AI agents call vibekit_agent_history to retrieve information from Vibekit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical chat messages associated with an app. It is a read-only operation that queries and returns data without altering state, executing code, or causing irreversible changes. The blast radius of misuse is minimal—an unauthorized actor could view conversation history but cannot modify, delete, or execute operations through this tool alone.
From the tool's definition Tool name 'vibekit_agent_history' and description 'Get the chat history with an app' indicate retrieval of existing data with no modification, deletion, or side effects.
Attacks that exploit this kind of access
Get the chat history with an app. It is categorised as a Read tool in the Vibekit MCP Server, which means it retrieves data without modifying state.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_agent_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 Vibekit. Nothing to install.
vibekit_agent_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 vibekit_agent_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 vibekit_agent_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.
vibekit_agent_history is provided by the Vibekit MCP server (vibekit-apps/vibekit-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 →