About Dexscreener MCP server
A basic MCP server for the Dexscreener API, based on its documentation as of April 4, 2025. It lets AI agents check on-chain token prices and is aimed at developers who need market data in MCP clients.
Key features
- 01On-chain price lookup via Dexscreener API
- 02Default SDTIO transport
- 03SSE version index-sse.js for remote hosting
- 04Testing with MCP Inspector
Use cases
- 01Letting an AI assistant check current on-chain token prices
- 02Connecting on-chain price data to Claude Desktop
- 03Hosting the SSE version on a remote server for clients
MCP support
This project is an MCP server that exposes Dexscreener API price lookups to MCP clients.
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
Basic MCP server for Dexscreener API based on their documentation (as of April 4th 2025): https://docs.dexscreener.com/api/reference
Project setup
Install all the dependencies
npm run install
If you are using Claude Desktop, after pulling the code open the config file claude_desktop_config.json in VSCode:
-
on MacOS:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json -
on Windows:
code $env:AppData\Claude\claude_desktop_config.json -
more info: https://modelcontextprotocol.io/quickstart/server
In claude_desktop_config.json put dexscreener object:
{
"mcpServers": {
"dexscreener": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/index.js"
]
}
}
}
Running the app
You can use Inspector to test the MCP server without using Claude Desktop - both for SDTIO version (default) and SSE version index-sse.js (server-sent events - can be hosted on remote server).
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.