List recent runs for an agent with their status and duration.
AI agents call list_executions to retrieve information from Spaceship 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 displays historical execution data without creating, modifying, deleting, or executing anything. It is purely informational and has minimal blast radius if misused by an agent—at worst, an agent would gain visibility into past run history.
From the tool's definition The tool is named 'list_executions' and described as listing 'recent runs for an agent with their status and duration.' The verb 'list' and the retrieval-only nature of the operation (status and duration are query results) indicate no modification or side…
Attacks that exploit this kind of access
List recent runs for an agent with their status and duration. It is categorised as a Read tool in the Spaceship MCP MCP Server, which means it retrieves data without modifying state.
Register the Spaceship MCP server in PolicyLayer and add a rule for list_executions: 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 Spaceship MCP. Nothing to install.
list_executions 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 list_executions 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 list_executions. 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.
list_executions is provided by the Spaceship MCP server (spaceship-ai/spaceship-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 →