AI agents call get_allowed_domains to retrieve information from Yanifend without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration or settings information (allowed domains for a client/form) without modifying, executing code, or deleting anything. It is a straightforward read operation with minimal blast radius if misused—at worst, an AI agent would access non-sensitive domain configuration data. Confidence is high despite the terse description because the naming pattern and stated action are unambiguous.
From the tool's definition Tool name 'get_allowed_domains' and description 'Read the client' both indicate data retrieval. The 'get_' prefix and 'Read' verb confirm this is a query operation with no side effects.
Attacks that exploit this kind of access
Read the client. It is categorised as a Read tool in the Yanifend MCP Server, which means it retrieves data without modifying state.
Register the Yanifend MCP server in PolicyLayer and add a rule for get_allowed_domains: 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 Yanifend. Nothing to install.
get_allowed_domains 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 get_allowed_domains 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 get_allowed_domains. 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.
get_allowed_domains is provided by the Yanifend MCP server (skippedaga/yanifend-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 →