get-tasks-by-filter
AI agents call get-tasks-by-filter to retrieve information from Todoist MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries task data filtered by specified criteria. It performs no modifications, deletions, or side effects on the Todoist workspace. The 'get-' prefix is a strong indicator of read-only retrieval. Even without an explicit description, the naming pattern and context within a task management system clearly indicates this is a safe data retrieval operation with minimal blast radius if misused.
From the tool's definition Tool name 'get-tasks-by-filter' indicates retrieval/querying of tasks based on filter criteria. The server description mentions 'tracking productivity statistics' and context of task management tools that retrieve data.
Attacks that exploit this kind of access
get-tasks-by-filter. It is categorised as a Read tool in the Todoist MCP MCP Server, which means it retrieves data without modifying state.
Register the Todoist MCP server in PolicyLayer and add a rule for get-tasks-by-filter: 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 MCP. Nothing to install.
get-tasks-by-filter 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-tasks-by-filter 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-tasks-by-filter. 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-tasks-by-filter is provided by the Todoist MCP server (miottid/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 →