AI agents call safety_policy to retrieve information from Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays safety policy metadata—essentially a lookup or informational query. It has no side effects, does not execute code or commands, does not modify data, and does not delete anything. The sole purpose is to inform the user about what operations need confirmation, making it a classic Read operation with minimal security risk.
From the tool's definition Tool name 'safety_policy' and description 'Lists which operations require explicit user confirmation before execution' indicate a read-only query operation that retrieves policy information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Lists which operations require explicit user confirmation before execution. It is categorised as a Read tool in the Context MCP Server, which means it retrieves data without modifying state.
Register the Context MCP server in PolicyLayer and add a rule for safety_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 Context. Nothing to install.
safety_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 safety_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 safety_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.
safety_policy is provided by the Context MCP server (vibhasdutta/context-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 →