get_run_logs
AI agents call get_run_logs 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 or queries log data from agent runs without modifying, deleting, or executing anything. It is a read-only operation with minimal blast radius—an AI agent cannot cause harm simply by retrieving logs, though logs may contain sensitive information.
From the tool's definition Tool name 'get_run_logs' indicates retrieval of log data. The verb 'get' is a classic read operation. The context of 'run statuses and logs' mentioned in server description confirms this retrieves existing data without modification.
Attacks that exploit this kind of access
get_run_logs. 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 get_run_logs: 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.
get_run_logs 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_run_logs 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_run_logs. 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_run_logs 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 →