Returns the first unbuilt item. Priority: Models -> Routes -> Tests.
AI agents call get_next_pending_task to retrieve information from Backend Architect MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although this is a Read operation, severity is high because it provides task sequencing information that an AI agent could misuse to bypass the structured workflow or prioritize destructive operations (e.g., retrieving a test task that deletes data, then skipping to execute it).
From the tool's definition Tool returns data ('Returns the first unbuilt item') without modifying state, matching the Read category pattern of retrieval operations.
Attacks that exploit this kind of access
Returns the first unbuilt item. Priority: Models -> Routes -> Tests. It is categorised as a Read tool in the Backend Architect MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Backend Architect MCP Server MCP server in PolicyLayer and add a rule for get_next_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 Backend Architect MCP Server. Nothing to install.
get_next_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_next_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_next_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_next_pending_task is provided by the Backend Architect MCP Server MCP server (jemhakdog/mcp_fastapi). 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 →