How to Use the Arweave MCP in LlamaIndex

Q: How does LlamaIndex prevent hallucinations when reading Arweave data?

By using gettransactiondata to fetch the exact payload of a transaction, LlamaIndex indexes the real on-chain content. The agent then references this verified text directly, avoiding any fabricated answers about historical data.

Q: Can I use LlamaIndex to search Arweave metadata?

Yes. Your pipeline can use querygraphql to find transactions matching specific tags, and then pass those IDs to gettransaction to build a semantic index of all related content.

Q: Does LlamaIndex expose my Arweave wallet balances to the public?

No, all queries to getwalletbalance and getwalletlasttx run through an ephemeral, zero-trust sandbox on Vinkius. Your financial data is only passed to your local LlamaIndex environment and is never cached or exposed to external third parties.

Index live Arweave transaction data and block history directly into your LlamaIndex RAG pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arweave MCP to LlamaIndex

Create your Vinkius account to connect Arweave 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 Arweave with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index historical blocks into LlamaIndex

The `get_block_by_height` tool retrieves raw block data, which your LlamaIndex pipeline can parse and index into a vector store. This turns static blockchain history into a searchable knowledge base that your agent can query semantically. By combining this with `get_block_by_hash`, your RAG application can retrieve specific block metadata to resolve user queries. The agent avoids hallucinating block details because it grounds its answers in the actual data returned by the server.

Search transaction content using RAG workflows

The `get_transaction_data` tool pulls the actual payload stored on the permaweb, allowing LlamaIndex to chunk and embed the text. This means you can build document search engines that run entirely on top of immutable, decentralized data. Your agent uses `get_transaction_offset` to handle large files, downloading only the segments it needs to answer a specific question. This keeps your indexing pipeline fast and minimizes memory usage when dealing with large datasets.

Query active network states with this MCP Server

This MCP Server lets your LlamaIndex agent fetch real-time network metrics using `get_network_info` and `get_peers`. The agent can index this status data to provide real-time dashboards or monitor the health of the decentralized network. When users ask about network congestion or transaction costs, the agent runs `get_storage_price` and updates its local index. This ensures your knowledge base always reflects the current financial and technical state of the blockchain.

Setup guide

Set up Arweave 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 Arweave 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 Arweave tools.",
)
response = await agent.run("List recent Arweave 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 Arweave. 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 Arweave 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 Arweave MCP in LlamaIndex

By using `get_transaction_data` to fetch the exact payload of a transaction, LlamaIndex indexes the real on-chain content. The agent then references this verified text directly, avoiding any fabricated answers about historical data.

Yes. Your pipeline can use `query_graphql` to find transactions matching specific tags, and then pass those IDs to `get_transaction` to build a semantic index of all related content.

Install the LlamaIndex Arweave tool package and initialize the basic client pointing to your Vinkius endpoint. This exposes all 13 tools, including `get_wallet_balance`, directly to your agent's tool spec.

Yes, you can use the allowed tools filter in the tool spec to restrict your agent's capabilities. For example, you can expose `get_network_info` while hiding transactional tools like `submit_transaction`.

No, all queries to `get_wallet_balance` and `get_wallet_last_tx` run through an ephemeral, zero-trust sandbox on Vinkius. Your financial data is only passed to your local LlamaIndex environment and is never cached or exposed to external third parties.

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