최근 Multi-Agent 실행 이력을 반환합니다.
AI agents call get_execution_history to retrieve information from MCP Multi-Agent Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and retrieves past execution records. It has no side effects, does not modify data, does not execute code or external operations, and does not delete or move resources. This is a straightforward data retrieval operation, characteristic of the Read category.
From the tool's definition Tool name 'get_execution_history' and description indicating it 'returns recent Multi-Agent execution history' — this retrieves historical logs/records without modifying or executing operations.
Attacks that exploit this kind of access
최근 Multi-Agent 실행 이력을 반환합니다. It is categorised as a Read tool in the MCP Multi-Agent Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Multi-Agent Server MCP server in PolicyLayer and add a rule for get_execution_history: 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 MCP Multi-Agent Server. Nothing to install.
get_execution_history 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 get_execution_history 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 get_execution_history. 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.
get_execution_history is provided by the MCP Multi-Agent Server MCP server (sunnylabtv-crypto/ai_mcp_multi_agent-public). 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 →