AI agents call get_block_logs to retrieve information from Pl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical log information about block execution. It performs a query operation that extracts and returns existing log data keyed by sample/run ID, with no capability to modify, delete, or execute operations. The blast radius of misuse is minimal—exposure of logs may leak information but cannot alter system state or trigger operations.
From the tool's definition Tool description states 'Read execution logs for a block' and 'reads log content'. The verb 'Read' and action of extracting and returning log data indicate retrieval without modification or side effects.
Attacks that exploit this kind of access
Read execution logs for a block. Extracts log handles from block outputs and reads log content. Returns logs keyed by sample/run ID. It is categorised as a Read tool in the Pl MCP Server, which means it retrieves data without modifying state.
Register the Pl MCP server in PolicyLayer and add a rule for get_block_logs: 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 Pl. Nothing to install.
get_block_logs 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 get_block_logs 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 get_block_logs. 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.
get_block_logs is provided by the Pl MCP server (@milaboratories/pl-mcp-server). 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 →