--- layout: integration title: Host an MCP server on Appwrite Functions description: Deploy your own MCP server on Appwrite Functions and connect it to Claude Code, Cursor, and other AI clients date: 2026-11-06 featured: false isPartner: true isNew: true cover: /images/integrations/mcp-server-functions/cover.avif category: mcp product: vendor: Model Context Protocol description: "The Model Context Protocol (MCP) is an open standard that lets AI applications discover and call external tools and data sources." platform: - 'Self-hosted' - 'Cloud' --- The [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) is an open standard for giving AI applications new capabilities. An MCP server exposes tools, and clients such as Claude Code, Cursor, and Claude Desktop discover and call them while they work. # How does the integration work? The **MCP server** function template deploys a stateless MCP server on Appwrite Functions, built with the official MCP Python SDK (`mcp==2.0.0`). Your function's domain becomes the server URL. It speaks JSON-RPC over HTTPS and handles both the legacy handshake for clients on protocol version `2025-06-18` and the stateless protocol from the [MCP 2026-07-28 specification](/blog/post/mcp-goes-stateless-in-the-2026-07-28-specification). The template ships with two demo tools, `echo` and `add`, so you can test the full loop before writing code. You add your own tools in `src/app.py`, and each request carries an [ephemeral API key](/docs/products/functions/develop#ephemeral-api-key), so tools can read and write your project's data without credentials you manage. This is for hosting tools you write. To let AI tools manage Appwrite itself, use the [Appwrite MCP server](/docs/tooling/ai/mcp-servers) instead. # How to implement To host your own MCP server on Appwrite Functions, there are several steps you must complete: ## Step 1: Create the Appwrite Function For this step, you must [create an account on Appwrite Cloud](/sign-up) or [self-host Appwrite](/docs/advanced/self-hosting) if you haven't already. If you self-host Appwrite, enable a Python runtime from 3.10 to 3.14 in `_APP_FUNCTIONS_RUNTIMES` and follow the [Functions configuration guide](/docs/advanced/self-hosting/configuration/functions) so function domains work. In the Appwrite Console, go to **Functions**, open the **Templates** tab, search for **MCP server**, and click **Create from template**. The **Template variables** are all optional: | Variable | Default | Purpose | | --- | --- | --- | | `MCP_SERVER_NAME` | `appwrite-hosted-mcp` | The server name clients see in the `initialize` handshake | | `MCP_AUTH_MODE` | `none` | `none` keeps the endpoint open, `bearer` requires a shared secret, and `oauth` signs users in through your project's OAuth2 server | | `MCP_AUTH_TOKEN` | Empty | The shared secret for `bearer` mode | | `MCP_AUTH_SCOPES` | Empty | `oauth` mode only: space-separated scopes advertised to clients, such as `openid tasks.read` | | `MCP_TOOL_TIMEOUT` | `25` | A soft deadline in seconds for each request | Choose **Connect your repository**, so you can add tools by pushing to Git, then click **Create and deploy**. ## Step 2: Secure the endpoint The endpoint is open by default, which is fine while you experiment. Before you expose anything internal, set `MCP_AUTH_MODE` to `bearer` and `MCP_AUTH_TOKEN` to a long random secret, and mark the token as a [secret variable](/docs/products/functions/environment-variables#secret-variables). The server then rejects any request without a matching `Authorization: Bearer` header. Redeploy the function after changing variables. To sign each user in instead, `oauth` mode sends MCP clients through your project's [OAuth2 server](/docs/products/auth/oauth-server) on Appwrite Cloud, and tools act as the signed-in user, so row permissions apply. The template requests the `users.write` scope for this mode. Follow the [OAuth setup in the template's README](https://github.com/appwrite/templates/tree/1.3.0/python/mcp-server#per-user-sign-in-oauth). ## Step 3: Connect your AI client Copy the function's domain from the **Domains** tab. In Claude Code, add the server with one command: ```bash claude mcp add --transport http my-mcp https:// ``` In Cursor or Claude Desktop, add the URL to your MCP configuration. With bearer authentication, pass the token in `headers`: ```json { "mcpServers": { "my-mcp": { "url": "https://", "headers": { "Authorization": "Bearer " } } } } ``` Ask your agent to list the server's tools, then call `echo` to see the request travel to your function and back. ## Step 4: Add your own tools Register tools in `src/app.py` with the `@server.tool` decorator. Python type hints become each tool's input schema: ```python from mcp.server.mcpserver import MCPServer server = MCPServer(name="my-mcp", version="0.1.0") @server.tool(description="Do something useful.") def my_tool(query: str) -> str: return f"got: {query}" ``` Push the change to your connected repository, and Appwrite builds and activates the new deployment. Clients pick up the updated tool list. Two limits apply. The server returns plain JSON, so there is no streaming and no server-initiated messages. Requests to the function's domain are [synchronous executions](/docs/products/functions/execute#synchronous-executions) capped at 30 seconds, so keep `MCP_TOOL_TIMEOUT` at 25 and have long jobs return a handle that another tool can poll. # Read more about MCP and Appwrite Functions If you would like to learn more about MCP and Appwrite Functions, we have some resources that you should visit: - [Build and deploy an MCP server with Appwrite Functions](/blog/post/announcing-mcp-server-template) - [MCP goes stateless in the 2026-07-28 specification](/blog/post/mcp-goes-stateless-in-the-2026-07-28-specification) - [Connect AI tools to Appwrite with the Appwrite MCP server](/docs/tooling/ai/mcp-servers) - [Learn more about Functions templates in Appwrite docs](/docs/products/functions/templates) - [MCP server template source](https://github.com/appwrite/templates/tree/1.3.0/python/mcp-server)