Medium Risk

create_concierge

[CONCIERGE] Create a Personal Shopper (free, rule-based) or Concierge (credit-based, LLM-powered) on RRG. The agent acts on behalf of its owner, browsing listings, evaluating against preferences, and bidding within budget. Returns the agent ID and session details. The created agent can be managed...

Risk signalsHigh parameter count (11 properties)

Part of the Real Real Genuine server.

create_concierge can modify Real Real Genuine data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE REAL REAL GENUINE →

Free to start. No card required.

AI agents use create_concierge to create or modify resources in Real Real Genuine. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call create_concierge repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Real Real Genuine.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_concierge": {
      "limits": [
        {
          "counter": "create_concierge_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Real Real Genuine policy for all 32 tools.

Get this rule live on your own Real Real Genuine server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY REAL REAL GENUINE →

View all 32 tools →

These attack patterns abuse exactly the kind of access create_concierge gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so create_concierge only ever does what you allow.

SECURE REAL REAL GENUINE →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the create_concierge tool do? +

[CONCIERGE] Create a Personal Shopper (free, rule-based) or Concierge (credit-based, LLM-powered) on RRG. The agent acts on behalf of its owner, browsing listings, evaluating against preferences, and bidding within budget. Returns the agent ID and session details. The created agent can be managed via the dashboard at realrealgenuine.com/agents/dashboard.. It is categorised as a Write tool in the Real Real Genuine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_concierge? +

Register the Real Real Genuine MCP server in PolicyLayer and add a rule for create_concierge: 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 Real Real Genuine. Nothing to install.

What risk level is create_concierge? +

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

Can I rate-limit create_concierge? +

Yes. Add a rate_limit block to the create_concierge 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 create_concierge completely? +

Set action: deny in the PolicyLayer policy for create_concierge. 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 create_concierge? +

create_concierge is provided by the Real Real Genuine MCP server (https://realrealgenuine.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Real Real Genuine tool call.

Deterministic rules across all 32 Real Real Genuine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.