Create a new review type with a custom schema
AI agents use add_review_type to create or update resources in Record MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Record MCP Server environment.
This tool creates new review types (schema definitions) but does not delete, overwrite irreversibly, or destroy data. Creation of schemas is reversible through modification or replacement. While it modifies the system state, it is fundamentally a Write operation (creates new data structures).
From the tool's definition Tool description states "Create a new review type with a custom schema" - the verb "Create" and context of managing dynamic review records indicates this tool creates new data structures/schemas that are reversibly modifiable.
Attacks that exploit this kind of access
Create a new review type with a custom schema. It is categorised as a Write tool in the Record MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Record MCP Server MCP server in PolicyLayer and add a rule for add_review_type: 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 Record MCP Server. Nothing to install.
add_review_type 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_review_type 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_review_type. 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_review_type is provided by the Record MCP Server MCP server (sanggggg/record-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 →