Remove a tool (by name) from a single_prompt agent. Works for any tool type (api_call, transfer_call, etc.).
AI agents call remove_agent_tool to permanently remove resources in Smallest — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a tool from an agent is an irreversible destructive action — it deletes the tool configuration from the agent. While the tool itself (e.g., an API call definition) might be re-added manually, the removal itself is not automatically undoable and could break agent functionality.
From the tool's definition Remove a tool (by name) from a single_prompt agent
Attacks that exploit this kind of access
Remove a tool (by name) from a single_prompt agent. Works for any tool type (api_call, transfer_call, etc.). It is categorised as a Destructive tool in the Smallest MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Smallest MCP server in PolicyLayer and add a rule for remove_agent_tool: 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 Smallest. Nothing to install.
remove_agent_tool 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_tool 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_tool. 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_tool is provided by the Smallest MCP server (@developer-smallestai/smallest-mcp-server). 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 →