Gets events filtered by action type
AI agents call get_events_by_action to retrieve information from Smartsheet MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves event data based on action type filters. It performs no creation, modification, deletion, execution, or financial operations. The blast radius is minimal—an agent querying events cannot cause harm beyond potentially accessing audit logs or event records, which is a standard read operation.
From the tool's definition Tool name 'get_events_by_action' and description 'Gets events filtered by action type' indicate a retrieval operation with no side effects. The verb 'gets' and the filtering capability are consistent with read-only query operations.
Attacks that exploit this kind of access
Gets events filtered by action type. It is categorised as a Read tool in the Smartsheet MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smartsheet MCP Server MCP server in PolicyLayer and add a rule for get_events_by_action: 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 Smartsheet MCP Server. Nothing to install.
get_events_by_action is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_events_by_action 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 get_events_by_action. 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.
get_events_by_action is provided by the Smartsheet MCP Server MCP server (thomaswtwrt/smar-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 →