AI agents use lexq_facts_create to create or update resources in LexQ — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LexQ environment.
This tool creates or registers new facts/variables that feed into the business rules engine, modifying the system's configuration reversibly. The action creates data (variable definitions) but is not destructive. While the system context involves rule management and potential deployments, the tool itself only registers input variable schemas, which is a Write operation.
From the tool's definition 'Register a new input variable' creates a new configuration item (fact/variable) in the business rules system.
Attacks that exploit this kind of access
Register a new input variable. Key must be lowercase with underscores (e.g. payment_amount). Types: STRING, NUMBER, BOOLEAN, LIST_STRING, LIST_NUMBER. It is categorised as a Write tool in the LexQ MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LexQ MCP server in PolicyLayer and add a rule for lexq_facts_create: 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 LexQ. Nothing to install.
lexq_facts_create 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 lexq_facts_create 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 lexq_facts_create. 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.
lexq_facts_create is provided by the LexQ MCP server (lexq-io/lexq-cli). 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 →