session_events
AI agents call session_events 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.
Given the context of a managed agent control system where observation is a primary use case, and the sibling tools being mostly read-only queries, session_events most likely retrieves or streams session event data without modifying state. The empty description lowers confidence slightly, but the naming convention and server design strongly suggest this is a Read operation.
From the tool's definition Tool name 'session_events' is paired with a set of sibling tools that are mostly observational (agent_get, agent_list, environment_get, environment_list, memory_store_get, memory_store_list, session_get).
Attacks that exploit this kind of access
session_events. 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 session_events: 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.
session_events 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 session_events 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 session_events. 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.
session_events 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 →