AI agents call saos_search_judgments 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 and queries court judgment data from a public database. It performs a search operation with no capability to create, modify, delete, or execute arbitrary operations. The operation has no side effects and presents minimal security risk—it simply returns existing court records that are part of the Polish public judicial system.
From the tool's definition Tool description states 'Wyszukuje orzeczenia sądowe w bazie SAOS' (searches court judgments in SAOS database).
Attacks that exploit this kind of access
Wyszukuje orzeczenia sądowe w bazie SAOS (sortowanie: najnowsze pierwsze).\n\nZASADA NACZELNA — frazy prawne zawsze w cudzysłowie:\n• query: \. 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_search_judgments: 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_search_judgments 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_search_judgments 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_search_judgments. 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_search_judgments 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 →