AI agents call saos_get_judgment 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 performs data retrieval from a public Polish court database without modifying, deleting, or executing arbitrary code. The archival file creation is a local-only side effect that does not alter the source database. Classification as Read is appropriate; severity is low due to limited blast radius (retrieval of public judicial records poses minimal security risk).
From the tool's definition Tool retrieves full judgment from SAOS database by ID, returning metadata, sentence, and full justification. Description indicates 'Pobiera' (retrieves) and 'Zwraca' (returns) - read-only operations.
Attacks that exploit this kind of access
Pobiera pełne orzeczenie z SAOS po ID. Zwraca metadane + sentencję dosłownie + pełne uzasadnienie. W trybie lokalnym zapisuje też plik .md z kopią archiwalną. 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_get_judgment: 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_get_judgment 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_get_judgment 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_get_judgment. 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_get_judgment 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 →