Connect with MCP

If your framework already supports remote MCP, you can connect directly without installing @agentmuxer/sdk.

Setting	Value
Endpoint	`https://mcp.agentmuxer.com/mcp`
Transport	Streamable HTTP
Authentication	`Authorization: Bearer <application-key>`
Credentials	An AgentMuxer application key; no OAuth login

The examples below show the connection settings to add to an existing agent. For complete runnable examples, use the SDK guides. Check compatibility for supported integrations and runtime requirements.

Configure your framework

Read AGENTMUXER_API_KEY from your server’s environment and reject startup if it is missing:

const apiKey = process.env.AGENTMUXER_API_KEY;
if (!apiKey) throw new Error("Set AGENTMUXER_API_KEY");

OpenAI Responses
Anthropic Messages
Mastra
LangChain / LangGraph

Add this item to the Responses API’s tools array:

{
  type: "mcp",
  server_label: "agentmuxer",
  server_url: "https://mcp.agentmuxer.com/mcp",
  authorization: apiKey,
  require_approval: "never",
}

OpenAI receives the application key and connects to AgentMuxer. require_approval controls OpenAI’s approval step; AgentMuxer’s payment policy still applies. See OpenAI remote MCP.

Add these fields to a beta Messages request:

{
  betas: ["mcp-client-2025-11-20"],
  mcp_servers: [{
    type: "url",
    name: "agentmuxer",
    url: "https://mcp.agentmuxer.com/mcp",
    authorization_token: apiKey,
  }],
  tools: [{
    type: "mcp_toolset",
    mcp_server_name: "agentmuxer",
  }],
}

Anthropic receives the application key and connects to AgentMuxer. The connector is beta and supports tool calls; check its current requirements before deploying.

Install @mastra/mcp, then configure its client:

import { MCPClient } from "@mastra/mcp";

const client = new MCPClient({
  servers: {
    agentmuxer: {
      url: new URL("https://mcp.agentmuxer.com/mcp"),
      requestInit: {
        headers: { Authorization: `Bearer ${apiKey}` },
      },
    },
  },
});

Pass await client.listTools() to your agent’s tools configuration. Call await client.disconnect() when the run finishes, including on errors. See Mastra MCP.

Install @langchain/mcp-adapters, then configure its client:

import { MultiServerMCPClient } from "@langchain/mcp-adapters";

const client = new MultiServerMCPClient({
  agentmuxer: {
    transport: "http",
    url: "https://mcp.agentmuxer.com/mcp",
    headers: { Authorization: `Bearer ${apiKey}` },
  },
});

Pass await client.getTools() to your agent’s tools configuration. Release the client when the run ends using the lifecycle API for your installed version. See LangChain MCP.

Permissions and spending

These connections expose AgentMuxer’s tools, including purchases. Your framework owns model configuration, tool selection, permissions, and connection lifecycle. AgentMuxer enforces the account balance, application spending limit, and payment-confirmation policy. Before using a headless workflow, confirm that it can handle your account’s payment approval requirements. Model-provider charges are separate. Keep application keys out of browser bundles, prompts, tool arguments, and logs.

Use an SDK helper

See the OpenAI, Claude, and Vercel integration options.

Troubleshooting

Resolve authentication, tool, and purchase errors.

Get started

Integrations

Your application

Configure your framework

Permissions and spending

Use an SDK helper

Troubleshooting

​Configure your framework

​Permissions and spending

Use an SDK helper

Troubleshooting

Configure your framework

Permissions and spending