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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.