List actions/tasks. Can filter by project or status.
AI agents call get_actions to retrieve information from Exponential MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing actions/tasks with optional filtering. No data is created, modified, deleted, or executed. It has no side effects beyond returning information, making it a read-only operation with low severity and wide applicability.
From the tool's definition Tool name 'get_actions' and description 'List actions/tasks' indicate a retrieval operation. The ability to 'filter by project or status' are query parameters that do not modify data.
Attacks that exploit this kind of access
List actions/tasks. Can filter by project or status. It is categorised as a Read tool in the Exponential MCP MCP Server, which means it retrieves data without modifying state.
Register the Exponential MCP server in PolicyLayer and add a rule for get_actions: 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 Exponential MCP. Nothing to install.
get_actions 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_actions 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_actions. 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_actions is provided by the Exponential MCP server (positonic/exponential-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 →