Tinyman MCP
Enables interaction with Tinyman AMM protocol on Algorand blockchain, supporting pool management, token swaps, liquidity operations, and analytics for both v1.1 and v2 protocols.
README
Tinyman MCP
A Model Context Protocol (MCP) implementation for Tinyman on Algorand, built by GoPlausible.
Overview
This project provides MCP tools and resources for interacting with Tinyman AMM protocol on Algorand blockchain. It consists of two main packages:
@tinyman-mcp/server: MCP server implementation providing tools for Tinyman operations like swaps, liquidity provision, pool management and analytics@tinyman-mcp/client: Client implementation for wallet connections and transaction signing (Work in Progress)
Features
The MCP server provides the following tools:
Pool Management
tinyman_get_pool: Retrieve detailed information about a specific pooltinyman_get_pool_analytics: Get analytics and statistics for a pooltinyman_get_pool_creation_quote: Generate quote for creating a new pool
Trading Operations
tinyman_get_swap_quote: Generate quotes for asset swaps with support for:- Fixed input amount swaps
- Fixed output amount swaps
- Slippage calculations
Liquidity Management
tinyman_get_liquidity_quote: Generate quotes for adding liquidity- Supports single and dual asset deposits
- Calculates expected pool tokens
tinyman_get_remove_liquidity_quote: Generate quotes for removing liquidity- Supports proportional and single-asset withdrawals
- Calculates expected asset returns
Asset Operations
tinyman_get_asset_optin_quote: Generate quote for opting into an assettinyman_get_validator_optin_quote: Generate quote for opting into a validatortinyman_get_validator_optout_quote: Generate quote for opting out of a validator
All tools support both Tinyman v1.1 and v2 protocols, with v2 being the default version where applicable.
Installation
To install or update the Tinyman MCP implementation, clone the repository, install the dependencies and build the project":
First check node version to be 23.6.1 or later:
node -v
Upgrade to 23.6.1 or later if needed!
Then check the Claude or Cursor container folders to have mcp-servers folder (if not create one):
mkdir PATH_ON_YOUR_MACHINE/Claude/mcp-servers
# or for Cursor
mkdir PATH_ON_YOUR_MACHINE/Cursor/mcp-servers
Then clone this repository under mcp-servers folder and install dependencies:
cd PATH_ON_YOUR_MACHINE/Claude/mcp-servers
# or for Cursor
cd PATH_ON_YOUR_MACHINE/Cursor/mcp-servers
# Clone the repository
git clone https://github.com/GoPlausible/tinyman-mcp.git
cd tinyman-mcp
# Install dependencies
npm install
# Build the project
npm run build
# Edit the .env file to set your configurations
And you are done! Now you can open you MCP config and add the server as :
{
"mcpServers": {
"tinyman-mcp": {
"command": "node",
"args": [
"PATH_ON_YOUR_MACHINE/Claude/mcp-servers/tinyman-mcp/packages/server/dist/index.js"
],
"env": {
"ALGORAND_NETWORK": "mainnet",
"ALGORAND_ALGOD_API": "https://mainnet-api.algonode.cloud/v2",
"ALGORAND_ALGOD": "https://mainnet-api.algonode.cloud",
"ALGORAND_ALGOD_PORT": "",
"ALGORAND_TOKEN": "",
"ALGORAND_AGENT_WALLET": "problem aim online jaguar upper oil flight stumble mystery aerobic toy avoid file tomato moment exclude witness guard lab opera crunch noodle dune abandon broccoli",
"ITEMS_PER_PAGE": "10"
}
}
}
}
Make sure yopu change the paths to match your local system's paths.
For example on MACOS and Claud, the path would be something like this:
{
"mcpServers": {
"algorand-mcp": {
"command": "node",
"args": [
" /Users/YOUR_USERNAME/Library/Application\ Support/Claude/mcp-servers/tinyman-mcp/packages/server/dist/index.js"
]
}
}
}
Project Structure
packages/
├── client/ # Client implementation (WIP)
└── server/ # MCP server implementation
Development
# Install dependencies
npm install
# Build all packages
npm run build
# Clean build artifacts
npm run clean
License
MIT
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。