Store chat history in the database
AI agents use store_chat_history to create or update resources in Small Business MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Small Business MCP Server environment.
This tool writes chat history records to a database, which is a reversible data creation/modification operation. Misuse could allow an AI agent to store false or manipulated conversation records, polluting audit trails or misleading users, hence medium severity.
From the tool's definition 'Store chat history in the database' — creates/persists new records in a database
Attacks that exploit this kind of access
Store chat history in the database. It is categorised as a Write tool in the Small Business MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Small Business MCP Server MCP server in PolicyLayer and add a rule for store_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 Small Business MCP Server. Nothing to install.
store_chat_history is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the store_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 store_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.
store_chat_history is provided by the Small Business MCP Server MCP server (joe-spencer/small-business-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 →