Flow MCP Server

@MCP-Mirror

About Flow MCP Server

Mirror of

#flow-mcp-server #blockchain #ai-assistant

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "lmcmz_flow-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@outblock/flow-mcp-server",
        "--stdio"
      ]
    }
  }
}

Tools

Get Flow balance for an address

Get fungible token balance

Get account information

Resolve a .find or .fn domain to an address

Execute a Cadence script

Send a transaction to the blockchain

Get transaction details by ID

Overview

What is Flow MCP Server?

Flow MCP Server is a Model Context Protocol (MCP) server that enables AI assistants to interact with the Flow blockchain. It provides a standardized interface for reading blockchain data, checking balances, resolving domains, executing scripts, and submitting transactions.

How to use Flow MCP Server?

Install and run it via npx -y @outblock/flow-mcp-server --stdio for AI assistant integration, or with --port 3000 to run as an HTTP server. Configure the Flow network and access node using environment variables like FLOW_NETWORK and FLOW_ACCESS_NODE. For development, clone the repository, run npm install, npm run build, and npm start.

Key features of Flow MCP Server

Check Flow and fungible token balances
Resolve .find and .fn domain names
Execute Cadence scripts on the blockchain
Send and monitor transactions
Retrieve account information
Configurable via environment variables

Use cases of Flow MCP Server

An AI assistant checking a user’s FLOW balance
Resolving a blockchain domain to an address
Reading smart contract data with a Cadence script
Submitting a transaction and tracking its status
Fetching account details for wallet verification

FAQ from Flow MCP Server

How do I start the server?

Run npx -y @outblock/flow-mcp-server --stdio for stdio mode (for AI assistant integration) or npx -y @outblock/flow-mcp-server --port 3000 to run as an HTTP server.

How do I integrate with Claude or other AI assistants?

Add a tool configuration entry in your assistant’s settings with the command npx -y @outblock/flow-mcp-server --stdio.

What Flow networks are supported?

Mainnet, testnet, and emulator. Specify the network via the FLOW_NETWORK environment variable or the --network CLI flag.

What tools are available?

Tools include get_balance, get_token_balance, get_account, resolve_domain, execute_script, send_transaction, and get_transaction.

Can I run the server in HTTP mode?

Yes, use the --port flag (e.g., --port 3000). HTTP endpoints are available at /sse, /messages, /health, and /.

Frequently asked questions

How do I start the server?

Run `npx -y @outblock/flow-mcp-server --stdio` for stdio mode (for AI assistant integration) or `npx -y @outblock/flow-mcp-server --port 3000` to run as an HTTP server.

How do I integrate with Claude or other AI assistants?

Add a tool configuration entry in your assistant’s settings with the command `npx -y @outblock/flow-mcp-server --stdio`.

What Flow networks are supported?

Mainnet, testnet, and emulator. Specify the network via the `FLOW_NETWORK` environment variable or the `--network` CLI flag.

What tools are available?

Tools include `get_balance`, `get_token_balance`, `get_account`, `resolve_domain`, `execute_script`, `send_transaction`, and `get_transaction`.

Can I run the server in HTTP mode?

Yes, use the `--port` flag (e.g., `--port 3000`). HTTP endpoints are available at `/sse`, `/messages`, `/health`, and `/`.

Comments

Basic information

More Other MCP servers

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Inbox Zero AI MCP

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K