AI agents call find_tasks_by_git_ref 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 tool queries and retrieves information about task-to-git-ref relationships without creating, modifying, or deleting any data. It is a lookup/search operation typical of Read category tools. The low severity reflects that retrieving task metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool description states 'Find tasks linked to a branch name, PR number, or PR URL' - the verb 'find' and action of querying/retrieving task associations indicates a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
Find tasks linked to a branch name, PR number, or PR URL. 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 find_tasks_by_git_ref: 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.
find_tasks_by_git_ref 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 find_tasks_by_git_ref 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 find_tasks_by_git_ref. 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.
find_tasks_by_git_ref 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 →