AI agents call uodo_get_decision to retrieve information from UODO MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval/query operation with no creation, modification, deletion, or external code execution. It fetches existing decision documents from a database and optionally saves read-only archive copies locally. No data in the source system is altered, and no financial or destructive actions occur. This clearly fits the Read category.
From the tool's definition Tool retrieves and returns complete UODO decisions by ID, including metadata, ruling text, and full justification. The description states it 'Pobiera pełną decyzję' (retrieves full decision) and 'Zwraca' (returns) data.
Attacks that exploit this kind of access
Pobiera pełną decyzję UODO 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 UODO MCP MCP Server, which means it retrieves data without modifying state.
Register the UODO MCP server in PolicyLayer and add a rule for uodo_get_decision: 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 UODO MCP. Nothing to install.
uodo_get_decision 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 uodo_get_decision 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 uodo_get_decision. 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.
uodo_get_decision is provided by the UODO MCP server (pawelojdowski/uodo-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 →