Save the current dataset to a file (.omv format).
AI agents use jamovi_save to create or update resources in jamovi MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your jamovi MCP environment.
The tool creates or updates a file on disk (the .omv dataset file). While this is persistent and could overwrite an existing file, it is not irreversible in the destructive sense—the original in-memory dataset state remains, backups may exist, and the file can be deleted or replaced. It modifies data state reversibly relative to the primary dataset. This is a classic Write operation.
From the tool's definition Tool is described as "Save the current dataset to a file (.omv format)." This operation creates or persists data in a new file location, modifying the filesystem state.
Attacks that exploit this kind of access
Save the current dataset to a file (.omv format). It is categorised as a Write tool in the jamovi MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the jamovi MCP server in PolicyLayer and add a rule for jamovi_save: 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 jamovi MCP. Nothing to install.
jamovi_save 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 jamovi_save 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 jamovi_save. 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.
jamovi_save is provided by the jamovi MCP server (yjm110517/jamovi-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 →