add_domain · UseGrant MCP Server MCP: Risk & Policy

WHAT IT DOES

What add_domain does on UseGrant MCP Server

AI agents use add_domain to create or update resources in UseGrant MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UseGrant MCP Server environment.

WHY IT NEEDS A POLICY

Why add_domain needs a policy

This tool creates or modifies provider configuration by adding a domain, which is a reversible write operation. While it affects access control infrastructure (medium severity given the context of the UseGrant platform managing authentication/authorization), it does not delete data, execute arbitrary code, or move money. The impact is scoped to domain configuration for a specific provider.

From the tool's definition Tool name 'add_domain' and description 'Add a domain to a provider' indicate a create/modify operation on provider configuration.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_domain Rate-limited

add_domain stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_domain": {
      "limits": [
        {
          "counter": "add_domain_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches UseGrant MCP Server, so you can run agents against it safely.

FAQ

Questions about add_domain

What does the add_domain tool do? +

Add a domain to a provider. It is categorised as a Write tool in the UseGrant MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_domain? +

Register the UseGrant MCP Server MCP server in PolicyLayer and add a rule for add_domain: 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 UseGrant MCP Server. Nothing to install.

What risk level is add_domain? +

add_domain is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_domain? +

Yes. Add a rate_limit block to the add_domain 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.

How do I block add_domain completely? +

Set action: deny in the PolicyLayer policy for add_domain. 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.

What MCP server provides add_domain? +

add_domain is provided by the UseGrant MCP Server MCP server (usegranthq/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.