AI agents invoke query-documents to trigger actions in Ravendb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Executing arbitrary RQL queries can encompass read operations, but RQL also supports update and patch operations (e.g., UPDATE clauses). The tool's blast radius is high because a malicious or erroneous query could modify or expose large amounts of data. Since the description says 'Execute RQL queries' without restricting to SELECT-only, the most severe applicable category is Execute.
From the tool's definition "Execute RQL queries" — the tool runs arbitrary RQL (RavenDB Query Language) queries against the database, whose effects depend entirely on the query arguments supplied.
Attacks that exploit this kind of access
Execute RQL queries with results handling. It is categorised as a Execute tool in the Ravendb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ravendb MCP server in PolicyLayer and add a rule for query-documents: 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.
query-documents is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query-documents 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 query-documents. 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.
query-documents 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 →