get_sandbox_violations_by_agent

Per-Agent sandbox violation counts over the last N days, top N by total, enriched with name/kind and a by-violation-type sub-count. Reveals which Agents most frequently attempt disallowed actions.

SERVERTodo for AI MCP Server SOURCEtodo-for-ai/todo-for-ai-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/todo-for-ai-todo-for-ai-mcp/get-sandbox-violations-by-agent.md

WHAT IT DOES

What get_sandbox_violations_by_agent does on Todo for AI MCP Server

AI agents call get_sandbox_violations_by_agent to retrieve information from Todo for AI MCP Server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why get_sandbox_violations_by_agent is rated Low

Even though get_sandbox_violations_by_agent only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs get_sandbox_violations_by_agent safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Todo for AI MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_sandbox_violations_by_agent, this is the rule to start with:

get_sandbox_violations_by_agent Allowed

get_sandbox_violations_by_agent is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_sandbox_violations_by_agent": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Todo for AI MCP Server, apply this rule, and every get_sandbox_violations_by_agent call is checked against it from then on.

FAQ

Questions about get_sandbox_violations_by_agent

What does the get_sandbox_violations_by_agent tool do? +

Per-Agent sandbox violation counts over the last N days, top N by total, enriched with name/kind and a by-violation-type sub-count. Reveals which Agents most frequently attempt disallowed actions. It is categorised as a Read tool in the Todo for AI MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_sandbox_violations_by_agent? +

Register the Todo for AI MCP Server MCP server in PolicyLayer and add a rule for get_sandbox_violations_by_agent: 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 Todo for AI MCP Server. Nothing to install.

What risk level is get_sandbox_violations_by_agent? +

get_sandbox_violations_by_agent is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_sandbox_violations_by_agent? +

Yes. Add a rate_limit block to the get_sandbox_violations_by_agent 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.

How do I block get_sandbox_violations_by_agent completely? +

Set action: deny in the PolicyLayer policy for get_sandbox_violations_by_agent. 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.

What MCP server provides get_sandbox_violations_by_agent? +

get_sandbox_violations_by_agent is provided by the Todo for AI MCP Server MCP server (todo-for-ai/todo-for-ai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Todo for AI MCP Server, and thousands of servers like it.

This server

All 244 Todo for AI MCP Server tools →

Across the catalogue

get_agent on 0rca Dojo MCP Server →get_cocktail_by_category on Cocktails RAG MCP Server →get_torrent_detail on M-Team MCP Server →aiva_get_affiliate on AIVA MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →