dexscreener
MCP server from openSVM/dexscreener-mcp-server
claude mcp add --transport stdio opensvm-dexscreener-mcp-server node dist/index.js
How to use
This MCP server provides a programmatic interface to the DexScreener API, exposing tools that let you retrieve token profiles, boosted tokens, top boosted tokens, and DEX pair information across supported blockchains. The server is designed to respect DexScreener's rate limits and includes error handling for common failure modes such as invalid parameters, network issues, and API-side errors. To use the tools, you instantiate an MCP client in your application and call the desired tool by name through the MCP client, for example mcpClient.callTool('dexscreener', 'get_latest_token_profiles') or mcpClient.callTool('dexscreener', 'get_pairs_by_chain_and_address', { chainId: 'solana', pairId: 'HxFLKUAmAMLz1jtT3hbvCMELwH5H9tpM2QugP8sKyfhc' }). The available tools cover token data and DexScreener pairs, enabling scenarios like monitoring the latest profiles, tracking boosted tokens, and querying specific pairs or token addresses. All tool calls are designed to be straightforward TypeScript-like calls and return structured results or standardized error objects when something goes wrong. You can integrate these capabilities into dashboards, alerts, or bots that need real-time DexScreener data.
How to install
Prerequisites:
- Node.js v14+ (with npm/yarn)
- Access to the project repository (or clone) and permission to install dependencies
Installation steps:
- Clone the repository or download the source code
- Install dependencies
npm install
or
yarn install - Build the server npm run build
- Setup any required configuration (see docs or environment variables in the repo)
- Run the server npm run start
If you prefer the one-line install script shown in the README, you can run: curl -L https://raw.githubusercontent.com/opensvm/dexscreener-mcp-server/main/install.sh | bash
Notes:
- The repository uses TypeScript; ensure your environment supports TS compilation if you customize locally.
- After building, the server typically starts from the compiled output (e.g., dist/index.js).
Additional notes
Tips and considerations:
- Rate limits: Token profile/boost endpoints allow up to 60 requests per minute; DEX/pairs endpoints allow up to 300 requests per minute. Plan your tool usage accordingly or implement client-side throttling.
- Error handling: The server returns standardized error objects for rate limits, invalid parameters, network errors, and API errors. Check error codes and messages to diagnose failures.
- Environment variables and config: If the server supports environment-based configuration, you can set API keys or rate-limit buffers through env vars as described in docs/docs/api-reference (see docs in the repo).
- Testing: Run npm test to execute integration tests. Ensure tests point to a valid DexScreener API endpoint and any required credentials are available in the test environment.
- Extensibility: To add new features, define TS types in src/types, implement service methods in src/services, add tool handlers in src/index.ts, and extend tests accordingly.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.