Check if a background command (started with run_background) has finished. Returns running=true/false, exit_code, and output so far. Use in a loop: wait(15) → check_command_status(pid) → repeat until running=false.
AI agents call check_command_status to retrieve information from DevToolkit MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a polling/status check operation with no side effects. It reads the state of an already-running process (running flag, exit code, accumulated output) but does not start, modify, stop, or affect the command itself. The worst misuse would be information disclosure if the output contains sensitive data, but that is an inherent property of the already-running command, not a capability of this tool.
From the tool's definition Tool queries status of a background command: 'Check if a background command...has finished. Returns running=true/false, exit_code, and output so far.' It only retrieves state information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Check if a background command (started with run_background) has finished. Returns running=true/false, exit_code, and output so far. Use in a loop: wait(15) → check_command_status(pid) → repeat until running=false. It is categorised as a Read tool in the DevToolkit MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DevToolkit MCP Server MCP server in PolicyLayer and add a rule for check_command_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 DevToolkit MCP Server. Nothing to install.
check_command_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 check_command_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 check_command_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.
check_command_status is provided by the DevToolkit MCP Server MCP server (tusharrayamajhi/devtoolkit-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 →