Search tasks with filters
AI agents call tududi_search_tasks to retrieve information from Tududi MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves task data based on filter criteria. It performs a non-destructive read operation with no side effects. Although the server includes destructive tools like tududi_delete_task and write operations like tududi_create_task and tududi_update_task, this specific tool only searches and returns matching results.
From the tool's definition Tool name contains 'search' and description states 'Search tasks with filters' - a query operation that retrieves data without modifying it.
Attacks that exploit this kind of access
Search tasks with filters. It is categorised as a Read tool in the Tududi MCP MCP Server, which means it retrieves data without modifying state.
Register the Tududi MCP server in PolicyLayer and add a rule for tududi_search_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 Tududi MCP. Nothing to install.
tududi_search_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 tududi_search_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 tududi_search_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.
tududi_search_tasks is provided by the Tududi MCP server (jerrytunin/tududi-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 →