AI agents use set_agent_run_adapter 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 updates adapter commands, which is a Write operation that modifies stored configuration data. It's not destructive since updates can be reversed, not financial, and doesn't execute code directly (it creates/stores adapter definitions).
From the tool's definition Tool description states 'Create or update a local agent run adapter command', which involves creating or modifying configuration/adapter data. The action is reversible through subsequent updates or deletion.
Attacks that exploit this kind of access
Create or update a local agent run adapter command. Supports {task_id}, {run_id}, and {agent_id} placeholders. 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_agent_run_adapter: 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_agent_run_adapter 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_agent_run_adapter 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_agent_run_adapter. 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_agent_run_adapter 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 →