AI agents call saos_list_courts to retrieve information from SAOS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves static reference data about Polish courts. It has no side effects, creates no data, executes no code, and performs no destructive operations. It is purely informational, supporting search filtering in a read-only manner. Low severity reflects minimal risk from misuse—an AI agent listing courts poses negligible harm.
From the tool's definition Tool returns a list of courts (ID, name, type) for filtering purposes. Description indicates 'Zwraca listę' (returns a list) with no modification capabilities.
Attacks that exploit this kind of access
Zwraca listę sądów powszechnych (ID, nazwa, typ). Użyj żeby znaleźć ID sądu do filtrowania w saos_search_judgments. It is categorised as a Read tool in the SAOS MCP MCP Server, which means it retrieves data without modifying state.
Register the SAOS MCP server in PolicyLayer and add a rule for saos_list_courts: 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 SAOS MCP. Nothing to install.
saos_list_courts 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 saos_list_courts 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 saos_list_courts. 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.
saos_list_courts is provided by the SAOS MCP server (pawelojdowski/saos-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 →