# Give your support agent a Google Sheet to read Support agents answer faster when the facts are one lookup away. Keep orders, refund policies, FAQ, and account tiers in a Google Sheet and PasteSheet publishes it as an MCP server your agent reads on every ticket — accurate and read-only, so it can quote a policy or check an order but never edit the record. *Last updated: 2026-07-11 · Source: * ## Key facts - PasteSheet's MCP server exposes three tools — `list_tabs`, `get_schema` and `query_rows` — and is **read-only by design**: an agent can query your sheet but can never modify it. - MCP is an **open protocol** built on JSON-RPC 2.0. A server exposes Resources, Prompts and Tools to any MCP client — Claude, Cursor, ChatGPT, VS Code and Windsurf all speak it. ([source](https://modelcontextprotocol.io/specification/2025-06-18)) - Google's **hosted** Workspace MCP servers cover Gmail, Drive, Calendar, Chat and the People API — **not Sheets**. Its managed Google Cloud MCP servers do not cover Sheets either. ([source](https://developers.google.com/workspace/guides/configure-mcp-servers)) - Google does publish an **open-source** Workspace MCP server (a Gemini CLI extension) that includes Sheets — but you run it yourself, and it still needs a Google Cloud project and OAuth credentials. There is **no hosted, zero-setup** Google Sheets MCP server from Google. ([source](https://github.com/google/mcp)) - Customer data need not be public: private endpoints and API keys start on **Starter ($9/mo)**, and the agent then sends an `Authorization: Bearer` key to read the lookup tabs. ## A lookup table your agent can trust When a ticket comes in, a support agent — human or AI — needs the customer's order, the relevant policy, and the account tier, fast. Keep those in a Google Sheet and PasteSheet exposes them as an [MCP](https://pastesheet.com/guides/google-sheets-mcp) server the agent queries mid-conversation: look up an order by id, match a refund policy, or check whether a plan includes a feature. Because the tools are [read-only](https://pastesheet.com/guides/read-only-google-sheets-mcp), this is safe to put in an automated support loop. The agent reads every row it needs to answer accurately, but it cannot mark an order refunded, bump a tier, or rewrite a policy — your records stay exactly as your team left them. ## What lives in the tabs One tab per lookup, all reachable from the same endpoint: - **Orders** — id, status, items, and ship date the agent looks up per ticket. - **Policies** — refund windows, warranty terms, and SLAs to quote verbatim. - **FAQ** — canned answers to the questions that fill your inbox. - **Account tiers** — plan, limits, and entitlements per customer. ## Connect the support sheet Each endpoint has its own MCP URL. Copy it from the **Connect via MCP** panel and add it as a custom connector in your support agent's runtime: ```json { "mcpServers": { "pastesheet": { "url": "https://pastesheet.com/mcp/sheets/your-endpoint-id" } } } ``` ## Read-only, so it cannot change a record Because the endpoint is **read-only by design**, it is safe to expose publicly or hand to a teammate: consumers can read and query the data but can never change the sheet. And there is **no Google Cloud project, OAuth screen, or service account** to set up — you paste a share URL and get a live API. ## What it costs **Starter — $9/month.** For indie makers shipping a real app. - Endpoints: 10 - Requests: 50,000 / month - Rows per endpoint: 5,000 - Tabs per endpoint: 5 - Rate limit: 300 / minute **MCP is included on the Free plan.** Connect any **public** endpoint over MCP with no Google Cloud project and no credit card. Private endpoints and the account-wide workspace server need a paid plan (from **Starter ($9/mo)**) for the keys and OAuth they authenticate with. Pro adds full-text search and aggregation (`count`, `sum`, `avg`, `group_by`) that your AI agent can call through `query_rows`. ## Frequently asked questions ### Can the support agent change an order or account tier? No. The connector is read-only. The agent can look up an order, quote a policy, or check a tier, but it cannot mark anything refunded, edit a record, or delete a row. ### How does the agent find the right customer? With query_rows — an exact filter on an order id or email, a contains match on a name, or full-text search across the tab. It pulls just the matching row rather than the whole sheet. ### Is customer data exposed publicly? Not if you make the endpoint private on a paid plan. It then requires a bearer key, which the agent sends as an Authorization header; the raw sheet is never public. ### Which agents can use the lookup? Any MCP-compatible client — Claude, Cursor, Claude Code, ChatGPT via the workspace server, or a custom support bot. The same endpoint also works over plain REST for frameworks without MCP. ## Sources - [Model Context Protocol specification](https://modelcontextprotocol.io/specification/2025-06-18) — Model Context Protocol - [Configure the Google Workspace MCP servers](https://developers.google.com/workspace/guides/configure-mcp-servers) — Google - [google/mcp — Google's open-source MCP servers](https://github.com/google/mcp) — Google - [Model Context Protocol (MCP)](https://platform.openai.com/docs/mcp) — OpenAI ## Related use cases - [A Google Sheets Data Source for AI Agents](https://pastesheet.com/use-cases/google-sheets-ai-agent-data-source) — Give any AI agent read-only access to a Google Sheet over MCP. It can list tabs, read the schema, and query rows in plain English — no glue code, no backend. - [A Chatbot Knowledge Base in Google Sheets](https://pastesheet.com/use-cases/google-sheets-chatbot-knowledge-base) — Keep your chatbot's Q&A and product facts in a Google Sheet it queries over MCP or REST — accurate answers from live rows, with no vector store to run. - [A RAG Data Source From Google Sheets](https://pastesheet.com/use-cases/google-sheets-rag-data-source) — Skip the vector store for small, structured corpora: your agent retrieves rows from a Google Sheet with query_rows filters and full-text search over MCP. - [Power an FAQ Page from a Google Sheet](https://pastesheet.com/use-cases/google-sheets-faq-page) — Build a searchable FAQ or help page from a Google Sheet — one row per question and answer. Full-text search over questions via a live, read-only JSON API. --- [PasteSheet](https://pastesheet.com) turns any Google Sheet into a live REST API and MCP server for AI agents — no backend, no code. Canonical HTML version of this page: