AI agents call get_block_state 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 and returns information about block state, arguments, and summaries. It has no side effects—it does not modify, execute, delete, or create data. It is a straightforward query operation that falls clearly under the Read category. The token estimate output is additional metadata, not an execution or state change.
From the tool's definition Tool name 'get_block_state' and description 'Get block state. Returns block args (data) and a concise output summary' indicate retrieval of state information without modification. The verb 'Get' and 'Returns' confirm read-only query semantics.
Attacks that exploit this kind of access
Get block state. Returns block args (data) and a concise output summary with token estimates by default. 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_state: 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_state 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_state 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_state. 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_state 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 →