Search for tasks by name using partial/fuzzy matching.
AI agents call search_task_by_name to retrieve information from Todoist MCP Helper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves task data based on search criteria without modifying, deleting, or executing any operations. It is a simple information retrieval function comparable to standard search/query operations. Even in the context of an AI agent with access to task management, searching tasks poses minimal risk—worst case is returning unintended results or excessive query volume.
From the tool's definition Tool description explicitly states 'Search for tasks by name' with 'partial/fuzzy matching', which is a read-only query operation with no side effects.
Attacks that exploit this kind of access
Search for tasks by name using partial/fuzzy matching. It is categorised as a Read tool in the Todoist MCP Helper MCP Server, which means it retrieves data without modifying state.
Register the Todoist MCP Helper MCP server in PolicyLayer and add a rule for search_task_by_name: 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 Helper. Nothing to install.
search_task_by_name 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 search_task_by_name 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 search_task_by_name. 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.
search_task_by_name is provided by the Todoist MCP Helper MCP server (littlepeter52012/todoist-mcp-helper). 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 →