refresh_feature_data
AI agents use refresh_feature_data to create or update resources in Sablier MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sablier MCP Server environment.
The name implies a data refresh or update operation, which is a Write action. However, with no description available, confidence is low. It could also be a Read (fetching fresh data) or Execute (triggering a pipeline). Given sibling tools like 'add_feature' and 'add_features_batch', a Write classification is most plausible, but severity is kept medium due to uncertainty.
From the tool's definition Tool name 'refresh_feature_data' suggests updating or reloading data; description is empty and uninformative.
Attacks that exploit this kind of access
refresh_feature_data. It is categorised as a Write tool in the Sablier MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sablier MCP Server MCP server in PolicyLayer and add a rule for refresh_feature_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 Sablier MCP Server. Nothing to install.
refresh_feature_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 refresh_feature_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 refresh_feature_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.
refresh_feature_data is provided by the Sablier MCP Server MCP server (sablier-ai/sablier-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 →