AI agents call get_main_page to retrieve information from Mcpzim without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays the main/home page from an offline ZIM archive. It performs a read-only query operation with no capacity to modify, delete, or execute code. The blast radius of misuse is minimal—an agent could only retrieve publicly available content that is already in the archive. No financial, destructive, or executable operations are possible.
From the tool's definition Tool name 'get_main_page' and description 'Fetch the main/home page of a ZIM' indicates retrieval of static content with no modification or side effects.
Attacks that exploit this kind of access
Fetch the main/home page of a ZIM. If no zim name is given, returns. It is categorised as a Read tool in the Mcpzim MCP Server, which means it retrieves data without modifying state.
Register the Mcpzim MCP server in PolicyLayer and add a rule for get_main_page: 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 Mcpzim. Nothing to install.
get_main_page 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_main_page 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_main_page. 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_main_page is provided by the Mcpzim MCP server (jasontitus/mcpzim). 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 →