Store an entity reference (e.g., after creating via API).
AI agents use state_put to create or update resources in Onboarded MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Onboarded MCP Server environment.
This tool modifies state by storing entity references. It is a Write operation because it creates or modifies data reversibly—state can be updated or cleared later (as evidenced by the sibling tool 'state_delete'). It does not execute arbitrary code, delete data irreversibly, or move money.
From the tool's definition Tool name is 'state_put' and description states 'Store an entity reference (e.g., after creating via API)'. The verb 'store' indicates data is being written/persisted to state.
Attacks that exploit this kind of access
Store an entity reference (e.g., after creating via API). It is categorised as a Write tool in the Onboarded MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Onboarded MCP Server MCP server in PolicyLayer and add a rule for state_put: 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_put is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the state_put 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_put. 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_put 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 →