List path descriptors registered by connected MDP clients.
AI agents call listPaths to retrieve information from Model Drive Protocol MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/discovery operation that retrieves information about registered path descriptors from connected clients. It has no side effects, does not execute code or commands, does not modify data, and does not move money. The blast radius of misuse is minimal—an agent could learn about available capabilities but cannot act on them without using other tools like callPath or callPaths.
From the tool's definition Tool name 'listPaths' and description 'List path descriptors registered by connected MDP clients' indicate retrieval of metadata about available paths/capabilities without modification or execution of external operations.
Documented attack patterns abuse exactly the kind of access listPaths gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Model Drive Protocol MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for listPaths:
{
"version": "1",
"default": "deny",
"tools": {
"listPaths": {}
}
}listPaths is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List path descriptors registered by connected MDP clients. It is categorised as a Read tool in the Model Drive Protocol MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Model Drive Protocol MCP Server MCP server in PolicyLayer and add a rule for listPaths: 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 Model Drive Protocol MCP Server. Nothing to install.
listPaths 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 listPaths 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 listPaths. 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.
listPaths is provided by the Model Drive Protocol MCP Server MCP server (modeldriveprotocol/modeldriveprotocol). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Model Drive Protocol MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Model Drive Protocol MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.