How to Use the Blockchain.com Data MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinations using Blockchain.com Data?

The agent uses gettransaction and getblock to fetch real-time facts directly from the Bitcoin network. LlamaIndex indexes these exact responses, forcing the LLM to ground its answers in real data.

Q: Can I query historical charts using Blockchain.com Data in LlamaIndex?

Yes, the agent can call getchart to pull historical datasets and index them. This allows LlamaIndex to run semantic searches over actual Bitcoin network history.

Q: How do I filter which blockchain tools the agent can access?

You can use the allowedtools filter when setting up the MCP tool specification. This lets you restrict the agent to harmless tools like getticker while hiding write-heavy operations.

Index live Bitcoin transactions and block data directly into your LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blockchain.com Data MCP to LlamaIndex

Create your Vinkius account to connect Blockchain.com Data to LlamaIndex 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 Blockchain.com Data with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Bitcoin metrics into LlamaIndex memory

This MCP server exposes `get_network_stats` and `get_mempool_stats` to feed live chain state directly into your index. LlamaIndex takes this raw data, structures it, and writes it to your vector store for semantic querying. Instead of guessing block heights, your agent runs `get_block_count` and indexes the actual number. This ensures your RAG pipeline answers questions using verified, current blockchain facts rather than outdated training data.

Semantic search over historical blockchain charts

Retrieve historical market data using `get_chart` and let LlamaIndex parse it into queryable document chunks. Your user can ask complex questions about past market trends, and the engine retrieves the exact chart metrics to construct the answer. Use `get_ticker` alongside these charts to ground your financial queries in real-time fiat conversion rates. The McpToolSpec integration makes these tools look like native LlamaIndex data sources.

Build RAG pipelines around transaction histories

Your LlamaIndex agent can call `get_address` and `get_transaction` to pull complete history logs for any Bitcoin public key. The tool output is immediately indexed, allowing semantic search over wallet behaviors and past transfers. When verifying pending transfers, the agent queries `list_unconfirmed_transactions` to index what is currently stuck in the mempool. This gives your search index a real-time view of pending network activity.

Setup guide

Set up Blockchain.com Data MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Blockchain.com Data MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Blockchain.com Data tools.",
)
response = await agent.run("List recent Blockchain.com Data data")

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 Blockchain.com. 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 Blockchain.com Data 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 Blockchain.com Data MCP in LlamaIndex

Yes. You connect using BasicMCPClient, convert the server tools with McpToolSpec, and pass them to your LlamaIndex agent to fetch and index live chain data.

The agent uses get_transaction and get_block to fetch real-time facts directly from the Bitcoin network. LlamaIndex indexes these exact responses, forcing the LLM to ground its answers in real data.

Yes, the agent can call get_chart to pull historical datasets and index them. This allows LlamaIndex to run semantic searches over actual Bitcoin network history.

You can use the allowed_tools filter when setting up the MCP tool specification. This lets you restrict the agent to harmless tools like get_ticker while hiding write-heavy operations.

Completely safe. This MCP server only handles public Bitcoin transaction hashes and addresses, with zero access to your private credentials. Vinkius processes everything inside an ephemeral sandbox, meaning your indexed data never persists on our servers.

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