AI agents use store-document to create or update resources in Ravendb — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ravendb environment.
This tool creates new documents or modifies existing ones, which are reversible operations typical of Write category. While the blast radius is non-negligible (an agent could create unwanted documents or corrupt data through updates), the operations are not destructive (can be undone via delete/update) and do not execute arbitrary code or move funds.
From the tool's definition Tool name 'store-document' and description 'Create or update a document' indicate reversible data modification operations on a RavenDB database. The operation is clearly write-oriented with no permanent destructive capability.
Attacks that exploit this kind of access
Create or update a document. It is categorised as a Write tool in the Ravendb MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ravendb MCP server in PolicyLayer and add a rule for store-document: 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 Ravendb. Nothing to install.
store-document 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-document 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-document. 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-document is provided by the Ravendb MCP server (johnib/ravendb-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 →