Best for
- AI assistant users needing multi-chain DEX and on-chain data
- DeFi analysts and market researchers
- Developers building token and pool analysis tools
A well-maintained multi-chain DEX data MCP server with 16 read-only tools (hosted adds submitFeedback), keyless free tier, and thorough docs and examples. Great for DeFi analytics; not suitable for on-chain writes or strict real-time needs.
Strongest · Documentation 17/20 Weakest · Reliability 9/20
Static review · not runListed 2026-09-07
Read the FMRS scoring method →Runtime:Node.js · Hosted (no local runtime)
Install with npm install -g dexpaprika-mcp, then run dexpaprika-mcp; or run directly with npx dexpaprika-mcp@latest. Alternatively install via Smithery: npx -y smithery mcp add coinpaprika/dexpaprika. Zero-setup option: point an MCP client at https://mcp.dexpaprika.com/streamable-http (hosted endpoint). Add a dexpaprika entry to your Claude Desktop config file and restart.
{"mcpServers":{"dexpaprika":{"command":"npx","args":["dexpaprika-mcp@latest"]}}}
Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"dexpaprika": {
"command": "npx",
"args": [
"dexpaprika-mcp@latest"
]
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add dexpaprika -- npx dexpaprika-mcp@latest
Run it in a terminal; replace any <…> placeholders with your own values first.
After adding the config and restarting Claude Desktop, the tool list should include getCapabilities and getNetworkPools; calling getNetworks should return the 36 supported blockchain networks.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
DexPaprika MCP Server, maintained by CoinPaprika, provides on-demand access to DexPaprika's crypto and DEX data API covering token prices, liquidity pools, trading volume, OHLCV history, and transactions across 36 blockchain networks. It runs locally over stdio via npm, or use the official hosted endpoint (streamable-http / sse / -rpc). The free tier requires no API key to start.
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
One binary. One grammar. Evidence from the biomedical sources you already trust.
Encrypted, fully offline long-term memory for AI agents
Source revision ed6d71152708 Data synced 2026-10-19 Read the FMRS scoring method