Retrieve the next single pending task from the active checklist. Returns
AI agents call get_pending_task to retrieve information from Subconductor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the active checklist without creating, modifying, or deleting any state. It is a simple query operation with no side effects, fitting the Read category. The severity is low because retrieving pending tasks poses minimal risk even if misused by an agent—it only exposes workflow state that the agent should already have access to.
From the tool's definition Tool name 'get_pending_task' and description 'Retrieve the next single pending task' indicate a read operation that queries state without modification.
Attacks that exploit this kind of access
Retrieve the next single pending task from the active checklist. Returns. It is categorised as a Read tool in the Subconductor MCP Server, which means it retrieves data without modifying state.
Register the Subconductor MCP server in PolicyLayer and add a rule for get_pending_task: 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 Subconductor. Nothing to install.
get_pending_task 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_pending_task 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_pending_task. 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_pending_task is provided by the Subconductor MCP server (paulbenchea/mcp-subconductor). 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 →