AI agents invoke call_model to trigger actions in FullScope-MCP. 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 tool explicitly invokes an external AI/ML model with arbitrary input. This constitutes an Execute action as it triggers an external operation whose effects depend on the arguments passed. The blast radius is high because arbitrary model calls could be used for prompt injection, data exfiltration via the model, or resource exhaustion.
From the tool's definition "调用模型进行回答" (Call model to answer) — triggers an external model invocation
Documented attack patterns abuse exactly the kind of access call_model gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FullScope-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for call_model:
{
"version": "1",
"default": "deny",
"tools": {
"call_model": {
"limits": [
{
"counter": "call_model_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}call_model 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.
调用模型进行回答. It is categorised as a Execute tool in the FullScope-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FullScope- MCP server in PolicyLayer and add a rule for call_model: 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 FullScope-MCP. Nothing to install.
call_model 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 call_model 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 call_model. 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.
call_model is provided by the FullScope- MCP server (yzfly/fullscope-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FullScope-MCP, 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.
7 FullScope-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.