Remove a configured local agent run adapter.
AI agents call remove_agent_run_adapter to permanently remove resources in Todos — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes a configured adapter, preventing its future use. While the blast radius depends on how critical that adapter is to the system, removing run adapters could break agent execution workflows. The absence of any mention of recovery or reversibility, combined with the destructive verb 'remove', places this in the Destructive category rather than Write.
From the tool's definition Tool name includes 'remove' which indicates deletion; description states 'Remove a configured local agent run adapter' with no undo mechanism specified.
Attacks that exploit this kind of access
Remove a configured local agent run adapter. It is categorised as a Destructive tool in the Todos MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Todos MCP server in PolicyLayer and add a rule for remove_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.
remove_agent_run_adapter is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_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 remove_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.
remove_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 →