Creates a new personality trait.
AI agents use create_trait to create or update resources in MCP Traits Matcher — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Traits Matcher environment.
This tool creates new data (a personality trait) in the system. It is a Write operation because it modifies the server's data store by adding a new trait, which is reversible through deletion. There is no side effect that triggers external operations (Execute), no financial impact, and no irreversible destruction.
From the tool's definition Tool name 'create_trait' and description 'Creates a new personality trait' indicate irreversible creation of new data in the traits system.
Attacks that exploit this kind of access
Creates a new personality trait. It is categorised as a Write tool in the MCP Traits Matcher MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Traits Matcher MCP server in PolicyLayer and add a rule for create_trait: 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 MCP Traits Matcher. Nothing to install.
create_trait 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_trait 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_trait. 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_trait is provided by the MCP Traits Matcher MCP server (waifuai/mcp-traits-matcher). 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 →