MCP Server
Let Claude, ChatGPT, Cursor or any MCP-compatible AI client check WhatsApp numbers directly - no code required, just your API key.
What is MCP?
Let your AI assistant use WA Validator as a tool
The Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude, ChatGPT and Cursor call external tools directly during a conversation. Once connected, you can just ask your AI assistant to check a number, and it will call the WA Validator checker for you and read back the result — no manual API calls, no code.
The WA Validator MCP server exposes two tools: check_whatsapp_number
and bulk_check_whatsapp_numbers.
Both run against the same credits, rate limits and validation engine as the REST
API.
Authentication
Your API key is your MCP credential
The MCP server uses the exact same API key as the REST API. Generate one from your dashboard, then send it as a Bearer token on every request to the MCP endpoint.
Authorization: Bearer YOUR_API_KEY
Keep your API key secure!
Only paste your key into your own AI client's trusted configuration file. Never share it or paste it into a public chat.
Server URL
Streamable HTTP transport
Point your MCP client at:
https://wavalidator.com/mcp/
This is a stateless MCP server using the Streamable HTTP transport (JSON-RPC 2.0 over a single POST endpoint) — no local install required.
Connect Your Client
Configure once, use in every conversation
Run this in your terminal:
claude mcp add --transport http wavalidator https://wavalidator.com/mcp/ \
--header "Authorization: Bearer YOUR_API_KEY"
Available Tools
What your AI assistant can call
Checks a single phone number. Costs 1 credit.
| Parameter | Type | Required | Description |
|---|---|---|---|
| phone_number | string | Required | Phone number with country code (e.g. "14155551234") |
Checks up to 100 phone numbers in one call. Costs 1 credit per number.
| Parameter | Type | Required | Description |
|---|---|---|---|
| numbers | array[string] | Required | Array of phone numbers with country code. Max 100 items. |
Example Prompts
Once connected, just ask
Error Handling
How tool errors are surfaced to your AI client
Tool call errors (invalid API key, insufficient credits, rate limits) are returned inside the
MCP tool result with isError:
true, so your AI client can read the message and explain it to you instead of the
connection failing silently.
Missing or invalid API key
Double-check the Authorization
header in your client config matches an active key from your dashboard.
Insufficient credits
You've run out of credits. Purchase more credits to continue.
Too many requests
Same per-minute and daily limits as the REST API apply. Wait a moment and ask your assistant to retry.
Ready to connect your AI assistant?
Grab your API key and paste the config above — you'll be checking numbers from chat in under a minute.