AI agents call bulk_find_tasks_by_files to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only query operation that checks file paths for task information and returns status data. It has no side effects, creates no resources, executes no external operations, and modifies no state. The term 'collisions' refers to detected conflicts in the returned data, not to any action the tool takes.
From the tool's definition Tool name contains 'find' and description states it 'Check multiple file paths' and 'Returns per-path task list, in-progress count, and conflict flag' — purely retrieves and queries data about task state without modifying anything.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Check multiple file paths at once for task/agent collisions. Returns per-path task list, in-progress count, and conflict flag. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for bulk_find_tasks_by_files: 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 Todos. Nothing to install.
bulk_find_tasks_by_files 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 bulk_find_tasks_by_files 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 bulk_find_tasks_by_files. 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.
bulk_find_tasks_by_files is provided by the Todos MCP server (@hasna/todos). 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 →