AI agents call summarize_by_status to retrieve information from Mcp Tasks without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Summarize_by_status queries the task database to compute aggregate statistics (task counts by status). This is a pure read operation that generates no side effects, leaves no data modified, and poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'Return counts of tasks grouped by status' — this retrieves and aggregates data without modification. No deletion, creation, execution, or financial operations are involved.
Attacks that exploit this kind of access
Return counts of tasks grouped by status. It is categorised as a Read tool in the Mcp Tasks MCP Server, which means it retrieves data without modifying state.
Register the Mcp Tasks MCP server in PolicyLayer and add a rule for summarize_by_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 Mcp Tasks. Nothing to install.
summarize_by_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 summarize_by_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 summarize_by_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.
summarize_by_status is provided by the Mcp Tasks MCP server (kanaparthikiran/mcp-tasks-server). 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 →