Cryo MCP

Cryo MCP

Enables natural language querying of blockchain data, including blocks, transactions, logs, and more, powered by Cryo and Reth, with optional micropayment integration via Payflow.

Category
访问服务器

README

Cryo MCP (with Payflow)

Button Icon

Cryo MCP is an MCP server that allows you to extensively query blockchain data in natural language, powered by Cryo and Reth.

We host a remote MCP server at https://cryo-mcp.fly.dev/v1/mcp that you can use to test it out. It is connected to a Reth archive node and has access to all datasets that Cryo provides:

cryo datasets
─────────────
- address_appearances
- balance_diffs
- balance_reads
- balances
- blocks
- code_diffs
- code_reads
- codes
- contracts
- erc20_balances
- erc20_metadata
- erc20_supplies
- erc20_transfers
- erc721_metadata
- erc721_transfers
- eth_calls
- four_byte_counts (alias = 4byte_counts)
- geth_calls
- geth_code_diffs
- geth_balance_diffs
- geth_storage_diffs
- geth_nonce_diffs
- geth_opcodes
- javascript_traces (alias = js_traces)
- logs (alias = events)
- native_transfers
- nonce_diffs
- nonce_reads
- nonces
- slots (alias = storages)
- storage_diffs (alias = slot_diffs)
- storage_reads (alias = slot_reads)
- traces
- trace_calls
- transactions (alias = txs)
- vm_traces (alias = opcode_traces)

It is also a demonstration of how to use payflow to integrate micropayments into your MCP server. To use it, you need to have a local payflow MCP server running that can create the payments for the paid tools.

Claude Desktop Quickstart

  1. Press cmd+, in Claude Desktop to open the settings
  2. Go to the Developer tab
  3. Click edit config and open the claude_desktop_config.json file
  4. Add the cryo server to the mcpServers object:
  5. Add the payflow server to the mcpServers object, with the correct configuration:
{
  "mcpServers": {
    "cryo": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://cryo-mcp.fly.dev/v1/mcp",
        "--header",
        "Authorization: test",
        "--transport",
        "http-only"
      ]
    },
    "payflow": {
      "command": "npx",
      "args": ["@chainbound/payflow-mcp"],
      "env": {
        "PRIVATE_KEY": "",
        // Set your max payment amount in USDC per tool call
        "MAX_PAYMENT_AMOUNT_USDC": "10",
        // Enable debug logging
        "DEBUG": "payflow:*"
      }
    }
  }
}

Paid Tools

Only the dataset generation (query_dataset) tool is paid, using Coinbase x402 through the payflow-sdk package. It currently costs 0.05 USDC and is payable on Base. The MCP server uses the facilitator hosted by Coinbase to settle the payments.

Limits

We limit the number of blocks per query to 10,000. If your agent needs more data, you can use the query_dataset tool multiple times with multiple payments.

Sequence Diagram

sequenceDiagram
    box Grey Local
    participant Claude
    participant Payflow MCP
    end
    box Purple Remote
    participant Cryo MCP
    participant Facilitator
    end
    Claude->>+Cryo MCP: get_tool_details
    Cryo MCP -->>-Claude: details
    Claude->>Claude: evaluate_details
    alt proceed
        Claude->>+Payflow MCP: generate_payment
        Payflow MCP->>-Claude: payment_details
        Claude->>+Cryo MCP: tool_call, payment
        Cryo MCP->>+Facilitator: verify and settle
        Facilitator->>-Cryo MCP: response (success)
        Cryo MCP->>-Claude: tool_result
        Claude->>Claude: process & present result to user
    end

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选