AI agents call get_productivity_stats to retrieve information from Todoist without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries productivity statistics from Todoist. It has no side effects, does not modify any data, does not execute code or commands, and does not affect financial obligations. It is a straightforward read operation accessing existing user metrics.
From the tool's definition Tool description states it 'Get[s] your Todoist productivity stats: karma score, task completion counts, streaks, and daily/weekly goals' — purely retrieval of existing data with no creation, modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Get your Todoist productivity stats: karma score, task completion counts, streaks, and daily/weekly goals. It is categorised as a Read tool in the Todoist MCP Server, which means it retrieves data without modifying state.
Register the Todoist MCP server in PolicyLayer and add a rule for get_productivity_stats: 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 Todoist. Nothing to install.
get_productivity_stats 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_productivity_stats 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_productivity_stats. 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_productivity_stats is provided by the Todoist MCP server (sjvadrevu/todoist-mcp-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 →