Medium Risk

send_driver_contact

Email the booking's client their assigned driver's first name + phone. Pass email if you already have the client's address (e.g. from Zeplan get-booking); otherwise WP looks it up on the booking post. Returns { sent, to (masked), client_phone }. Voice agent use.

Part of the Booking server.

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

SECURE BOOKING →

Free to start. No card required.

AI agents use send_driver_contact to create or modify resources in Booking. 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 send_driver_contact 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 Booking.

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

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

See the full Booking policy for all 8 tools.

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

ENFORCE ON MY BOOKING →

These attack patterns abuse exactly the kind of access send_driver_contact 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 send_driver_contact only ever does what you allow.

SECURE BOOKING →

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

What does the send_driver_contact tool do? +

Email the booking's client their assigned driver's first name + phone. Pass email if you already have the client's address (e.g. from Zeplan get-booking); otherwise WP looks it up on the booking post. Returns { sent, to (masked), client_phone }. Voice agent use.. It is categorised as a Write tool in the Booking MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_driver_contact? +

Register the Booking MCP server in PolicyLayer and add a rule for send_driver_contact: 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 Booking. Nothing to install.

What risk level is send_driver_contact? +

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

Can I rate-limit send_driver_contact? +

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

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

send_driver_contact is provided by the Booking MCP server (https://mcp-mydriverparis.mydriverparis.workers.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Booking tool call.

Deterministic rules across all 8 Booking 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.