Claude Desktop is a powerful LLM client by Anthopic, designed for both personal and professional use. By integrating it with a Model Context Protocol (MCP) server, you can dynamically inject real-time, relevant context into your Claude sessions from documents, workspaces, tools, apps, and data sources. You can also enable Claude to go beyond text or image generation, taking direct action in business systems like Slack, Salesforce, Jira, and more.

This step-by-step guide will walk you through three methods for integrating Claude Desktop with an MCP server using the examples of GitHub, Asana, and Datadog.

MCP Server Types Supported

Claude Desktop supports the following types of MCP servers:

  • Local Stdio: Runs on your machine and streams responses via standard input/output (stdio).

  • Streamable HTTP: The server operates as an independent process that can handle multiple client connections

Step 1: Enable MCP in Claude Desktop

  1. Open the Claude Desktop App.

  2. Click Developer in the left-hand sidebar.

  3. Click Edit Config.

  1. This will create or open the config file at one of the following paths:

macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
Windows: `%APPDATA%\\Claude\\claude_desktop_config.json`
  1. Add or modify your configuration as shown in the examples below.

Step 2: Choose Your MCP Server Setup

Claude Desktop requires an MCP-compliant server that can respond to context queries. You have three setup options:

Option A: Run the MCP Server Locally

Ideal for development, testing, and debugging.

Instructions:

  1. Install Docker.

  2. Ensure Docker is running.

    • If you encounter issues pulling the image, try running `docker logout ghcr.io` to refresh your credentials.

  3. Create a GitHub Personal Access Token.

    • Choose permissions based on what you’re comfortable sharing with the LLM.

    • Learn more in the GitHub documentation.

Config Example:

{
  "mcpServers": {
    "github": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN",
        "ghcr.io/github/github-mcp-server"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>"
      }
    }
  }
}

Save and restart Claude

Option B: Use a Hosted MCP Server (e.g., Asana, Atlassian)

The easiest option—no setup required. Note that you won’t have central control or visibility into interactions between Claude and the integrated service.

Method 1: Via UI

  1. Navigate to Settings > Integrations.

    • For Enterprise or Team plans, go to the Organization integrations tab.

  2. Click Add integration.

  3. In the modal:

    • Integration name: Any label (e.g., Asana)

    • Integration URL: For Asana, use `https://mcp.asana.com/sse`

  4. Click Add, then Connect to authenticate.

Method 2: Via Config

  1. Install Node and npm.

  2. Install the `mcp-remote` package.

Config Example:

{
  "mcpServers": {
    "asana": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.asana.com/sse"]
    }
  }
}

Save and restart Claude



Option C: Deploy Your Own Remote MCP Server

Recommended for teams and production use. This setup offers:

  • Full visibility and governance

  • Access control across employees and agents

You can deploy your MCP server using a platform like Natoma. Connect apps from the registry, and retrieve the configuration

 or Streamable HTTP endpoint, and paste it into Claude Desktop.

Restart Claude

Troubleshooting & Testing

To verify MCP integration:

  • Ask Claude a question that requires context from recent activity.

  • Claude will send a background request to the MCP server, which returns structured context.

  • Monitor Claude MCP logs at:

    ~/Library/Logs/Claude/mcp.log
  • Claude may block localhost URLs depending on CORS policies. Use ngrok or a Cloudflare Tunnel for HTTPS tunneling.

  • Ensure your MCP server responds with valid JSON in the correct schema.

  • Use the MCP Inspector for debugging.

Wrap-Up

Integrating Claude Desktop with an MCP server—whether local, remote, or SaaS-hosted—takes just a few steps, but can have varying degrees of complexity. Using tools like Natoma can help streamline the process and ensure that security controls are covered. The result is a significantly enhanced contextual experience, making your interactions with Claude more powerful and personalized. Claude more powerful and personalized.

About Natoma

Natoma enables enterprises to adopt AI agents securely. The secure agent access gateway empowers organizations to unlock the full power of AI, by connecting agents to their tools and data without compromising security.

Leveraging a hosted MCP platform, Natoma provides enterprise-grade authentication, fine-grained authorization, and governance for AI agents with flexible deployment models and out-of-the-box support for 100+ pre-built MCP servers.

You may also be interested in:

Five pillars representing how to accelerate enterprise AI adoption

How to Accelerate Enterprise AI Adoption: The 5-Pillar Framework

Accelerating enterprise AI adoption requires the right foundation, not more pilots. Organizations deploying protocol-based infrastructure like Model Context Protocol (MCP) move from experimentation to production in weeks instead of quarters. This guide provides CIOs and innovation leaders with a proven 5-pillar framework for scaling AI adoption: standardized integration layer, automated governance, rapid deployment capability, organizational readiness, and measurement systems. The result: deploy AI tools in minutes instead of months while maintaining enterprise-grade security and control.

Five pillars representing how to accelerate enterprise AI adoption

How to Accelerate Enterprise AI Adoption: The 5-Pillar Framework

Accelerating enterprise AI adoption requires the right foundation, not more pilots. Organizations deploying protocol-based infrastructure like Model Context Protocol (MCP) move from experimentation to production in weeks instead of quarters. This guide provides CIOs and innovation leaders with a proven 5-pillar framework for scaling AI adoption: standardized integration layer, automated governance, rapid deployment capability, organizational readiness, and measurement systems. The result: deploy AI tools in minutes instead of months while maintaining enterprise-grade security and control.

Five pillars representing how to accelerate enterprise AI adoption

How to Accelerate Enterprise AI Adoption: The 5-Pillar Framework

Accelerating enterprise AI adoption requires the right foundation, not more pilots. Organizations deploying protocol-based infrastructure like Model Context Protocol (MCP) move from experimentation to production in weeks instead of quarters. This guide provides CIOs and innovation leaders with a proven 5-pillar framework for scaling AI adoption: standardized integration layer, automated governance, rapid deployment capability, organizational readiness, and measurement systems. The result: deploy AI tools in minutes instead of months while maintaining enterprise-grade security and control.

How AI-Data Integration Solves the Enterprise Workflow Bottleneck

AI workflow automation transforms manual data transfers into intelligent, automated processes through secure control points. Key requirements include unified data access and proper authentication infrastructure.

How AI-Data Integration Solves the Enterprise Workflow Bottleneck

AI workflow automation transforms manual data transfers into intelligent, automated processes through secure control points. Key requirements include unified data access and proper authentication infrastructure.

How AI-Data Integration Solves the Enterprise Workflow Bottleneck

AI workflow automation transforms manual data transfers into intelligent, automated processes through secure control points. Key requirements include unified data access and proper authentication infrastructure.

The Enterprise Guide to AI Data Integration

The path to successful AI data integration requires strategic thinking beyond technical implementation.

The Enterprise Guide to AI Data Integration

The path to successful AI data integration requires strategic thinking beyond technical implementation.

The Enterprise Guide to AI Data Integration

The path to successful AI data integration requires strategic thinking beyond technical implementation.