **List all Google Docs userinfo** (List). Retrieves basic profile information about the authenticated user in Google Calendar. The response includes essential details such as the user's unique identifier (sub), full name (name), first name (given_name), last name (family_name), profile picture URL (picture), and email address (email). - **List all Google Docs document content** (List). Get a Google document by page_id. Returns the full document object including its body content, title, and revision metadata. Required: page_id. - **Google Docs document content batch update** (Update). Apply one or more structured updates to a Google document identified by document_id. Returns the document id and an array of replies corresponding to each applied request. Required: document_id and requests.