Create a relationship between two entities AND save state.
AI agents use add_fact to create or update resources in Alethea World History Engine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Alethea World History Engine environment.
The tool creates new relationships in the narrative graph and persists changes ('save state'), which is a write operation that modifies the underlying data model. This falls under Write rather than Read (which would only retrieve data) or Destructive (since relationships can be removed/modified later).
From the tool's definition Tool description states 'Create a relationship between two entities AND save state' - the action of creating a relationship and persisting state changes indicates reversible data modification rather than retrieval or destruction.
Attacks that exploit this kind of access
Create a relationship between two entities AND save state. It is categorised as a Write tool in the Alethea World History Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Alethea World History Engine MCP server in PolicyLayer and add a rule for add_fact: 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 Alethea World History Engine. Nothing to install.
add_fact 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 add_fact 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 add_fact. 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.
add_fact is provided by the Alethea World History Engine MCP server (watashicuvu/world-history-engine). 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 →