Bitquery MCP Server MCP

Blockchain data for AI agents via the Model Context Protocol

This URL is an MCP (Model Context Protocol) server. It is not meant to be opened in a browser — it's a programmatic API used by AI agents like Claude, Cursor, and VS Code to query Bitquery's blockchain data.

📖 Full installation guide: https://docs.bitquery.io/docs/usecases/MCP/

Buttons require the client to be installed. For Claude and ChatGPT, follow the manual steps below — they don't yet support deep-link install for custom connectors.

What you can ask

Once connected, you talk to your AI client in plain English and it picks the right MCP tool behind the scenes. Concrete examples that work today:

• "What are the trending Solana tokens in the last 24 hours by trade volume?" — uses trending_tokens.
• "Show me OHLCV candles for WETH/USDC on Uniswap v3 for the past 7 days." — uses pair_ohlcv.
• "Who are the most profitable traders of in the last month, and what are they holding now?" — combines profitable_traders_by_token and trader_positions.
• "Build a profile of wallet 0xabc… — total PnL, win rate, top tokens, recent activity." — uses trader_profile and trader_activity.
• "Find every token whose symbol contains 'AI' on Base, sorted by 24h volume." — uses find_tokens.
• "Run this SQL against Bitquery: SELECT … FROM solana.dex_trades WHERE …" — uses execute_sql (paid plans).

The full tool list, parameter shapes, and supported networks are returned by the server itself when your client calls tools/list — so the AI always sees the up-to-date catalog without you reading docs.

Why use the MCP endpoint instead of GraphQL?

The underlying dataset is the same Bitquery you already know. The difference is the interface:

• No query writing. The agent picks the tool and supplies arguments. You stay in conversation.
• Structured tool definitions. Each tool advertises its inputs and outputs to the model, so the model can chain calls — for example, find a token, then pull its top traders, then look up each trader's recent positions, in one turn.
• Same auth, same plan. Quotas, rate limits, and billing come from your existing Bitquery account. There's no separate signup.
• Streaming transport. The server speaks Streamable HTTP, so long responses (large trade histories, multi-step tool chains) stream back without timing out.

How to install

Install Bitquery as a custom connector in your AI client. No config file editing required.

Claude (Desktop & Web)

1. Open Settings → Connectors
2. Click Add custom connector
3. Enter:
   • Name: Bitquery Trading Data
   • URL: https://mcp.bitquery.io
4. Click Add — a browser window opens to log in with your Bitquery account

ChatGPT

1. Open Settings → Connectors (requires Plus/Pro/Business plan)
2. Click Add connector → Custom connector
3. Enter URL: https://mcp.bitquery.io
4. Authenticate with your Bitquery account

Cursor

1. Open Settings → MCP
2. Click Add new MCP server
3. Enter URL: https://mcp.bitquery.io

VS Code / other MCP clients

Add a new MCP server with URL: https://mcp.bitquery.io

Authentication

The recommended method is OAuth 2.1 — no manual token handling needed. On first connection, your AI client opens a browser to log in with your Bitquery account. Tokens are cached for ~30 days and refresh automatically.

Direct token (URL parameter)

For clients that can't perform the OAuth flow, or when you need to control token lifetime yourself, append your access token as a query parameter:

https://mcp.bitquery.io/?token=ory_at_xxxxxxxx...

Generate a token at account.bitquery.io (see how to generate API credentials). The token is validated on every request, so revoking it from your account immediately disables access.

Note: URL-embedded tokens appear in proxy access logs and may leak via shell history or referrers. Prefer the Authorization: Bearer header where the client supports it.

FAQ

What is the Bitquery MCP Server?

It is a hosted Model Context Protocol (MCP) server at https://mcp.bitquery.io that exposes Bitquery's on-chain blockchain data as MCP tools. AI agents like Claude, ChatGPT, Cursor, and VS Code can call these tools directly during a conversation, without you having to write GraphQL queries by hand.

Which AI clients can connect to it?

Any client that supports remote MCP servers over Streamable HTTP. This includes Claude Desktop and Claude.ai (web, with Plus/Pro/Max), ChatGPT (Plus/Pro/Business with custom connectors enabled), Cursor, VS Code with MCP enabled, and custom agents built with the Anthropic or OpenAI SDKs.

Which blockchains and datasets are available?

The MCP server exposes Bitquery's full multi-chain dataset: Ethereum, Solana, Tron, BNB Chain, Base, Polygon, Arbitrum, and others. Tools cover token prices, OHLCV candles, trending tokens, top and profitable traders, trader profiles and positions, DEX pairs, and raw SQL access where the user has a paid plan.

How does authentication work?

Two methods are supported. OAuth 2.1 is recommended: the AI client opens a browser to your Bitquery account, you approve access, and tokens refresh automatically for ~30 days. For clients that can't run the OAuth flow, you can append a personal access token as a URL query parameter (?token=…). The token is validated on every call, so revoking it from your account immediately disables access.

How is this different from the Bitquery GraphQL API?

The MCP server is built for AI agents. Instead of writing a GraphQL query, the agent picks an MCP tool (for example token_ohlcv or top_traders_by_token) and the server runs the underlying query on Bitquery for you. The data source is the same; the interface is conversational. Quotas, plans, and billing are shared with your regular Bitquery account.

Is it free?

There is a free tier inherited from your Bitquery account. Heavier workloads — high request rates, large historical scans, or execute_sql — require a paid Bitquery plan. The MCP server itself does not add a separate charge.

Documentation

• MCP Installation Guide
• Bitquery Docs
• Generate API credentials
• Model Context Protocol Spec
• Bitquery Account