Retrieves details, progress, and results of an active asynchronous run using runId. The status field in response can be
AI agents call get_run_status to retrieve information from FullMention without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and reads status information about an existing run. It performs no creation, modification, deletion, or execution of operations. The action is informational only, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'get_run_status' and description states it 'Retrieves details, progress, and results of an active asynchronous run' — a pure query operation with no side effects.
Attacks that exploit this kind of access
Retrieves details, progress, and results of an active asynchronous run using runId. The status field in response can be. It is categorised as a Read tool in the FullMention MCP Server, which means it retrieves data without modifying state.
Register the FullMention MCP server in PolicyLayer and add a rule for get_run_status: 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 FullMention. Nothing to install.
get_run_status 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_status 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_status. 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_status is provided by the FullMention MCP server (riisager/fullmention-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 →