Attestable MCP Server

What does “Attestable” MCP Server do?

The Attestable MCP Server is a Model Context Protocol (MCP) server designed to provide a high level of security and trustworthiness through remote attestation. It enables AI assistants and MCP clients to verify that the server they are interacting with is running the exact, untampered code as built and published, leveraging confidential computing and trusted execution environments (TEEs). Before any connection is established, the server generates a hardware-backed certificate and provides cryptographic proof (via RA-TLS with embedded SGX quote) of its code integrity, allowing independent validation. This ensures secure AI workflows that can confidently interact with external data sources, services, or sensitive APIs while guaranteeing that the server environment remains uncompromised.

List of Prompts

No information about prompt templates is provided in the repository.

List of Resources

No information about MCP resources exposed by the server is available in the repository.

List of Tools

No information about tools or executable functions provided by the server is available in the repository (e.g., no server.py or tool definitions).

Use Cases of this MCP Server

• Secure API Gateway: Allow AI agents to access sensitive APIs only if the server integrity is attested and verified, ensuring data protection.
• Trusted Data Access: Enable secure querying of databases or data sources, with proof that the code handling the data is unmodified.
• Compliance and Auditing: Provide verifiable logs and evidence to meet regulatory requirements for data handling and processing by proving the server’s integrity.
• Supply Chain Verification: Assure downstream users and partners that the server they interact with is running the exact code as published, reducing risks of tampering.
• Development of Confidential AI Workflows: Facilitate end-to-end confidential AI pipelines where only attested code can process or transform sensitive information.

How to set it up

Windsurf

1. Ensure prerequisites: Install Node.js and Docker.
2. Locate the Windsurf configuration file (typically windsurf.config.json).
3. Add the Attestable MCP Server using a JSON snippet:

   {
     "mcpServers": {
       "attestable-mcp": {
         "command": "docker",
         "args": ["run", "-p", "8000:8000", "--rm", "gsc-attestable-mcp-server"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify that the server is running and accessible at the specified port.

Claude

1. Ensure Docker is installed.
2. Find Claude’s MCP integration settings.
3. Register the Attestable MCP Server with:

   {
     "mcpServers": {
       "attestable-mcp": {
         "command": "docker",
         "args": ["run", "-p", "8000:8000", "--rm", "gsc-attestable-mcp-server"]
       }
     }
   }
   

4. Save changes and restart Claude.
5. Test AI agent connections to confirm setup.

Cursor

1. Install Node.js and Docker.
2. Open Cursor’s configuration file for MCP servers.
3. Add:

   {
     "mcpServers": {
       "attestable-mcp": {
         "command": "docker",
         "args": ["run", "-p", "8000:8000", "--rm", "gsc-attestable-mcp-server"]
       }
     }
   }
   

4. Restart Cursor.
5. Confirm the Attestable MCP Server is discoverable by AI workflows.

Cline

1. Prepare environment with Docker and necessary system dependencies.
2. Edit Cline’s MCP server config.
3. Include:

   {
     "mcpServers": {
       "attestable-mcp": {
         "command": "docker",
         "args": ["run", "-p", "8000:8000", "--rm", "gsc-attestable-mcp-server"]
       }
     }
   }
   

4. Save config and restart Cline.
5. Check system logs or UI for successful MCP server registration.

Securing API Keys

To secure API keys, use environment variables in your configuration. Example:

{
  "mcpServers": {
    "attestable-mcp": {
      "command": "docker",
      "args": ["run", "-p", "8000:8000", "--rm", "gsc-attestable-mcp-server"],
      "env": {
        "API_KEY": "${YOUR_API_KEY}"
      },
      "inputs": {
        "apiKey": "${API_KEY}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "attestable-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “attestable-mcp” to your actual MCP server name and replace the URL with your own MCP server URL.

Overview

Based on the information found, the Attestable MCP Server is highly specialized in security and remote attestation but currently lacks exposed prompt templates, resources, or tools typical of more feature-rich MCP servers. Its configuration and security focus are strong, but developer-facing features are limited.

MCP Score

Our opinion:
This MCP server scores a 3/10. It offers robust attestation and security features, which are valuable for compliance and trust, but lacks standard MCP functionality such as prompts, resources, and tools that would make it widely usable for typical AI development workflows. Its open-source status is unclear due to the absence of a LICENSE file, but its focus on remote attestation is unique and useful for high-trust scenarios.