Connect your agent to Exepal in one step.

Run once in your terminal. Every Exepal tool shows up in Claude Code with its price.

claude mcp add --transport http exepal "https://api.exepal.com/mcp?key=YOUR_KEY"

Claude desktop or claude.ai: Settings → Connectors → Add custom connector, name it Exepal and paste this URL. (Custom connectors depend on your Claude plan.)

https://api.exepal.com/mcp?key=YOUR_KEY

One click, or paste into ~/.cursor/mcp.json.

{
  "mcpServers": {
    "exepal": { "url": "https://api.exepal.com/mcp?key=YOUR_KEY" }
  }
}

One click, run the command, or add it to .vscode/mcp.json to share with your team.

code --add-mcp '{"name":"exepal","type":"http","url":"https://api.exepal.com/mcp?key=YOUR_KEY"}'

// .vscode/mcp.json
{
  "servers": {
    "exepal": { "type": "http", "url": "https://api.exepal.com/mcp?key=YOUR_KEY" }
  }
}

Paste into ~/.codeium/windsurf/mcp_config.json.

{
  "mcpServers": {
    "exepal": { "serverUrl": "https://api.exepal.com/mcp?key=YOUR_KEY" }
  }
}

Turn on Developer mode (Settings → Apps & Connectors → Advanced), then create a connector with this URL and no authentication. Availability depends on your ChatGPT plan.

https://api.exepal.com/mcp?key=YOUR_KEY

Paste into ~/.gemini/settings.json.

{
  "mcpServers": {
    "exepal": { "httpUrl": "https://api.exepal.com/mcp?key=YOUR_KEY" }
  }
}

Paste into ~/.codex/config.toml.

[mcp_servers.exepal]
url = "https://api.exepal.com/mcp?key=YOUR_KEY"

Any MCP client that speaks Streamable HTTP. No OAuth, no session. The key is optional; you can also send it as Authorization: Bearer.

URL        https://api.exepal.com/mcp
Transport  Streamable HTTP (stateless, JSON responses)
Auth       none · optional key: ?key=YOUR_KEY or Authorization: Bearer YOUR_KEY
Payment    free daily calls, prepaid credit, or x402 USDC per call

curl -X POST https://api.exepal.com/v1/read \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_KEY" \
  -d '{"url":"https://example.com"}'

const res = await fetch("https://api.exepal.com/v1/domain", {
  method: "POST",
  headers: { "Content-Type": "application/json", Authorization: "Bearer YOUR_KEY" },
  body: JSON.stringify({ domain: "stripe.com" }),
});
console.log(await res.json());

import requests

r = requests.post(
    "https://api.exepal.com/v1/email",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"email": "jane@gmial.com"},
    timeout=60,
)
print(r.json())

pip install langchain langchain-mcp-adapters langchain-anthropic. Every Exepal tool becomes a LangChain tool.

import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain.agents import create_agent

async def main():
    client = MultiServerMCPClient({
        "exepal": {
            "transport": "streamable_http",
            "url": "https://api.exepal.com/mcp",
            "headers": {"Authorization": "Bearer YOUR_KEY"},
        }
    })
    tools = await client.get_tools()
    agent = create_agent("anthropic:claude-sonnet-5-5", tools)
    out = await agent.ainvoke({"messages": [{"role": "user", "content": "Is stripe.com protected against email spoofing?"}]})
    print(out["messages"][-1].content)

asyncio.run(main())

npm i ai @ai-sdk/mcp @ai-sdk/anthropic. Works with any AI SDK model.

import { createMCPClient } from "@ai-sdk/mcp";
import { generateText, isStepCount } from "ai";
import { anthropic } from "@ai-sdk/anthropic";

const exepal = await createMCPClient({
  transport: { type: "http", url: "https://api.exepal.com/mcp", headers: { Authorization: "Bearer YOUR_KEY" } },
});
try {
  const { text } = await generateText({
    model: anthropic("claude-sonnet-5-5"),
    tools: await exepal.tools(),
    stopWhen: isStepCount(5),
    prompt: "Read https://example.com and summarise it in two lines.",
  });
  console.log(text);
} finally {
  await exepal.close();
}

pip install openai-agents

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    async with MCPServerStreamableHttp(
        name="exepal",
        params={"url": "https://api.exepal.com/mcp", "headers": {"Authorization": "Bearer YOUR_KEY"}},
    ) as exepal:
        agent = Agent(name="Researcher", instructions="Use Exepal tools for web and data lookups.", mcp_servers=[exepal])
        result = await Runner.run(agent, "Does jane@gmial.com look deliverable?")
        print(result.final_output)

asyncio.run(main())

npm i @modelcontextprotocol/sdk. For paying with a wallet instead of a key, see x402 over MCP.

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js";

const mcp = new Client({ name: "my-agent", version: "1.0.0" });
await mcp.connect(new StreamableHTTPClientTransport(new URL("https://api.exepal.com/mcp?key=YOUR_KEY")));
const { tools } = await mcp.listTools();
const res = await mcp.callTool({ name: "domain", arguments: { domain: "stripe.com" } });
console.log(res.structuredContent);

No key, no account: an agent with a wallet pays each call in USDC on Base. npm i @x402/fetch @x402/evm viem

import { wrapFetchWithPaymentFromConfig } from "@x402/fetch";
import { ExactEvmScheme } from "@x402/evm";
import { privateKeyToAccount } from "viem/accounts";

const pay = wrapFetchWithPaymentFromConfig(fetch, {
  schemes: [{ network: "eip155:8453", client: new ExactEvmScheme(privateKeyToAccount(process.env.WALLET_KEY)) }],
});
const res = await pay("https://api.exepal.com/v1/company-enrich", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ domain: "stripe.com" }),
});
console.log(await res.json());