Create a new knowledge base with embedding model configuration.
AI agents use create_kb to create or update resources in MindsDB MySQL MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MindsDB MySQL MCP Server environment.
This tool creates a new knowledge base, which is a Write action—it adds new data/structure to the system. It is not Read (no mere retrieval), not Execute (no arbitrary code/command execution), not Destructive (creation is reversible), and not Financial.
From the tool's definition Tool name 'create_kb' and description 'Create a new knowledge base with embedding model configuration' indicate creation of a new data structure.
Attacks that exploit this kind of access
Create a new knowledge base with embedding model configuration. It is categorised as a Write tool in the MindsDB MySQL MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MindsDB MySQL MCP Server MCP server in PolicyLayer and add a rule for create_kb: 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 MindsDB MySQL MCP Server. Nothing to install.
create_kb 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 create_kb 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 create_kb. 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.
create_kb is provided by the MindsDB MySQL MCP Server MCP server (nikhgupta/mindsdb-mysql-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 →