Check what policy requires for given signals. Returns: - Whether MINIMAL vs ROBUST options comparison is required - Required validation level (BASIC/STANDARD/STRICT) - Any warnings or requirements Call this before implementation to understand constraints.
AI agents call check_policy to retrieve information from Decision OS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves policy information and validation requirements without modifying any state or triggering external operations. It is a pure read operation that helps inform decision-making. While it relates to a decision tracking system, the tool itself merely queries existing policy data, placing it clearly in the Read category with low severity and minimal risk of misuse.
From the tool's definition Tool description states it 'Check[s] what policy requires' and 'Return[s]' policy requirements and validation levels. The verb 'check' and 'returns' indicate information retrieval with no side effects.
Attacks that exploit this kind of access
Check what policy requires for given signals. Returns: - Whether MINIMAL vs ROBUST options comparison is required - Required validation level (BASIC/STANDARD/STRICT) - Any warnings or requirements Call this before implementation to understand constraints. It is categorised as a Read tool in the Decision OS MCP MCP Server, which means it retrieves data without modifying state.
Register the Decision OS MCP server in PolicyLayer and add a rule for check_policy: 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 Decision OS MCP. Nothing to install.
check_policy 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 check_policy 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 check_policy. 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.
check_policy is provided by the Decision OS MCP server (marianstefi20/decision-os-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 →