Access Web3 Data & Analyze Blockchain Insights

Heurist Mesh MCP Server

A Model Context Protocol (MCP) server that connects to Heurist Mesh APIs - your gateway to Web3 intelligence.

Heurist Mesh is the skills marketplace for AI agents. General-purpose AI models lack specialized knowledge about Web3 and often fail to deliver accurate results. Heurist Mesh provides 30+ specialized AI agents that are experts in crypto analytics, ready to give your AI applications the Web3 expertise they need.

Features

• Gateway to Web3 Intelligence: Access 30+ specialized crypto analytics agents via MCP
• Optimized for AI: Input/output formats optimized for AI agents - fewer tool calls, less token usage
• Supports both SSE and stdio transports
• Works with Claude, Cursor, Claude Desktop, and other MCP-compatible interfaces
• Use one API key to access multiple services (CoinGecko, DexScreener, Twitter analytics, and more)

🔥 Just In: Customize Your Agents and Create Managed MCP Servers On-Demand

You can use Heurist Mesh Console to create SSE MCP Servers. Select your agents and compose a personalized swarm for your tasks!

Hosted SSE Endpoint

We provide a hosted SSE endpoint at https://mesh.heurist.xyz/mcp/sse. Authentication is required - you need a Heurist API key (use invite code "claude" for free credits).

Provide your API key via:

• X-HEURIST-API-KEY header (recommended)
• Authorization: Bearer <your-api-key> header
• api_key query parameter

This endpoint includes tools from recommended agents for comprehensive Web3 intelligence:

This is a shared server and the performance may be unstable. For production use, we recommend self-hosting or using Heurist Mesh Console to create dedicated servers.

Cursor can directly access SSE servers. For Claude Desktop users, we recommend installing mcp-proxy to connect to the SSE server.

Prerequisites

• Python 3.10 or higher
• UV package manager (recommended)
• OR Docker
• Get a Heurist API key or you can claim free API credits with invite code "claude"

Installation

Using UV (Recommended)

# Clone the repository
git clone https://github.com/heurist-network/heurist-mesh-mcp-server.git
cd heurist-mesh-mcp-server

# Install the package
uv pip install -e .

Using Docker

# Clone the repository
git clone https://github.com/heurist-network/heurist-mesh-mcp-server.git
cd heurist-mesh-mcp-server

# Build the Docker image
docker build -t mesh-tool-server .

Usage

Option 1: Run with stdio Transport (for Claude Desktop)

Using UV

To use this with Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "heurist-mesh-agent": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/heurist-mesh-mcp-server/mesh_mcp_server",  // Update this path
        "run",
        "mesh-tool-server"
      ],
      "env": {
        "HEURIST_API_KEY": "your-api-key-here"  // Update this key
      }
    }
  }
}

Using Docker

Alternatively, you can use Docker with Claude Desktop by adding this to your claude_desktop_config.json:

{
  "mcpServers": {
    "mesh-agent": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "TRANSPORT=stdio",
        "-e", "HEURIST_API_KEY=your-api-key-here",  // Update this key
        "mesh-tool-server"
      ]
    }
  }
}

Replace /path/to/heurist-mesh-mcp-server with the actual path to the repository and your-api-key-here with your Heurist API key.

Option 2: Run with SSE Transport (for Cursor)

Setting up Environment Variables in .env

cp .env.example .env
HEURIST_API_KEY=your-api-key-here

Using UV:

uv run mesh-tool-server --transport sse --port 8000

Using Docker:

docker run -p 8000:8000 -e PORT=8000 mesh-tool-server

Then, in Cursor, add the MCP Server URL: http://0.0.0.0:8000/sse

Available Tools

Visit https://mesh.heurist.ai/metadata.json or https://mesh.heurist.ai/console to view all 30+ available agents and their tools.

Recommended Tools

These tools from our recommended agents cover most Web3 intelligence use cases:

Customizing Supported Agents

The server comes with a default set of recommended agents. To modify which agents are available:

1. Open the server.py file and locate the Config class.
2. Edit the DEFAULT_AGENTS list to add or remove agents listed at Heurist Metadata

DEFAULT_AGENTS = [
    "TokenResolverAgent",        # Comprehensive token lookup
    "TrendingTokenAgent",        # Aggregated trending tokens
    "TwitterIntelligenceAgent",  # Twitter/X analytics
    "ExaSearchDigestAgent",      # Web search with summarization
    "FundingRateAgent",          # Binance funding & OI data
    "AIXBTProjectInfoAgent",     # Project analysis
    "ZerionWalletAnalysisAgent", # Wallet holdings
    # Add more agents as needed
]