Store information with a key. The value can be any JSON-serializable data.
AI agents use store_data to create or update resources in Store MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Store MCP Server environment.
This tool writes data persistently to a key-value store. It creates or overwrites entries but does not irreversibly destroy data (deletion is handled by a sibling tool). Misuse could lead to data corruption or overwriting of important stored information, warranting a medium severity.
From the tool's definition 'Store information with a key. The value can be any JSON-serializable data.' — creates or modifies persistent key-value entries in JSON file-based storage.
Attacks that exploit this kind of access
Store information with a key. The value can be any JSON-serializable data. It is categorised as a Write tool in the Store MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Store MCP Server MCP server in PolicyLayer and add a rule for store_data: 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 Store MCP Server. Nothing to install.
store_data 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_data 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_data. 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_data is provided by the Store MCP Server MCP server (mariano-cecowski/store_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 →