AI agents use lexq_facts_update 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 modifies existing fact definitions in the business rules system, which constitutes a Write operation. It is reversible (facts can be updated again to previous states) and not destructive.
From the tool's definition Tool description explicitly states 'Update a fact definition' with constraints on what can be modified. The verb 'Update' and the nature of modifying fact definitions (business logic data) indicates a reversible write operation.
Attacks that exploit this kind of access
Update a fact definition. Key and type cannot be changed. Only provided fields are updated. System facts only allow name and description changes. 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_update: 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_update 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_update 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_update. 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_update 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 →