environment_list
AI agents call environment_list 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 tool name 'environment_list' strongly indicates a list operation that queries or enumerates environments without modification. No description is provided, but the naming convention and sibling tools (all read-only operations like get, list, events, archive) establish a clear pattern. This tool almost certainly retrieves configuration or environment data.
From the tool's definition Tool name 'environment_list' and contextual pattern matching sibling tools (environment_get, memory_store_get, memory_store_list, session_get, session_events, session_archive) which are all query/retrieval operations.
Attacks that exploit this kind of access
environment_list. 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 environment_list: 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.
environment_list 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 environment_list 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 environment_list. 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.
environment_list 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 →