About DexScreener MCP Server
DexScreener MCP Server is an MCP server for the DexScreener API, providing DEX pair data, token information and market statistics across several blockchains. It is written with typed interfaces and applies rate limits that follow DexScreener's published limits.
Key features
- 01Latest token profiles and boosted token lists
- 02Pair lookup by chain and pair address
- 03Batch pair lookup by token addresses
- 04Keyword search across pairs
- 05Rate limiting and standardized error responses
Use cases
- 01Querying DEX pair data for tokens on Solana
- 02Tracking token boosts and paid orders
- 03Retrieving market statistics from an MCP client
MCP support
This is an MCP server that wraps the DexScreener API endpoints as MCP tools that clients can call.
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 READMEDexScreener MCP Server
An MCP server implementation for accessing the DexScreener API, providing real-time access to DEX pair data, token information, and market statistics across multiple blockchains.
One-line install (automatically adds to Claude Desktop):
curl -L https://raw.githubusercontent.com/opensvm/dexscreener-mcp-server/main/install.sh | bash
Features
- Rate-limited API access (respects DexScreener's rate limits)
- Comprehensive error handling
- Type-safe interfaces
- Support for all DexScreener API endpoints
- Integration tests
Installation
Manual installation:
npm install
npm run build
npm run setup
Testing
npm test
Usage
Available Tools
-
get_latest_token_profiles- Get the latest token profiles
- No parameters required
const result = await mcpClient.callTool('dexscreener', 'get_latest_token_profiles'); -
get_latest_boosted_tokens- Get the latest boosted tokens
- No parameters required
const result = await mcpClient.callTool('dexscreener', 'get_latest_boosted_tokens'); -
get_top_boosted_tokens- Get tokens with most active boosts
- No parameters required
const result = await mcpClient.callTool('dexscreener', 'get_top_boosted_tokens'); -
get_token_orders- Check orders paid for a specific token
const result = await mcpClient.callTool('dexscreener', 'get_token_orders', { chainId: 'solana', tokenAddress: 'So11111111111111111111111111111111111111112' }); -
get_pairs_by_chain_and_address- Get one or multiple pairs by chain and pair address
const result = await mcpClient.callTool('dexscreener', 'get_pairs_by_chain_and_address', { chainId: 'solana', pairId: 'HxFLKUAmAMLz1jtT3hbvCMELwH5H9tpM2QugP8sKyfhc' }); -
get_pairs_by_token_addresses- Get one or multiple pairs by token address (max 30)
const result = await mcpClient.callTool('dexscreener', 'get_pairs_by_token_addresses', { tokenAddresses: 'So11111111111111111111111111111111111111112' }); -
search_pairs- Search for pairs matching query
const result = await mcpClient.callTool('dexscreener', 'search_pairs', { query: 'SOL' });
Rate Limits
The server implements rate limiting to comply with DexScreener's API limits:
- Token Profile/Boost endpoints: 60 requests per minute
- DEX/Pairs endpoints: 300 requests per minute
Error Handling
The server handles various error scenarios:
- Rate limit exceeded
- Invalid parameters
- Network errors
- API errors
Errors are returned in a standardized format with appropriate error codes and messages.
API Documentation
For detailed API documentation, see docs/api-reference.md.
Development
Project Structure
.
├── src/
│ ├── types/ # TypeScript interfaces and types
│ ├── services/ # API service implementations
│ ├── tests/ # Integration tests
│ └── index.ts # Main server implementation
├── scripts/ # Setup and utility scripts
├── docs/ # Documentation
└── README.md # This file
Adding New Features
- Define types in
src/types/ - Implement service methods in
src/services/ - Add tool handlers in
src/index.ts - Update documentation
- Add tests
License
MIT
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.