How to Use the TzKT (Tezos Indexer & Explorer API) MCP in LangChain

Q: Can LangChain aggregate contract and account data using TzKT (Tezos Indexer & Explorer API)?

Absolutely. Your agent can first use listcontracts to identify a target, then call getcontractcode, and finally cross-reference the code's behavior against an account's history by calling getaccountreport. The chain manages this flow.

Q: Does LangChain help track token movements across multiple accounts with TzKT (Tezos Indexer & Explorer API)?

Yes. By chaining calls like listaccounts followed by listtokentransfers, your agent can map out complex asset flows, giving you a full audit trail of how tokens moved between various wallets.

Build multi-step Tezos data pipelines with LangChain and your AI agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TzKT (Tezos Indexer & Explorer API) MCP to LangChain

Create your Vinkius account to connect TzKT (Tezos Indexer & Explorer API) 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 TzKT (Tezos Indexer & Explorer API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace complex account investigations.

You start by calling `list_accounts` to filter for target users based on activity or balance. Then, you feed the resulting accounts into `get_account_report`, which generates a full JSON report of that account's movements. This chain allows your agent to follow complex reasoning paths: identifying relevant contract entrypoints using `get_contract_entrypoints` before finally listing all related transactions via `list_token_transfers`. The output of one step dictates the next action.

Map out smart contract lifecycles.

When investigating a smart contract, you first use `list_contracts` to find available contracts. Next, call `get_contract_code` to pull the raw Michelson or Micheline code for review. You can then check how that code interacts with existing data by calling `get_contract_storage`, providing a complete picture of its current state. This sequence lets your agent verify the contract's structure and history. It also supports checking the list of available entrypoints using `get_contract_entrypoints` to ensure all interaction vectors are mapped.

Analyze network-wide financial movements.

To get a macro view, you start by calling `get_statistics` for overall TPS and volume data. You can then pivot to specific user activity by using `list_token_balances`, which gives token counts across multiple accounts. This allows the chain to aggregate data: comparing network-level trends with granular account data. You'll also use `list_delegations` to understand staking activity and measure how rewards are distributed cycle over cycle.

Setup guide

Set up TzKT (Tezos Indexer & Explorer API) 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 TzKT (Tezos Indexer & Explorer API) 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({
    "tzkt-tezos-indexer-explorer-api-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 TzKT (Tezos Indexer & Explorer API) 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 TzKT. 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 TzKT (Tezos Indexer & Explorer API) 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 TzKT (Tezos Indexer & Explorer API) MCP in LangChain

LangChain handles complexity by linking tool outputs to subsequent inputs. For instance, you might use `list_transactions` first; the resulting transaction hashes can then be immediately fed into a call to `get_operations_by_hash`. It's about building sequential reasoning.

Absolutely. Your agent can first use `list_contracts` to identify a target, then call `get_contract_code`, and finally cross-reference the code's behavior against an account's history by calling `get_account_report`. The chain manages this flow.

Yes. By chaining calls like `list_accounts` followed by `list_token_transfers`, your agent can map out complex asset flows, giving you a full audit trail of how tokens moved between various wallets.

The MCP Server provides real-time Tezos blockchain data, so the results are directly pulled from the index. You get accurate account balances and transaction details every time you run a chain.

This server primarily exposes structured financial records, including token transfer manifests (`list_token_transfers`), account balance histories, and detailed contract storage JSON objects.

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