- Check the server address before you install.
- Keep the confirmation prompt on for the tools that overwrite or delete.
- Know what an admin can and cannot control.
The official endpoint
Surfer operates one server, the one on Server details. Before you add Surfer from a marketplace listing, an install link, or a shared snippet, check two things:- The URL matches the one on Server details.
- The snippet asks for no API key and no custom header. A snippet that asks for either is not Surfer’s.
What connecting grants
The connection is bound to your account and one organization, across every tool.- The token Surfer issues at authorization is bound to your user account and to the one organization you picked on the consent page. From then on the client acts as you inside that organization.
- Permission checks apply to you, not to the client. A tool that requires an organization owner or admin, such as creating or activating a workspace, fails for a member.
- The connection reaches only the workspaces you are a member of. A workspace in the organization that you do not belong to is not listed, and a tool call that names it answers
not_found, for reads and writes alike. An organization owner or admin adds you to a workspace in the app. - The connection can read the Search Console performance data of every workspace you belong to that has Search Console connected.
- The grant covers the whole tool catalog. Every tool, read and write, is available to the client from the first call.
What an agent can change or delete
Keep confirmation prompts on for actions that change content, settings, or reusable assets.
The server supplies behavior annotations with each tool so your client can distinguish reads from changes and deletions. Client approval settings determine when you see a confirmation. Some actions also spend credits; see Credits and limits.
Prompt injection
Text that Surfer fetches from the web comes back through read tools, and it can carry instructions aimed at your assistant. These actions fetch web content:- Creating a workspace analyzes the brand site.
- Creating a Content Editor analyzes the SERP, and imports a page when you give it a URL to import.
- Loading more competitors fetches additional competitor pages.
- Competitor titles and URLs, with the SEO guidelines.
- The imported page, as the editor’s document.
- AI Search facts, with their source URLs.
- Keep confirmation prompts on for changes and deletions, so a hidden instruction cannot rewrite or delete content without you seeing the call.
- Do not allowlist write tools, even in a client that can allowlist a whole server.
- Be deliberate about which other servers share the session. A client can pass content returned by Surfer to another connected server. A session that also has email, chat, or shell access carries that risk.
Keep confirmations on
Each client decides when to ask before a tool runs. The table shows where each client’s setting lives, so you do not switch the prompt off by accident.- Claude, ChatGPT desktop, and Codex read the tool annotations and prompt before a tool Surfer marks destructive, such as deleting a template, unless you allowed that tool to run without asking.
- ChatGPT web asks before any tool that Surfer does not mark as read-only.
- Cursor and VS Code ask before every MCP tool until you allowlist it.
Allowlisting read-only tools costs nothing: they change no data and spend no credits. Keep the prompt for the rest.
What an admin controls
Your organization’s Surfer plan decides whether its members can use MCP. To restrict MCP further, an administrator uses the settings of the AI client. On the Surfer side there is:- No separate switch to allow or deny MCP for an organization.
- No list of connected clients or of the members who have connected, and no revoke button; disconnecting happens in the client, as described on Authentication.
A server that never appears for a member may be policy rather than a network fault.
What Surfer records
Surfer records which tools were called and by whom. The MCP server sends no tool arguments or document content to its own error reporting or analytics; its requests to Surfer’s backend are logged like any other API request.- Every call is recorded with the tool, the user, the organization, the client, the outcome, and the duration.
- Unexpected failures are sent to error reporting with the tool name, the client id, and an id for your account.