Store email/password for automatic token refresh. Credentials are encrypted.
AI agents use set_login to create or update resources in Restaurant Reservation MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Restaurant Reservation MCP Server environment.
This tool creates or modifies authentication credentials persistently. While it doesn't delete data (not Destructive) or execute arbitrary code (not Execute), it irreversibly establishes a write operation by storing secrets for future use.
From the tool's definition Tool stores credentials (email/password) for automatic token refresh. Description indicates persistent modification of authentication state through credential storage.
Attacks that exploit this kind of access
Store email/password for automatic token refresh. Credentials are encrypted. It is categorised as a Write tool in the Restaurant Reservation MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Restaurant Reservation MCP Server MCP server in PolicyLayer and add a rule for set_login: 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 Restaurant Reservation MCP Server. Nothing to install.
set_login 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 set_login 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 set_login. 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.
set_login is provided by the Restaurant Reservation MCP Server MCP server (jrklein343-svg/restaurant-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 →