AI agents call list-todos to retrieve information from Mmc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing workflow todo items without modifying, deleting, or executing operations. It is purely informational—retrieving and filtering data based on role criteria. The blast radius of misuse is minimal since no actions are triggered, data is not modified, and no external operations are invoked. This falls squarely into the Read category.
From the tool's definition Tool description states it 'List[s] pending work items' and 'Filter[s] by role', which are query operations with no side effects. The verb 'list' and the read-only nature of filtering existing data confirm this is a retrieval operation.
Attacks that exploit this kind of access
List pending work items (todos) created by the workflow engine. Filter by role to see only items relevant to your role. It is categorised as a Read tool in the Mmc MCP Server, which means it retrieves data without modifying state.
Register the Mmc MCP server in PolicyLayer and add a rule for list-todos: 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 Mmc. Nothing to install.
list-todos 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 list-todos 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 list-todos. 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.
list-todos is provided by the Mmc MCP server (modelmycontext/mmc-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 →