AI agents use store_put to create or update resources in Willow — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Willow environment.
store_put creates new records in a key/value store with persistent side effects. It is reversible (via store_delete), so it qualifies as Write rather than Destructive. The append-only nature and multi-application access context (SAP/1.0 auth) mean misuse could corrupt application state, justifying medium severity. Confidence is high because the description explicitly states the write semantics.
From the tool's definition Tool description states 'Write a record to a named collection' — this is a create/insert operation that modifies data.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Write a record to a named collection. Append-only — every write gets a unique ID. It is categorised as a Write tool in the Willow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Willow MCP server in PolicyLayer and add a rule for store_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 Willow. Nothing to install.
store_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 store_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 store_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.
store_put is provided by the Willow MCP server (rudi193-cmd/willow-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 →