A highly specialized sniping MCP for Solana SPLP tokens that has Raydium pools
What is monostate 100ms SPL Token Sniper MCP
100ms Raydium Sniper MCP
A high-performance tool for token sniping on Raydium DEX with multi-region support and Claude AI integration.
Overview
The 100ms Raydium Sniper uses Model Context Protocol (MCP) to integrate with Claude AI, allowing natural language interaction for sniping tokens on the Raydium DEX on Solana. Key features include:
- Multi-region execution: Deploy cloud functions across US, Asia, and Europe for the fastest possible execution
- WebSocket monitoring: Real-time monitoring of new pool creation
- GraphQL integration: Fast pool discovery via indexed data
- Claude AI integration: Natural language instructions for token sniping
- Fast execution: Optimized transaction submission with 100ms target response time
- Demo mode: Test and showcase without real blockchain transactions
Requirements
- Node.js 18+ (20+ recommended)
- pnpm
- Solana wallet with SOL
- Claude Desktop App
- Google Cloud account (for multi-region deployment)
- API keys:
- Helius API key (https://helius.xyz)
- Shyft API key (https://shyft.to)
Quick Start
Basic Setup
-
Clone the repository
git clone https://github.com/yourname/100ms-sniper-mcp.git cd 100ms-sniper-mcp
-
Install dependencies
pnpm install
-
Create environment file
cp .env.example .env
Edit
.env
with your API keys and wallet private key. -
Build the project
pnpm run build
-
Launch with Claude Desktop
pnpm run launch-claude
Demo Mode
To try the tool in demo mode without real transactions:
pnpm run setup-demo
This builds the project and launches Claude Desktop with a mock server that simulates responses without requiring API keys or SOL in your wallet.
Usage with Claude
Once Claude Desktop is launched with the MCP installed, you can use natural language to:
-
Check status: "Show me the status of the Raydium sniper"
-
Snipe a token: "Snipe token DezXAZ8z7PnrnRJjz3wXBoRgixCa6xjnB7YaB1pPB263 with 1% slippage"
-
Configure parameters: "Configure my sniper with 2% slippage and 0.1 SOL per transaction"
Cloud Deployment
For multi-region deployment:
-
Set up cloud configuration
cp cloud/.env.cloud.example cloud/.env.cloud
Edit
cloud/.env.cloud
with your API keys, project ID and wallet information. -
Run cloud setup
pnpm run cloud:setup
-
Build and deploy cloud functions
pnpm run cloud:build pnpm run cloud:deploy
-
Update your environment with function URLs After deployment, copy the deployed function URLs to your
.env
file.
See DEPLOYMENT.md for detailed deployment instructions.
Architecture
The architecture consists of several components:
- MCP Server: Communicates with Claude AI
- Cloud Functions: Multi-region execution points that run on Google Cloud Functions
- Region Manager: Manages connections to different geographical regions
- WebSocket Manager: Handles real-time Solana program subscription
- AMM Manager: Interacts with Raydium AMM protocol
Troubleshooting
- "No pools found" error: Ensure the token mint address is correct and has liquidity on Raydium
- Slow performance: Check that your API keys are valid and have sufficient rate limits
- Deployment failures: See DEPLOYMENT.md for specific deployment troubleshooting steps
- Claude integration issues: Ensure Claude Desktop is properly installed and the MCP is correctly configured
License
MIT License - See LICENSE for details.
Leave a Comment
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
chrisdoc hevy mcp
sylphlab pdf reader mcp
An MCP server built with Node.js/TypeScript that allows AI agents to securely read PDF files (local or URL) and extract text, metadata, or page counts. Uses pdf-parse.
aashari mcp server atlassian bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
aashari mcp server atlassian confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
prisma prisma
Next-generation ORM for Node.js & TypeScript | PostgreSQL, MySQL, MariaDB, SQL Server, SQLite, MongoDB and CockroachDB
Zzzccs123 mcp sentry
mcp sentry for typescript sdk
zhuzhoulin dify mcp server
zhongmingyuan mcp my mac
zhixiaoqiang desktop image manager mcp
MCP 服务器,用于管理桌面图片、查看详情、压缩、移动等(完全让Trae实现)
zhixiaoqiang antd components mcp
An MCP service for Ant Design components query | 一个减少 Ant Design 组件代码生成幻觉的 MCP 服务,包含系统提示词、组件文档、API 文档、代码示例和更新日志查询
Submit Your MCP Server
Share your MCP server with the community
Submit Now