How to Use the Bitquery (Web3 Blockchain GraphQL APIs) MCP in LangChain

Q: How do I pass credentials to Bitquery (Web3 Blockchain GraphQL APIs) inside LangChain?

You run generatetoken with your Client ID and Secret to get an active token. LangChain agents then pass this token automatically to subsequent queryv1 or queryv2 tool calls.

Q: How does this MCP Server handle large Bitquery (Web3 Blockchain GraphQL APIs) payloads in LangChain?

The server returns raw JSON data from queryv1 or queryv2 directly to the active chain. You can configure your agent's prompt to summarize the payload to keep token consumption low.

Run multi-step blockchain data pipelines in LangChain using raw GraphQL queries across 40 chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bitquery (Web3 Blockchain GraphQL APIs) MCP to LangChain

Create your Vinkius account to connect Bitquery (Web3 Blockchain GraphQL APIs) to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Bitquery (Web3 Blockchain GraphQL APIs) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain raw blockchain queries inside LangChain agents

This MCP Server exposes `query_v1` and `query_v2` directly to your multi-step chains so your agent pulls historical or streaming blockchain data on the fly. The output of a token transfer query feeds directly into the next chain step without hardcoded glue code. You track every single GraphQL payload and execution latency inside LangSmith. When an agent decides to pull DEX trades, you see the exact query format and token usage for that specific step.

Handle OAuth2 token generation in your active chains

The `generate_token` tool lets your agent fetch a fresh BITQUERY_ACCESS_TOKEN using your client credentials during runtime. This prevents expired session errors when long-running LangChain pipelines analyze multiple blocks. Your agent monitors token validity and pulls a new one only when needed. You don't have to write custom credential rotation scripts or pause your active chains.

Query real-time streams with LangChain memory

Use `query_v2` with this MCP Server to fetch active streaming data across Ethereum, Solana, or Bitcoin and pass it straight to your agent's memory. This tool supports complex joins like DexTrades and BalanceUpdates in a single call. Your agent processes these real-time streams, filters the results, and updates its internal state. You get direct access to live on-chain events without managing separate websocket connections.

Setup guide

Set up Bitquery (Web3 Blockchain GraphQL APIs) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Bitquery (Web3 Blockchain GraphQL APIs) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bitquery-web3-blockchain-graphql-apis-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Bitquery (Web3 Blockchain GraphQL APIs) transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Bitquery. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Bitquery (Web3 Blockchain GraphQL APIs) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Bitquery (Web3 Blockchain GraphQL APIs) MCP in LangChain

You run `generate_token` with your Client ID and Secret to get an active token. LangChain agents then pass this token automatically to subsequent `query_v1` or `query_v2` tool calls.

Yes, the agent analyzes the user request to select the right tool. It uses `query_v1` for historical data and `query_v2` for complex joins like DexTrades or streaming balance updates.

The server returns raw JSON data from `query_v1` or `query_v2` directly to the active chain. You can configure your agent's prompt to summarize the payload to keep token consumption low.

Every tool call made by the client is logged in LangSmith. You can inspect the exact GraphQL query strings generated by the agent and see the raw response payload.

Your Client ID and Secret remain in your local environment variables. The Vinkius MCP sandbox processes the `generate_token` call securely without persisting your API keys or query payloads on external disks.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript