Fetch the full server-persisted event log of a managed cloud-agent session (user turns, agent thinking, tool_use, tool_result, status) — the transcript/artifact view, the CLOUD counterpart of wasm_agent_files. Use when native Read is wrong because the work happened in Anthropic\
AI agents call managed_agent_events to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries historical event data from a managed cloud-agent session without modifying, deleting, or executing operations. However, severity is elevated to 'medium' rather than 'low' because the event log may contain sensitive information about agent reasoning, tool usage, and user turns in a multi-tenant cloud environment.
From the tool's definition Tool description states 'Fetch the full server-persisted event log' and explicitly frames itself as retrieving/viewing a 'transcript/artifact'.
Attacks that exploit this kind of access
Fetch the full server-persisted event log of a managed cloud-agent session (user turns, agent thinking, tool_use, tool_result, status) — the transcript/artifact view, the CLOUD counterpart of wasm_agent_files. Use when native Read is wrong because the work happened in Anthropic\. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for managed_agent_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 Claude Flow. Nothing to install.
managed_agent_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 managed_agent_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 managed_agent_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.
managed_agent_events is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.