AI agents use set_project_agent_role to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates or modifies role assignments in a persistent data structure (the organization's role hierarchy). It is reversible (a role can be reassigned or revoked), so it does not qualify as Destructive. While it has governance implications, it does not directly move money (Financial) or execute external code (Execute). This is a Write operation that alters organizational metadata.
From the tool's definition Tool description states 'Assign an agent a role' — 'assign' indicates modification of role/permission data.
Attacks that exploit this kind of access
Assign an agent a role on a specific project (client, lead, developer, qa, reviewer, etc.). Per-project roles extend the global org chart. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for set_project_agent_role: 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.
set_project_agent_role is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_project_agent_role 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 set_project_agent_role. 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.
set_project_agent_role 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 →