EVM MCP Server

What does “EVM” MCP Server do?

The EVM MCP Server is a comprehensive Model Context Protocol (MCP) server designed to provide blockchain services across multiple EVM-compatible networks. It enables AI assistants and agents to interact seamlessly with various Ethereum Virtual Machine (EVM) chains—including Ethereum, Optimism, Arbitrum, Base, Polygon, and more—using a unified interface. By exposing tools and resources for interacting with smart contracts, querying blockchain data, and managing accounts, the EVM MCP Server streamlines development workflows. It empowers AI-driven tasks such as querying chain data, managing transactions, and integrating on-chain logic, thus enhancing the capabilities of developers and AI systems working with decentralized environments.

List of Prompts

No explicit prompt templates are mentioned in the available repository documentation or code.

List of Resources

No explicit resources are described in the available repository documentation or code.

List of Tools

No explicit tool definitions are listed in the available repository documentation or code (including server.py or equivalent).

Use Cases of this MCP Server

• Multi-chain Blockchain Querying: Developers and AI agents can interact with a wide range of EVM-compatible chains using a single, unified protocol, improving efficiency for on-chain data extraction tasks.
• Smart Contract Interaction: Enables programmatic reading from and writing to smart contracts across supported EVM networks, supporting automated workflows and contract testing.
• Transaction Management: Facilitates transaction construction, signing, and sending, allowing both manual and AI-driven operations in decentralized applications.
• AI-driven On-chain Analytics: Provides the foundation for AI agents to analyze blockchain data, monitor network activity, and generate real-time insights for DeFi, NFT, or DAO platforms.

How to set it up

Windsurf

1. Ensure you have Node.js and Windsurf installed.
2. Locate your Windsurf configuration file (typically windsurf.config.json).
3. Add the EVM MCP Server to the mcpServers section:

   {
     "mcpServers": {
       "evm-mcp": {
         "command": "npx",
         "args": ["@evm/mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify the EVM MCP Server is running within the Windsurf UI.

Claude

1. Install Node.js and ensure Claude is set up.
2. Edit your Claude configuration file.
3. Add the EVM MCP Server as follows:

   {
     "mcpServers": {
       "evm-mcp": {
         "command": "npx",
         "args": ["@evm/mcp-server@latest"]
       }
     }
   }
   

4. Restart Claude and confirm the EVM MCP Server is available.
5. Test connectivity via Claude’s MCP server list.

Cursor

1. Verify that you have Node.js and Cursor installed.
2. Open your Cursor configuration file.
3. Insert the following in the mcpServers section:

   {
     "mcpServers": {
       "evm-mcp": {
         "command": "npx",
         "args": ["@evm/mcp-server@latest"]
       }
     }
   }
   

4. Save your changes and restart Cursor.
5. Check that the EVM MCP Server appears in Cursor’s MCP integrations.

Cline

1. Make sure Node.js and Cline are installed.
2. Access the Cline configuration file.
3. Add the EVM MCP Server:

   {
     "mcpServers": {
       "evm-mcp": {
         "command": "npx",
         "args": ["@evm/mcp-server@latest"]
       }
     }
   }
   

4. Restart Cline and ensure the server loads correctly.
5. Use Cline’s tools to verify EVM MCP connectivity.

Securing API Keys

• Store sensitive keys or secrets in environment variables.
• Reference environment variables in your configuration using the env property:

  {
    "mcpServers": {
      "evm-mcp": {
        "command": "npx",
        "args": ["@evm/mcp-server@latest"],
        "env": {
          "EVM_API_KEY": "your-api-key"
        },
        "inputs": {
          "network": "mainnet"
        }
      }
    }
  }
  

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:

{
  "evm-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 “evm-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

My overall rating for EVM MCP Server based on the above tables is 4/10. While the server clearly targets a useful and in-demand capability (EVM blockchain integration), the public documentation lacks details on prompts, resources, and explicit tool interfaces, limiting immediate utility for some users.

MCP Score