添加新用户
AI agents use add_user to create or update resources in MCP Test Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Test Server environment.
This tool creates new user records, modifying the user database by adding entries. It is reversible (users can typically be deleted or modified later), so it falls under Write rather than Destructive. Severity is medium because adding unauthorized users could lead to unauthorized access or data management issues, but the blast radius depends on the system's user management constraints.
From the tool's definition Tool name 'add_user' and description '添加新用户' (Chinese for 'add new user') indicate creation of new user data, which is a write operation.
Attacks that exploit this kind of access
添加新用户. It is categorised as a Write tool in the MCP Test Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Test Server MCP server in PolicyLayer and add a rule for add_user: 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 Test Server. Nothing to install.
add_user 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_user 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_user. 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_user is provided by the MCP Test Server MCP server (small-tou/mcp-test). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
add_user is one line of MCP Test Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →