How to Use the Mirror.xyz (Web3 Publishing Platform) MCP in LlamaIndex

Q: How do I index Mirror.xyz (Web3 Publishing Platform) content into LlamaIndex?

Use the getentries tool to fetch publication digests, then pass them to getentry to retrieve the raw markdown. LlamaIndex can then parse this text into nodes and store them in your index.

Q: How does the LlamaIndex integration handle large Mirror.xyz (Web3 Publishing Platform) posts?

The getentry tool fetches the complete post from Arweave. You should use a LlamaIndex text splitter to break the markdown into manageable chunks before embedding them.

Q: Do I need a specialized parser for the markdown returned by the MCP Server?

No. The getentry tool returns clean markdown. LlamaIndex handles markdown parsing natively, so you can feed the tool output directly into your ingestion pipeline.

Index Mirror.xyz publication content directly into your LlamaIndex vector stores using our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mirror.xyz (Web3 Publishing Platform) MCP to LlamaIndex

Create your Vinkius account to connect Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz (Web3 Publishing Platform) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Mirror.xyz feeds with LlamaIndex

The `get_entries` tool retrieves a list of publication digests from the MCP Server for any ENS domain you query. LlamaIndex uses these digests to track which posts need to be pulled and indexed into your local vector database. This lets you build a pipeline that monitors specific ENS domains for new posts. Your agent checks for updates, gets the new digests, and prepares them for semantic ingestion.

Convert decentralized posts into queryable documents

The `get_entry` tool fetches the raw markdown content of a post using its Arweave digest. LlamaIndex wraps this markdown in a Document object, making it ready for chunking and embedding. Your agent queries these documents using natural language. Instead of guessing what a publisher wrote, your RAG system searches the actual text retrieved from Arweave.

Reduce search hallucinations with live Web3 data

The `get_entry` and `get_entries` tools ground your LlamaIndex queries in verified publishing data. Your agent pulls the exact text of a Mirror.xyz post instead of relying on outdated model weights. This mechanism ensures your RAG pipeline serves accurate information. You get factual answers directly from the decentralized web without risking LLM hallucinations.

Setup guide

Set up Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz (Web3 Publishing Platform) tools.",
)
response = await agent.run("List recent Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz. 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 Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz (Web3 Publishing Platform) MCP in LlamaIndex

Use the `get_entries` tool to fetch publication digests, then pass them to `get_entry` to retrieve the raw markdown. LlamaIndex can then parse this text into nodes and store them in your index.

Yes. Once the MCP Server retrieves the markdown content via `get_entry`, you embed the text into a vector store. You can then run standard LlamaIndex queries against those embeddings.

The `get_entry` tool fetches the complete post from Arweave. You should use a LlamaIndex text splitter to break the markdown into manageable chunks before embedding them.

No. The `get_entry` tool returns clean markdown. LlamaIndex handles markdown parsing natively, so you can feed the tool output directly into your ingestion pipeline.

This server only reads public blockchain data, specifically ENS domains, Arweave digests, and public markdown content. No private user data or wallet credentials are processed or stored during indexing.

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