AI agents call maple_get_started to retrieve information from Maple without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current Maple state and returns decision/routing information to guide next steps. It does not modify state, execute commands, delete data, or involve financial operations. It is purely informational—a read operation that helps with navigation and planning. The low severity reflects that misuse would only expose internal routing logic without enabling direct harm.
From the tool's definition Tool returns routing information and next MCP calls based on current state; described as providing a 'quickstart' by returning data rather than executing actions. Uses verbs like 'Returns' indicating data retrieval with no side effects.
Attacks that exploit this kind of access
LLM quickstart for Maple routing. Returns the exact next MCP calls (search/connect/call) based on current Maple state so no UI steps are required. It is categorised as a Read tool in the Maple MCP Server, which means it retrieves data without modifying state.
Register the Maple MCP server in PolicyLayer and add a rule for maple_get_started: 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 Maple. Nothing to install.
maple_get_started 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 maple_get_started 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 maple_get_started. 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.
maple_get_started is provided by the Maple MCP server (omar2001ramadan/mcp). 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 →