AI agents call get_overdue_tasks to retrieve information from Jamot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple read-only query against task records to identify overdue incomplete tasks. It does not create, modify, delete, execute code, or move money. The retrieval of overdue task metadata presents minimal risk to the system — the worst case is the agent acts on incomplete information, which is a business logic concern rather than a security violation.
From the tool's definition Tool description states 'Find all tasks that are past their due date and not yet completed' — a query operation that retrieves task data without modifying or deleting anything. The verb 'Find' indicates a retrieval/search action with no side effects.
Attacks that exploit this kind of access
Find all tasks that are past their due date and not yet completed. It is categorised as a Read tool in the Jamot MCP MCP Server, which means it retrieves data without modifying state.
Register the Jamot MCP server in PolicyLayer and add a rule for get_overdue_tasks: 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 Jamot MCP. Nothing to install.
get_overdue_tasks 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_overdue_tasks 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_overdue_tasks. 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_overdue_tasks is provided by the Jamot MCP server (jamot-pro/jamot-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 →