@apitier/mcp-server

MCP (Model Context Protocol) server that exposes all APITier utility APIs as tools for AI agents.

Tools Available

Setup

1. Get your API keys

Sign up at apitier.com. Each APITier service has its own subscription and API key. You only need keys for the services you want to use — tools without a configured key are automatically omitted from the MCP tool list.

2. Install

npm install -g @apitier/mcp-server
# or run directly without installing:
npx @apitier/mcp-server

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "apitier": {
      "command": "npx",
      "args": ["@apitier/mcp-server"],
      "env": {
        "APITIER_POSTCODE_KEY":     "key-from-postcode-subscription",
        "APITIER_EMAIL_KEY":        "key-from-email-subscription",
        "APITIER_PHONE_KEY":        "key-from-phone-subscription",
        "APITIER_VAT_KEY":          "key-from-vat-subscription",
        "APITIER_BARCODE_KEY":      "key-from-barcode-subscription",
        "APITIER_CONVERT_DATA_KEY": "key-from-data-conversion-subscription"
      }
    }
  }
}

Only set keys for services you have subscribed to. Restart Claude Desktop — you will see only the tools for your active subscriptions.

Cursor / Windsurf / other MCP clients

{
  "mcp": {
    "servers": {
      "apitier": {
        "command": "npx",
        "args": ["@apitier/mcp-server"],
        "env": {
          "APITIER_API_KEY": "your-api-key-here"
        }
      }
    }
  }
}

LangChain (Python)

from mcp import ClientSession, StdioServerParameters
from mcp.client.stdio import stdio_client
from langchain_mcp_adapters.tools import load_mcp_tools
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic

async def main():
    server_params = StdioServerParameters(
        command="npx",
        args=["@apitier/mcp-server"],
        env={"APITIER_API_KEY": "your-api-key"},
    )

    async with stdio_client(server_params) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await load_mcp_tools(session)

            model = ChatAnthropic(model="claude-sonnet-4-6")
            agent = create_react_agent(model, tools)

            result = await agent.ainvoke({
                "messages": "Validate this email: test@example.com and look up postcode SW1A 1AA"
            })
            print(result["messages"][-1].content)

Vercel AI SDK (TypeScript)

import { experimental_createMCPClient as createMCPClient } from "ai";
import { Experimental_StdioMCPTransport as StdioMCPTransport } from "ai/mcp-stdio";
import { anthropic } from "@ai-sdk/anthropic";
import { generateText } from "ai";

const mcp = await createMCPClient({
  transport: new StdioMCPTransport({
    command: "npx",
    args: ["@apitier/mcp-server"],
    env: { APITIER_API_KEY: process.env.APITIER_API_KEY! },
  }),
});

const tools = await mcp.tools();

const { text } = await generateText({
  model: anthropic("claude-sonnet-4-

... [View full README on GitHub](https://github.com/apitier/apitier-mcp-server#readme)