MCP Servers

mcp-mempool

MCP server for querying live Bitcoin data from mempool.space, including recommended fees, mempool stats, blocks, transactions, addresses, and price. No API key required.

README

mcp-mempool

MCP (Model Context Protocol) server for the mempool.space Bitcoin API. No API key required.

Lets any MCP client (Claude Code, Claude Desktop, etc.) query live Bitcoin data: recommended fees, mempool state, blocks, transactions, addresses, price.

Tools

Tool	Arguments	Returns
`get_recommended_fees`	—	Fee estimates in sat/vB (fastest, 30 min, 1 h, economy, minimum)
`get_mempool_stats`	—	Unconfirmed tx count, total vsize, total pending fees
`get_tip`	—	Current block height and hash
`get_recent_blocks`	`limit` (1-10, default 5)	Recent blocks: height, time, tx count, median fee, mining pool
`get_transaction`	`txid` (64 hex chars)	Confirmation status, fee, fee rate, inputs/outputs
`get_address`	`address`	Confirmed balance, received total, tx counts, pending delta
`get_price`	—	BTC price in USD, EUR, GBP, CAD, CHF, AUD, JPY

Install and build

npm install
npm run build

Try it

examples/client.mjs spawns the server over stdio and calls each tool:

npm run example

Use with Claude Code

claude mcp add mempool -- node /path/to/mcp-mempool/dist/index.js

Then ask, for example: "quels frais je mets pour une transaction confirmée dans l'heure ?"

Use with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mempool": {
      "command": "node",
      "args": ["/path/to/mcp-mempool/dist/index.js"]
    }
  }
}

Other networks / self-hosted instance

Set MEMPOOL_API_BASE to point elsewhere (default: https://mempool.space/api):

{
  "mcpServers": {
    "mempool-testnet": {
      "command": "node",
      "args": ["/path/to/mcp-mempool/dist/index.js"],
      "env": { "MEMPOOL_API_BASE": "https://mempool.space/testnet4/api" }
    }
  }
}

Works with any mempool.space-compatible instance (e.g. a self-hosted one on your own node).

Notes

Uses the public REST API; heavy usage should point MEMPOOL_API_BASE at a self-hosted instance (mempool.space rate-limits aggressively).
API errors are returned as MCP tool errors (isError: true) with the upstream message, so the model can react to them.

License

MIT

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.

Official

Featured

TypeScript

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.

Official

Featured

Local

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.

Official

Featured

TypeScript

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.

Official

Featured

Python

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

E2B

Using MCP to run code via e2b.

Official

Featured

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.

Official

Featured

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official

Featured