Rootstock MCP Server
Enables Claude AI to interact with the Rootstock blockchain, including calling contracts, checking ERC20 token balances, transferring tokens, and querying gas prices.
README
<img src="img/rootstock-docs.png" alt="Rootstock Logo" style="width:100%; height: auto;" />
Rootstock MCP Server
This is a Model Context Protocol (MCP) server that provides onchain tools for Claude AI, allowing it to interact with the Rootstock blockchain.
Features
- Call contract functions on Rootstock Network
- Get ERC20 token balances
- Transfer ERC20 tokens
- Get current gas prices
Installation
- Clone this repository:
git clone https://github.com/rsksmart/rsk-mcp-server
cd rootstock-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
Create a .env file in the root directory with the following variables:
SEED_PHRASE="your twelve word seed phrase here"
Usage
Running the server
npm start
Using with Claude
{
"mcpServers": {
"rootstock": {
"command": "node",
"args": ["/path/to/rootstock-mcp/build/index.js"],
"env": {
"SEED_PHRASE": "your twelve word seed phrase here"
},
"disabled": false,
"autoApprove": []
}
}
}
Available Tools
call_contract
Call a contract function on Rootstock Network.
Parameters:
contractAddress: The address of the contract to callfunctionName: The name of the function to callfunctionArgs: The arguments to pass to the functionabi: The ABI of the contractvalue(optional): The value of RBTC to send with the transaction
erc20_balance
Get the balance of an ERC20 token on Rootstock Network.
Parameters:
contractAddress: The address of the contract to get the balance of
erc20_transfer
Transfer an ERC20 token on Rootstock Network.
Parameters:
contractAddress: The address of the contract to transfer the token fromtoAddress: The address of the recipientamount: The amount of tokens to transfer
get_gas_price
Get the current gas price on Rootstock Network.
License
MIT
Disclaimer
The software provided in this GitHub repository is offered “as is,” without warranty of any kind, express or implied, including but not limited to the warranties of merchantability, fitness for a particular purpose, and non-infringement.
- Testing: The software has not undergone testing of any kind, and its functionality, accuracy, reliability, and suitability for any purpose are not guaranteed.
- Use at Your Own Risk: The user assumes all risks associated with the use of this software. The author(s) of this software shall not be held liable for any damages, including but not limited to direct, indirect, incidental, special, consequential, or punitive damages arising out of the use of or inability to use this software, even if advised of the possibility of such damages.
- No Liability: The author(s) of this software are not liable for any loss or damage, including without limitation, any loss of profits, business interruption, loss of information or data, or other pecuniary loss arising out of the use of or inability to use this software.
- Sole Responsibility: The user acknowledges that they are solely responsible for the outcome of the use of this software, including any decisions made or actions taken based on the software’s output or functionality.
- No Endorsement: Mention of any specific product, service, or organization does not constitute or imply endorsement by the author(s) of this software.
- Modification and Distribution: This software may be modified and distributed under the terms of the license provided with the software. By modifying or distributing this software, you agree to be bound by the terms of the license.
- Assumption of Risk: By using this software, the user acknowledges and agrees that they have read, understood, and accepted the terms of this disclaimer and assumes all risks associated with the use of this software.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。