AI agents use pruva_update_document to create or update resources in Pruva — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pruva environment.
The tool creates or modifies data reversibly by updating an existing document. This falls clearly into the Write category. Severity is medium because document updates could affect downstream AI context and decision-making, but the operation is reversible (unlike Destructive actions) and carries less risk than Execute or Financial operations.
From the tool's definition Tool name contains 'update' and description states 'Update an existing context document', indicating modification of existing data.
Attacks that exploit this kind of access
Update an existing context document. It is categorised as a Write tool in the Pruva MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pruva MCP server in PolicyLayer and add a rule for pruva_update_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 Pruva. Nothing to install.
pruva_update_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 pruva_update_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 pruva_update_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.
pruva_update_document is provided by the Pruva MCP server (pruva-ai/pruva-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 →