{
  "schema_version": "agentpmt.docs.v1",
  "generated_at": "2026-07-21T09:20:50.858Z",
  "release_id": "645ba065961f3e4869733f1c5ebbd86e4233149ebb79daf3c648378a1d5336d2",
  "id": "docs-845e8dbbdf5227f1",
  "page_url": "https://www.agentpmt.com/docs/getting-started/connect-an-agent",
  "markdown_url": "https://www.agentpmt.com/docs/getting-started/connect-an-agent?format=agent-md",
  "json_url": "https://www.agentpmt.com/docs/getting-started/connect-an-agent?format=agent-json",
  "source_path": "content/docs/connect-an-agent.mdoc",
  "updated_at": "2026-07-18T21:01:08.834Z",
  "headings": [
    {
      "depth": 2,
      "id": "mcp-integration",
      "title": "MCP Integration"
    },
    {
      "depth": 3,
      "id": "30-second-setup",
      "title": "30 Second Setup"
    },
    {
      "depth": 3,
      "id": "hosted-streamable-https",
      "title": "Hosted Streamable HTTPS"
    },
    {
      "depth": 3,
      "id": "config-example",
      "title": "Config Example"
    },
    {
      "depth": 2,
      "id": "restapi-integration",
      "title": "RestAPI Integration"
    },
    {
      "depth": 3,
      "id": "api-overview",
      "title": "API Overview"
    },
    {
      "depth": 3,
      "id": "api-reference",
      "title": "API Reference"
    }
  ],
  "related_products": [],
  "related_workflows": [],
  "doc": {
    "title": "Connect An Agent",
    "description": "Learn how to connect AI agents to AgentPMT using MCP or REST API integration methods.",
    "category": "Getting Started",
    "image": null,
    "full_path": "getting-started/connect-an-agent",
    "body_markdown": "# Connect An Agent\n\nConnect your AI agents to AgentPMT to enable tool and workflow execution. AgentPMT supports two primary connection methods: Model Context Protocol (MCP) for modern AI platforms, and REST API for custom integrations.\n\n## MCP Integration\n\nThe Model Context Protocol (MCP) provides a standardized way for AI agents to discover and use tools from AgentPMT. This is the recommended method for connecting AI agents like Claude, ChatGPT, and other MCP-compatible platforms.\n\n### 30 Second Setup\n\nSTDIO connector for Claude Code, Codex, Cursor, Zed, and other LLMs that require STDIO or custom connections.\n\n```bash\nnpm install -g @agentpmt/mcp-router\nagentpmt-setup\n```\n\n### Hosted Streamable HTTPS\n\nMCP endpoint for browser-based apps like ChatGPT, Claude, Grok, or any time you want a streamable connection with no local install.\n\n```text\nhttps://api.agentpmt.com/mcp\n```\n\n### Config Example\n\nUse the hosted endpoint directly in clients that support remote MCP. Store your Bearer token in the client config or secret field.\n\n```json\n{\n  \"mcpServers\": {\n    \"agentpmt\": {\n      \"type\": \"streamable-http\",\n      \"url\": \"https://api.agentpmt.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer <AGENTPMT_BEARER_TOKEN>\",\n        \"x-instance-metadata\": \"{\\\"client\\\":\\\"generic-mcp\\\",\\\"platform\\\":\\\"remote\\\"}\"\n      }\n    }\n  }\n}\n```\n\nFor platform-specific setup and the full connection guide, see [Connection](https://www.agentpmt.com/docs/mcp-reference/connection).\n\n## RestAPI Integration\n\nFor custom integrations and advanced use cases, AgentPMT provides a REST API that gives you programmatic control over tool execution, workflow management, and agent interactions.\n\n### API Overview\n\nThe REST API allows you to:\n\n- **Execute tools** directly via HTTP requests\n- **Manage workflows** and their execution\n- **Handle authentication** programmatically\n- **Monitor usage** and billing\n- **Integrate with existing systems** using standard web protocols\n\n### API Reference\n\nFor complete API documentation, see the [Programmatic Access reference](https://www.agentpmt.com/docs/api-reference/programmatic-access).\n"
  }
}