The Graph Token API MCP
@pinax-network
关于 The Graph Token API MCP
Official MCP server that turns The Graph’s Token API into a plug-and-play web3 data tool. Exposes ERC-20 & NFT metadata, balances, transfers, top-holder stats, prices, and more, allowing LLMs to run SQL queries on structured and indexed blockchain data.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"token-api": {
"command": "npx",
"args": [
"@pinax/mcp",
"--sse-url",
"https://token-api.mcp.thegraph.com/sse"
],
"env": {
"ACCESS_TOKEN": "<https://thegraph.market JWT Access Token>"
}
}
}
}工具
4List available databases
List available tables from a database
Describe the schema of a table from a database
Run a read-only SQL query
概览
What is The Graph Token API MCP?
An MCP server that provides an interface to The Graph Token API, connecting to a ClickHouse database. It runs on Bun and exposes SSE and HTTP streaming endpoints for MCP communication.
How to use The Graph Token API MCP?
Run with bun run index.ts. Configure via CLI options or environment variables for port, ClickHouse URL, database name, username, password, and logging preferences. The server listens on http://localhost:8080/sse (SSE) and http://localhost:8080/stream (HTTP streaming) by default.
Key features of The Graph Token API MCP
- Runs with the Bun runtime
- Provides SSE and HTTP streaming endpoints
- Connects to a ClickHouse database
- Configurable via CLI flags and environment variables
- Supports pretty and verbose logging options
Use cases of The Graph Token API MCP
—
FAQ from The Graph Token API MCP
—
开发工具 分类下的更多 MCP 服务器
nuxt-mcp / vite-plugin-mcp
antfuMCP server helping models to understand your Vite/Nuxt app better.
Code Index MCP
johnhuang316A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with minimal setup
MCP-Scan: An MCP Security Scanner
invariantlabs-aiSecurity scanner for AI agents, MCP servers and agent skills.
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
评论