Unlock a user account
AI agents use unlock_user to create or update resources in Tonle OpenProject MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tonle OpenProject MCP Server environment.
Unlocking a user account modifies user state but is reversible and does not permanently destroy data. While it grants access that was previously restricted, the action can be undone by locking the account again. This qualifies as a Write operation rather than Execute (no arbitrary code/command invocation) or Destructive (reversible).
From the tool's definition Tool name 'unlock_user' and description 'Unlock a user account' indicate a state change to a user object that is reversible (can be locked again).
Attacks that exploit this kind of access
Unlock a user account. It is categorised as a Write tool in the Tonle OpenProject MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tonle OpenProject MCP Server MCP server in PolicyLayer and add a rule for unlock_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 Tonle OpenProject MCP Server. Nothing to install.
unlock_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 unlock_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 unlock_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.
unlock_user is provided by the Tonle OpenProject MCP Server MCP server (liratanak/openproject-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 →