About Solana-MCP
Solana-MCP is an Agent Kit MCP server for the Solana blockchain that runs on-chain operations from natural language commands. It offers asset queries, DeFi actions and an open API, aimed at users and developers who want to interact with Solana through conversation.
Key features
- 01Natural language parsing for on-chain operations
- 02Connections to Solana ecosystem DApps
- 03Digital asset management and trading
- 04Staking and lending DeFi operations
- 05Open API for developers
Use cases
- 01Query Solana wallet asset balances using natural language
- 02Perform staking or lending actions through conversation
MCP support
This project is a Solana Agent Kit MCP server; the README describes its on-chain and asset query capabilities but does not detail specific MCP tool definitions.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESolana-MCP
Solana Agent Kit MCP Server
Overview
Solana-MCP is a fully on-chain operation platform designed specifically for the Solana blockchain. By using natural language commands, Solana-MCP simplifies user interactions with the Solana ecosystem, improving efficiency and user experience.
Features
- Natural Language Command Support: Execute complex on-chain operations by parsing user input with LLM technology.
- DApp Integration: Seamlessly connect with major DApps in the Solana ecosystem.
- Digital Asset Management: Support real-time management and trading of major Solana-based assets.
- DeFi Operations: Perform staking, lending, and other DeFi activities with one-click solutions.
- Open API: Developer-friendly APIs for integrating on-chain operations.
Technical Architecture
Core Technologies
- LLM (Large Language Model):
- Multi-language support for global users.
- Intent recognition for accurate operations.
- Context understanding for handling complex commands.
- Dynamic learning for continuous optimization.
- Solana Blockchain:
- High throughput for fast operations.
- Low fees to reduce user costs.
- Strong security based on robust consensus mechanisms.
- High scalability to meet growing user demands.
- Smart Contracts:
- Automated execution of on-chain operations.
- Transparent and secure code logic.
- Programmable and extensible for diverse use cases.
Workflow
- Users input natural language commands on the Solana-MCP platform.
- LLM parses the commands to identify intent and parameters.
- Solana-MCP maps the parsed results to corresponding on-chain operations.
- Smart contracts are invoked to execute the operations.
- Users sign transactions with their Solana wallet.
- Transactions are executed on the Solana blockchain.
- Results are returned to the platform and displayed to the user.
Installation
- Clone the repository:
git clone https://github.com/solanamcp/solana-mcp.git cd solana-mcp - Install dependencies:
npm install - Start the development server:
npm run dev
API Documentation
Example: Execute On-Chain Transaction
Request:
POST /api/execute
Content-Type: application/json
{
"command": "Buy 10 SOL"
}
Response:
{
"status": "success",
"transactionId": "5G9s...kL2"
}
Example: Query Assets
Request:
GET /api/assets
Authorization: Bearer <token>
Response:
{
"assets": [
{ "name": "SOL", "balance": 10.5 },
{ "name": "USDC", "balance": 200.0 }
]
}
Contributing
We welcome contributions! Please follow these steps:
- Fork this repository.
- Create a new branch:
git checkout -b feature/your-feature - Commit your changes:
git commit -m "Add your feature" - Push the branch:
git push origin feature/your-feature - Submit a Pull Request.
License
This project is open-sourced under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.