Get a stored entity by ID (internal or external).
AI agents call state_get to retrieve information from Onboarded MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from storage by ID lookup. It performs a read-only query operation without side effects, making it a Read category tool. Severity is low because retrieval of stored entities poses minimal risk unless the data itself is sensitive, but the tool's mechanism is non-destructive and reversible. Confidence is high because the description explicitly uses 'Get', a clear read operation.
From the tool's definition Tool name 'state_get' and description 'Get a stored entity by ID' indicate a retrieval operation with no modification or deletion capability.
Attacks that exploit this kind of access
Get a stored entity by ID (internal or external). It is categorised as a Read tool in the Onboarded MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Onboarded MCP Server MCP server in PolicyLayer and add a rule for state_get: 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 Onboarded MCP Server. Nothing to install.
state_get 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 state_get 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 state_get. 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.
state_get is provided by the Onboarded MCP Server MCP server (onboardedinc/onboarded-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 →