Get full message history for a session.
AI agents call get_chat_history to retrieve information from AgentSpawnMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing chat history data without modifying, executing, or deleting anything. It is a straightforward query operation with no side effects. The severity is low because retrieving chat history, while potentially containing sensitive information depending on context, does not directly cause harm through the tool itself. Confidence is high given the explicit 'Get' language and read-only semantics.
From the tool's definition Tool name is 'get_chat_history' and description states 'Get full message history for a session.' The verb 'Get' and lack of any modification, deletion, or side-effect language clearly indicate a retrieval operation.
Attacks that exploit this kind of access
Get full message history for a session. It is categorised as a Read tool in the AgentSpawnMCP MCP Server, which means it retrieves data without modifying state.
Register the AgentSpawn MCP server in PolicyLayer and add a rule for get_chat_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 AgentSpawnMCP. Nothing to install.
get_chat_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_chat_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_chat_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_chat_history is provided by the AgentSpawn MCP server (sandsaber/agentspawnmcp). 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 →