Chunk MCP Server

Chunk MCP Server

Enables querying median feeds and metrics from the Chunk network via MCP tools, including listing metrics, getting quotes, and checking contract health.

Category
Visit Server

README

Chunk MCP Server

Production-ready MCP server exposing Chunk MedianFeeds tools over stdio.

  • Network: Chunk testnet (default RPC: https://rpc.chunknet.org)
  • Contract: MedianFeeds (default): 0x78D02A47fA898ffF4B37A9B414Eace5eed3e7fAD

Requirements

  • Node.js 18+ (ESM modules)

Quickstart

  • Install
    • cd mcp-server
    • npm install
  • Build
    • npm run build
  • Run (stdio transport)
    • npm start

Configuration

  • Environment variables
    • CHUNK_RPC — JSON-RPC endpoint (default: https://rpc.chunknet.org)
    • CHUNK_MEDIAN_ADDR — MedianFeeds contract address (default: 0x78D02A47fA898ffF4B37A9B414Eace5eed3e7fAD)
    • METRICS_CACHE_TTL_MS — metrics cache TTL in milliseconds (default: 30000)

Production .env (overrides optional)

CHUNK_RPC=https://rpc.chunknet.org
CHUNK_MEDIAN_ADDR=0x78D02A47fA898ffF4B37A9B414Eace5eed3e7fAD
METRICS_CACHE_TTL_MS=30000

Notes: You can omit .env entirely — these are the built-in defaults.

Tools

  • list_metrics — List metric definitions from MedianFeeds
    • Args: { chain?, rpcUrl?, contractAddress?, currency?, tagIncludes?, nameContains?, limit?, offset? }
  • quote_metrics — Get last quotes for given metric names
    • Args: { names: string[], chain?, rpcUrl?, contractAddress?, format?: 'raw'|'int'|'decimal'|'all', decimals?: number }
  • get_signed_root — Get current signed Merkle tree root (epoch)
    • Args: { chain?, rpcUrl?, contractAddress? }
  • get_metrics_count — Total metrics count
  • has_metric — Check if a metric exists by name
  • get_metrics_map — Mapping name -> id (index-based)
  • quote_by_ids — Quote metrics by numeric ids
    • Args: { ids: number[], chain?, rpcUrl?, contractAddress?, format?, decimals? }
  • quote_metrics_at_block — Quote metrics at specific block number
    • Args: { names: string[], blockNumber: number, chain?, rpcUrl?, contractAddress?, format?, decimals? }
  • quote_metrics_at_epoch_end — Quote metrics at the end of an epoch
    • Args: { names: string[], epochDuration?: number, epochId?: number, chain?, rpcUrl?, contractAddress?, format?, decimals? }
  • quote_metrics_at_timestamp — Quote metrics at specific UNIX timestamp (seconds)
    • Args: { names: string[], timestamp: number, chain?, rpcUrl?, contractAddress?, format?, decimals? }
  • get_health — RPC health info { chainId, blockNumber }
  • check_staleness — Check if metrics are stale w.r.t maxAgeSeconds
  • check_thresholds — Threshold checks for rules of form { name, op: 'lt'|'lte'|'gt'|'gte'|'eq'|'neq', value: string|number }

Formatting

  • Raw values are returned as on-chain 2**112-scaled integers.
  • Use format: 'decimal' and decimals to get human-friendly strings with rounding.

Resources

  • chunk://median/{chain}/metrics — JSON array of metrics for a chain (chunk supported)
  • chunk://median/{chain}/metric/{name} — JSON object with the latest quote for a metric

Subscriptions

  • The server registers resources.subscribe capability.
  • On epoch changes, resources/updated notifications are sent for subscribed URIs.

Client Example (Node.js)

import { Client } from '@modelcontextprotocol/sdk/client/index.js';
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js';

const transport = new StdioClientTransport({
  command: 'node',
  args: ['dist/server.js'],
  env: process.env,
});

const client = new Client({ name: 'chunk-mcp', version: '0.1.0' });
await client.connect(transport);

const list = await client.callTool({ name: 'list_metrics', arguments: { limit: 5 } });
const names = list.structuredContent.metrics.map(m => m.name).slice(0, 2);
const quotes = await client.callTool({ name: 'quote_metrics', arguments: { names, format: 'decimal', decimals: 6 } });
console.log(quotes.structuredContent.quotes);

await client.close();

Claude Desktop (MCP) configuration (example)

  • Configure a stdio MCP server:
{
  "mcpServers": {
    "chunk-mcp": {
      "command": "node",
      "args": ["dist/server.js"],
      "env": {
        "CHUNK_RPC": "https://rpc.chunknet.org",
        "CHUNK_MEDIAN_ADDR": "0x78D02A47fA898ffF4B37A9B414Eace5eed3e7fAD"
      }
    }
  }
}

Operational Notes

  • Timeouts and RPC limits depend on your provider.
  • Handle network errors and transient failures with retries on the client side.
  • For production, pin a stable RPC endpoint and contract address.

Project Structure

  • src/server.js — source (ESM)
  • dist/server.js — bundled build (after npm run build)
  • No tests are included in this directory by design.

Recommended Servers

playwright-mcp

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)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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

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
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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

Qdrant Server

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

Official
Featured