Connect Strapi to ChatGPT via MCP: Query Documents

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Strapi 5, paste your credentials, mint an MCP API key — done. No Docker, no git clone, no local server.

Strapi 5 + ChatGPT

Connect to a Strapi 5 instance to check its availability, query documents from collection types, and retrieve individual documents through the read-only REST Content API.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

STRAPI_URL, STRAPI_API_TOKEN

Step 1 — Get credentials

Setting up takes about 2 minutes. You need a Strapi 5 instance and a read-only Content API token.

1. Set STRAPI_URL to the root URL of your Strapi instance, for example https://cms.example.com, without /api at the end.
2. In the Strapi admin, open Settings → API Tokens and create a Content API token with read-only access to the collection types the AI should see. Copy it into STRAPI_API_TOKEN. It is sent only in the Authorization Bearer header.
3. Install the connector and run strapi_health to check that Strapi is reachable. Then run strapi_list_documents on a collection you know, such as articles: only that shows the token works, because strapi_health does not check the token or its permissions.

Where Strapi runs: Strapi Cloud and any other publicly reachable Strapi 5 instance work from AnythingMCP Cloud. An instance on a private network, on localhost or at a private IP address works only with self-hosted AnythingMCP, and its host must be allowed through SSRF_ALLOWED_HOSTS, because the outbound guard blocks private address space by default.

What it reads: documents from one collection type at a time. You address a collection type by its plural API ID, such as articles, not by its display name, and the connector cannot discover the collection types for you. strapi_list_documents supports field selection, Strapi filter operators, sorting (field:asc or field:desc), page-based pagination, populate for relations or media, locale for localized content and status for published or draft documents; it keeps Strapi's meta, so pagination information stays available. strapi_get_document fetches one document by its Strapi 5 documentId. Relations, media, components and dynamic zones come back only when populate asks for them.

Read-only: all three tools are GET requests. The connector cannot create, update, publish, unpublish or delete content.

The connector works with the Strapi 5 REST Content API only: it does not support Strapi 4 response shapes or the Admin, Content Manager and Content-Type Builder APIs.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in ChatGPT

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

ChatGPT adds MCP servers as plugins on its Plugins page, on the web and on paid plans. Developer mode is no longer needed. In a Business workspace only admins and owners can add one; in Enterprise and Edu an admin can grant the Create plugins with MCPs permission.

1. Go to chatgpt.com/plugins, click Add, then Add custom MCP server.
2. Enter a name, e.g. Name: Strapi 5.
3. Under Connection, enter the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID and keep Authentication on OAuth.
4. Select I understand and want to continue, then Create as a plugin. When ChatGPT asks, sign in to AnythingMCP and allow access.
5. Install the new plugin from your personal plugins, then type @ in a chat and pick it.

Available tools

FAQ

Does the free ChatGPT plan work with custom MCP servers? OpenAI documents custom MCP servers for paid plans only; the Free plan is not on its list.

Next steps

• Connector landing page
• Connect to Claude