AI agents call find_tasks 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.
The tool name and position among retrieval-focused sibling tools (all prefixed with 'get' or 'find') strongly suggest this retrieves task data with no side effects. The empty description prevents full certainty, but the naming pattern and server's stated 'reading' capability make a Read classification appropriate.
From the tool's definition Tool name 'find_tasks' and server description indicating 'reading' tasks as part of 'task management.' Sibling tools like 'find_tasks_by_date', 'get_comments', 'get_projects', 'get_sections', and 'get_overview' all perform retrieval operations without…
Attacks that exploit this kind of access
find_tasks. 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 find_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 Todoist. Nothing to install.
find_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 find_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 find_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.
find_tasks is provided by the Todoist MCP server (kpanko/todoist-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 →