AI agents call get_history to retrieve information from AgentChat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical conversation messages without side effects. It is a read-only query operation that does not create, modify, delete, or execute code. The only action is fetching and returning stored message data, which is characteristic of the Read category.
From the tool's definition Tool name 'get_history' and description 'Return the most recent messages in the conversation' indicate retrieval of existing data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Return the most recent messages in the conversation (default last 50). It is categorised as a Read tool in the AgentChat MCP Server, which means it retrieves data without modifying state.
Register the AgentChat MCP server in PolicyLayer and add a rule for get_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 AgentChat. Nothing to install.
get_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_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_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_history is provided by the AgentChat MCP server (jimmyfaqwq/agentchat-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 →