Bitcompare MCP Server
The official crypto yield data MCP server: native Claude access to live and historical crypto lending, savings, staking, borrowing, stablecoin, price, coin metadata, and market data.
README
@bitcompare/mcp-server
The official crypto yield data MCP server: native Claude access to live and historical crypto lending, savings, staking, borrowing, stablecoin, price, coin metadata, and market data. Built on Model Context Protocol — works with Claude Desktop, Claude Code, Claude.ai, and any MCP-compatible agent.
One npm install, eighteen tools, one API key.
npx -y @bitcompare/mcp-server
Requires a Bitcompare Pro or Enterprise plan. Get a ck_live_* key at https://pro.bitcompare.net/dashboard/keys.
What you get
18 read-only tools, all gated by the same plan limits as REST:
- Crypto yield data — current & historical lending, borrowing, savings, and staking APYs across CeFi and DeFi providers
- Coins — metadata, markets, history, similar coins, and top-by-market-cap lookups
- Prices — aggregated exchange prices with median + outlier filtering
- Global market stats — total market cap, dominance, Fear & Greed Index, 24h top movers
- Stablecoin data — peg deviation leaderboard, historical drift, and yield comparison
- Symbol resolution — map exchange-specific tickers (
BTC,XBT,wBTC) to canonical coin IDs
Full tool catalog: https://www.bitcompare.net/mcp · machine-readable: https://api.bitcompare.net/mcp/tools.json · agent manifest: https://api.bitcompare.net/llms.txt.
Install
You don't need to install it — run via npx:
BITCOMPARE_API_KEY=ck_live_... npx @bitcompare/mcp-server --test
Configure Claude Desktop
Edit claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"bitcompare": {
"command": "npx",
"args": ["-y", "@bitcompare/mcp-server"],
"env": {
"BITCOMPARE_API_KEY": "ck_live_..."
}
}
}
}
Restart Claude Desktop. Ask "what's the best yield on BTC right now?" — Claude will call get_rates and answer from live data.
Configure Claude Code
In your project's .claude/settings.local.json:
{
"mcpServers": {
"bitcompare": {
"command": "npx",
"args": ["-y", "@bitcompare/mcp-server"],
"env": {
"BITCOMPARE_API_KEY": "ck_live_..."
}
}
}
}
Hosted alternative
If you prefer not to install anything, we also run the MCP server at https://api.bitcompare.net/mcp over Streamable HTTP. Point your MCP client at that URL with an Authorization: Bearer ck_live_* header.
Docker
A container is provided for hosted introspection (e.g. Glama). It installs the published npm package and runs the server over stdio:
docker build -t bitcompare-mcp .
docker run -i -e BITCOMPARE_API_KEY=ck_live_... bitcompare-mcp
tools/list introspection works without a key; tool calls require a valid ck_live_ Pro key.
CLI flags
--test— validate your key and list available tools, then exit--version— print version--help— print help--base-url <url>— override API base URL (for staging/dev)
Source
The server is developed in the Bitcompare services monorepo and published to npm as @bitcompare/mcp-server. This repository mirrors the published package and its container for public discovery and hosted introspection.
Support
- Documentation: https://www.bitcompare.net/mcp
- Issues: https://github.com/bitcompare/mcp-server/issues
- Email: support@bitcompare.net
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.