AI agents call read_agent to retrieve information from Snak 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 agent configuration data without altering, deleting, or executing anything. It is a straightforward data retrieval operation with no destructive or executable side effects. The low severity reflects minimal risk—an AI agent misusing this would at worst see agent details, which may include sensitive configuration but causes no irreversible changes.
From the tool's definition Tool description explicitly states 'Get/retrieve/show/view/find details and configuration' with no modification or side effects mentioned. The verb phrases (get, retrieve, show, view, find) are all read-only operations.
Attacks that exploit this kind of access
Get/retrieve/show/view/find details and configuration of a specific agent by ID or name. Use when user wants to see information about a particular agent. It is categorised as a Read tool in the Snak MCP Server, which means it retrieves data without modifying state.
Register the Snak MCP server in PolicyLayer and add a rule for read_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 Snak. Nothing to install.
read_agent 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 read_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.
Set action: deny in the PolicyLayer policy for read_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.
read_agent is provided by the Snak MCP server (kasarlabs/snak). 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 →