Invoke one exact path on one exact MDP client.
AI agents invoke callPath to trigger actions in Model Drive Protocol MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The parent server description indicates this bridge exposes 'runtime-local capabilities from browsers, apps, devices, and local processes.' Invoking an arbitrary 'path' on such clients is equivalent to Execute: the tool triggers external operations (local process actions, browser behavior, device commands) based on attacker-controlled arguments.
From the tool's definition Tool description states 'Invoke one exact path on one exact MDP client' — invoking arbitrary paths on local processes, browsers, apps, and devices constitutes code/command execution whose effects are determined by the path argument.
Documented attack patterns abuse exactly the kind of access callPath 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 callPath:
{
"version": "1",
"default": "deny",
"tools": {
"callPath": {
"limits": [
{
"counter": "callpath_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}callPath stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Invoke one exact path on one exact MDP client. It is categorised as a Execute tool in the Model Drive Protocol MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Model Drive Protocol MCP Server MCP server in PolicyLayer and add a rule for callPath: 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.
callPath is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the callPath 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 callPath. 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.
callPath 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.