How to Use the Covalent MCP in LangChain

Q: How do I install the Covalent MCP Server in LangChain?

Run pip install langchain-mcp-adapters langgraph. Use MultiServerMCPClient to connect to the Vinkius endpoint and pass the resulting tools to your createagent function.

Q: How do I get NFT data using Covalent and LangChain?

Give your agent access to the getnftbalances tool. It will resolve contract names, token IDs, and image links directly into the active chain context.

Build multi-step blockchain data pipelines by plugging Covalent into your LangChain agents via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Covalent MCP to LangChain

Create your Vinkius account to connect Covalent 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 Covalent with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Covalent MCP Server with local databases

LangChain agents excel when you give them building blocks. Pass `list_supported_chains` output directly into a vector store to keep your internal network directory updated. ReAct agents can decide what to do next based on intermediate results. If a user asks for a wallet's net worth, the agent calls `get_historical_portfolio`, parses the USD valuations, and passes that context to a reporting tool further down the chain.

Trace blockchain queries via LangSmith

Every tool call generates telemetry. When your agent runs `get_transaction_details`, LangSmith tracks the exact parameters, latency, and token usage for that specific query. You see exactly why an agent chose a specific path. If it fails to find liquidity data, you can check the trace to see if it fed the wrong DEX address into `get_dex_pools` before trying to fix the prompt.

Build multi-step token reasoning pipelines

Complex blockchain queries require multiple steps. Your agent can fetch a user's assets using `get_token_balances`, then loop through those contract addresses to grab transfer history via `get_token_transfers`. The output of one Covalent tool becomes the input for the next. Agents handle the formatting and parameter extraction automatically, turning raw chain data into structured insights without manual data mapping.

Setup guide

Set up Covalent 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 Covalent 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({
    "covalent-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 Covalent 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 Covalent. 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 Covalent 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 Covalent MCP in LangChain

Run `pip install langchain-mcp-adapters langgraph`. Use `MultiServerMCPClient` to connect to the Vinkius endpoint and pass the resulting tools to your `create_agent` function.

Yes. The server supports over 100 networks. Your agent can check `get_chains_status` to verify API availability before fetching data.

It does. While the MCP connection is stateless by default, you can use `client.session()` to keep context persistent across multiple wallet queries.

Give your agent access to the `get_nft_balances` tool. It will resolve contract names, token IDs, and image links directly into the active chain context.

Vinkius runs the server in an ephemeral V8 Isolate Sandbox. When your agent queries transaction hashes or wallet balances, the instance dies immediately after returning the data. Nothing persists on our infrastructure.

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