AI agents call get_page_by_id to retrieve information from Magnet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries page data with no side effects. It neither modifies, deletes, executes operations, nor involves financial transactions. The previewOnly parameter further confirms read-only semantics. This is a straightforward data retrieval operation with minimal security risk.
From the tool's definition Tool description explicitly states 'Fetch a single page by its ID from Magnet and return it as markdown' with an option for preview. The verb 'Fetch' and return-only behavior indicate data retrieval without modification.
Attacks that exploit this kind of access
Fetch a single page by its ID from Magnet and return it as markdown. Use previewOnly=true to get a markdown preview instead of full content. It is categorised as a Read tool in the Magnet MCP Server, which means it retrieves data without modifying state.
Register the Magnet MCP server in PolicyLayer and add a rule for get_page_by_id: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Magnet. Nothing to install.
get_page_by_id is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_page_by_id rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_page_by_id. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_page_by_id is provided by the Magnet MCP server (@magnet-ai/magnet-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →