get_completed_tasks
AI agents call get_completed_tasks to retrieve information from Todoist MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves completed task data with no side effects. It performs a query/fetch operation on existing data. Absence of description lowers confidence slightly, but the 'get_' prefix and context of a task management system clearly indicate read-only retrieval.
From the tool's definition Tool name is 'get_completed_tasks' with no description provided. The name indicates a retrieval operation on completed tasks. This is consistent with the server's 'read' capabilities mentioned in the server description ('read tasks').
Attacks that exploit this kind of access
get_completed_tasks. It is categorised as a Read tool in the Todoist MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Todoist MCP Server MCP server in PolicyLayer and add a rule for get_completed_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 MCP Server. Nothing to install.
get_completed_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_completed_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_completed_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_completed_tasks is provided by the Todoist MCP Server MCP server (stevesimpson418/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 →