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

Q: How do I query Mirror.xyz (Web3 Publishing Platform) posts using LangChain?

Use the getentries tool within a LangChain agent to fetch digests for an ENS domain. The agent can then loop through those digests to retrieve full posts using the getentry tool.

Q: Can I chain Mirror.xyz (Web3 Publishing Platform) outputs to other LangChain tools?

Yes. You can take the markdown output from getentry and pass it directly to a vector store tool or a database tool in the same chain. The framework handles the data flow between the MCP Server and your other integrations.

Q: What happens if a Mirror.xyz digest fails to resolve in LangChain?

The getentry tool returns an error message if the Arweave gateway is down or the digest is invalid. Your LangChain run can catch this exception and decide to retry or skip that entry.

Feed Mirror.xyz publication data directly into your LangChain chains 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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Parse Mirror.xyz feeds with LangChain chains

The `get_entries` tool connects your agent to the Mirror.xyz MCP Server to fetch publication digests for any ENS domain you feed into your LangChain run. Your agent uses this tool to resolve ENS addresses like optimism.eth and extract the underlying content identifiers. You feed these digests directly into downstream chains. This sets up a pipeline where the first step resolves the publication feed and the next step runs summarization on the returned digests.

Fetch raw Arweave content for prompt templates

The `get_entry` tool retrieves the full markdown content of a publication using its specific Arweave transaction digest. This lets your agent pull the exact text of a post without needing to scrape web pages. You can route this raw text into LangChain prompt templates for translation or sentiment analysis. Because the tool returns raw data, your LLM works with clean text instead of messy HTML.

Trace Web3 content runs in LangSmith

The `get_entries` and `get_entry` tools work with LangSmith to show you exactly how your agent queries Mirror.xyz. You see the latency of the GraphQL queries and the exact token size of the Arweave payloads. This visibility helps you spot slow gateway responses or excessive token usage when fetching large posts. You get a clear log of every tool call in your multi-step Web3 agent workflows.

Setup guide

Set up Mirror.xyz (Web3 Publishing Platform) 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 Mirror.xyz (Web3 Publishing Platform) 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({
    "mirrorxyz-web3-publishing-platform-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 Mirror.xyz (Web3 Publishing Platform) 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 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 LangChain

Use the `get_entries` tool within a LangChain agent to fetch digests for an ENS domain. The agent can then loop through those digests to retrieve full posts using the `get_entry` tool.

Yes. You can take the markdown output from `get_entry` and pass it directly to a vector store tool or a database tool in the same chain. The framework handles the data flow between the MCP Server and your other integrations.

The server queries public endpoints that do not require API keys. If your LangChain agent makes rapid, successive calls to `get_entries`, you should implement a simple rate-limiting wrapper in your chain config to avoid gateway errors.

The `get_entry` tool returns an error message if the Arweave gateway is down or the digest is invalid. Your LangChain run can catch this exception and decide to retry or skip that entry.

This server only processes public blockchain data, specifically ENS domains and Arweave digests. No private keys or personal credentials pass through the MCP Server, keeping your Web3 publishing workflows secure.

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