agent_get
AI agents call agent_get to retrieve information from Managed Agent Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get' suffix and sibling tool patterns strongly suggest this performs a read operation (retrieves agent data). However, the empty description introduces uncertainty about whether it might return sensitive agent state information or configuration that could be misused by an AI agent (justifying 'medium' rather than 'low' severity). Confidence is reduced due to the missing description.
From the tool's definition Tool name 'agent_get' suggests retrieval of agent data. The server context indicates it is used to 'observe and interact with Claude Managed Agents', and sibling tools like 'agent_list', 'session_get', 'environment_get', and 'memory_store_get' are all read…
Attacks that exploit this kind of access
agent_get. It is categorised as a Read tool in the Managed Agent Control MCP Server, which means it retrieves data without modifying state.
Register the Managed Agent Control MCP server in PolicyLayer and add a rule for agent_get: 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 Managed Agent Control. Nothing to install.
agent_get 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 agent_get 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 agent_get. 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.
agent_get is provided by the Managed Agent Control MCP server (modus-agendi/managed-agent-control-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 →