> For the complete documentation index, see [llms.txt](https://guides.noloco.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guides.noloco.io/quickstart/connect-an-ai-agent.md). # Connect your own AI agent Most teams already work with an AI assistant. By connecting yours directly to Noloco, your assistant can read your live app data, query these guides in real time, and write back to your app on your behalf — all from the chat interface you already use. The connection uses two [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) servers: * The **Noloco app data MCP** gives your assistant access to your apps' tables, schemas, and records. * The **Noloco guides MCP** gives your assistant read-only access to these guides — the same documentation you're reading now. Together, these two connections turn your assistant into an expert architect. It already knows your business; it can now read both your live data and our recommended patterns, so it can tell you exactly what tables to create, what relationships you need, which views to add, and how to set up workflows and permissions for your use case. Once your app is live, the same connection lets your assistant answer questions about your data and run updates for you in natural language. {% hint style="warning" %} A connected client acts with the same permissions as your data admin role on every Noloco app you approve during sign-in. Only connect AI clients you trust. See [MCP Integration](/settings/integrations-and-api-keys/mcp-integration.md) for the full security model. {% endhint %} ## What you can do with a connected AI A few prompts that show the range: * *"I run a small HVAC company. Design the tables and relationships I need for a job-tracking app, using Noloco's recommended patterns."* * *"Review the schema in my current app and suggest improvements based on Noloco best practices."* * *"Walk me through setting up a permission rule so contractors only see their own jobs."* * *"Look up the 20 most recent records in my Jobs table and summarize which are at risk of slipping."* * *"Create five test customers in my CRM with realistic data."* You don't need to know Noloco's table or field names — your assistant will inspect the schema itself and use the guides MCP to look up anything it needs. ## The two MCP servers ### Noloco app data MCP * **URL:** `https://api.core.noloco.io/mcp` * **Auth:** OAuth — sign in to Noloco the first time you connect a client. No API key. * **What it gives the agent:** list projects, list tables, read schemas, list/get/create/update/delete records * **Scope:** every Noloco app where you're a data admin and which you approve during sign-in. One connection per client covers your entire portfolio — the agent picks which app to act on per request. For the full list of available tools, scope rules, and rate-limit behavior, see [MCP Integration](/settings/integrations-and-api-keys/mcp-integration.md). ### Noloco guides MCP * **URL:** `https://guides.noloco.io/~gitbook/mcp` * **Auth:** none — public * **What it gives the agent:** read-only access to these guides Hosted by GitBook. Anyone can connect — no sign-in required. ## Setting up your agent The blocks below show how to add both servers together for each major MCP client. The app data MCP triggers an OAuth sign-in the first time you use it — a browser window opens, you sign in to Noloco, and you pick which apps and which scope (read or read + write) the client gets. ### Claude Desktop Open **Settings → Connectors**. You have two ways to add Noloco: * **Directory** — find **Noloco** in the connector directory and click **Connect**. This is the quickest if Noloco is listed for your account. * **Custom connector** — click **Add custom connector**, enter a name (e.g. `Noloco`) and `https://api.core.noloco.io/mcp` as the remote MCP server URL, then click **Add**. Use this if you don't see Noloco in the directory. Either way, a browser window opens — sign in to Noloco, pick which apps the client can access, and choose the scope (read or read + write). Add the **Noloco guides** connector the same way using `https://guides.noloco.io/~gitbook/mcp` (no auth).

The Noloco consent screen — pick which apps the client can use, and whether it gets read or write on each.

Once approved, you'll see the Noloco tools in Claude's tool list. You can disconnect or re-run the consent step at any time from the same Connectors screen. ### Claude Code Run: ```bash claude mcp add --transport http noloco https://api.core.noloco.io/mcp ``` For the guides MCP: ```bash claude mcp add --transport http noloco-guides https://guides.noloco.io/~gitbook/mcp ``` The next time you start a session, Claude Code opens the Noloco consent screen in your browser. ### Cursor In Cursor, open **Settings → MCP** and add the following: ```json { "mcpServers": { "noloco": { "url": "https://api.core.noloco.io/mcp" }, "noloco-guides": { "url": "https://guides.noloco.io/~gitbook/mcp" } } } ``` The first time Cursor calls a Noloco tool, a browser window opens for you to sign in and approve access. ### Windsurf In Windsurf, open the MCP configuration panel and add the same JSON shown for Cursor. The browser will open for OAuth sign-in on first use. ### ChatGPT — Custom Connectors In ChatGPT, open **Settings → Connectors → Create** and add each server by URL: * For the **Noloco app data MCP**, paste `https://api.core.noloco.io/mcp`. ChatGPT will walk you through the OAuth sign-in step automatically — no header to configure. * For the **Noloco guides MCP**, paste `https://guides.noloco.io/~gitbook/mcp` with no auth. {% hint style="info" %} ChatGPT Custom Connectors are available on Business, Enterprise, Edu, and developer plans. If your plan doesn't include them, Claude Desktop and Gemini CLI both offer free MCP support. {% endhint %} ### Gemini CLI Edit `~/.gemini/settings.json` (create it if it doesn't exist) and add: ```json { "mcpServers": { "noloco": { "httpUrl": "https://api.core.noloco.io/mcp" }, "noloco-guides": { "httpUrl": "https://guides.noloco.io/~gitbook/mcp" } } } ``` Restart `gemini` after saving. The first Noloco tool call will open a browser for OAuth sign-in. Run `/mcp` inside the CLI to confirm both servers are connected. ### Other MCP clients Any client that supports OAuth over the [Streamable HTTP transport](https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http) can connect. You need one URL per server: * **Noloco app data MCP** — `https://api.core.noloco.io/mcp` (OAuth handled by the client on first call). * **Noloco guides MCP** — `https://guides.noloco.io/~gitbook/mcp` (no auth). See [MCP Integration](/settings/integrations-and-api-keys/mcp-integration.md#other-mcp-clients) for additional notes. ## A sample conversation Once both servers are connected, the interaction feels like working with a Noloco expert who already knows your business. A short example: **You:** "I run a residential cleaning company with around 10 cleaners. I want to track customers, recurring cleaning jobs, and which cleaner is assigned to each visit. Can you design the table structure I need?" **Your assistant:** "Let me check the Noloco guides for the recommended way to model recurring jobs and assignees…" *(reads the guides via the MCP)* "Here's what I'd suggest: * **Customers** — name, address, phone, email, notes * **Cleaning Jobs** — linked to Customer, frequency (one-off, weekly, fortnightly, monthly), duration, hourly rate * **Visits** — linked to Job, scheduled date, status (Scheduled / Completed / Cancelled), assigned cleaner * **Cleaners** — linked to Noloco's User table so each cleaner can log in For the *assigned cleaner*, Noloco has a dedicated Assignee field type that handles this exact pattern — it links to a User and powers 'My visits' filters and notifications. Want me to use that?" **You:** "Yes. We also need to send a reminder email to the customer the day before each visit." **Your assistant:** "Got it. That's a Workflow on the Visits table with a *scheduled trigger* (1 day before the visit date) and a *send email* action. I can see exactly how to set it up from the guides — want me to walk you through the steps in the studio, or just outline what you need to do?" The assistant won't create those tables for you (see the next section) — but with a complete plan in hand, the build itself takes minutes. ## What this can and can't do **Your connected assistant can:** * Read and write records in any Noloco app you approved during sign-in * Read those apps' table schemas and field definitions * Look up anything in these guides in real time * Recommend tables, fields, relationships, views, workflows, and permission rules suited to your business * Walk you through setting up features step by step, referencing the live guides **It can't (today):** * Create tables, pages, views, or workflows in the Noloco studio for you — for that, use [Nola](/quickstart/start-with-nola.md), Noloco's in-studio AI assistant * Modify your app's design, theme, or layout * Access settings, billing, or user management ## Security notes * A connected client has the same permissions as your data admin role on every app you approved during sign-in. Only connect clients you trust. * No long-lived API key is shared — OAuth tokens are issued per client and can be revoked individually. * Permissions changes (role revoked, removed from workspace) take effect on the next tool call, no token reissue needed. * The MCP server enforces HTTPS — plain HTTP connections are not accepted. * To disconnect a client, remove it from your Noloco connected applications. For the full security model and a complete list of tools available on the app data MCP, see: {% content-ref url="/pages/x2Etj6jf6m7fSkuKZE8s" %} [MCP Integration](/settings/integrations-and-api-keys/mcp-integration.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://guides.noloco.io/quickstart/connect-an-ai-agent.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.