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

Resolve complex Tezos data questions through multi-agent debate with AutoGen.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate account risk and activity.

You set up an agent system where one agent calls `get_account_report` to gather raw financial data, while a second agent uses `list_token_balances` to check current assets. The agents then debate if the reported activity represents high risk or normal operations. This consensus-driven process forces a deeper analysis than simple querying. A third agent might use `get_operations_by_hash` to pinpoint the exact transaction that caused the discrepancy.

Validate contract security and purpose.

Multiple agents tackle smart contracts. One focuses on performance, using `list_transactions` to check call volume; another acts as a reviewer, calling `get_contract_code` to flag potential vulnerabilities. The system converges only when the risk agent and the performance agent agree on the contract's operational status. This is critical for understanding complex contracts.

Synthesize network statistics and delegation facts.

You can force a debate between agents: one gathers overall market data using `get_statistics`, while another focuses only on staking, running `list_delegations`. The final decision is a synthesis of both the macro view and the micro-level stake health. This structure ensures that every piece of information—from general block details (`get_block`) to specific delegator rewards (`get_delegator_rewards`)—is considered in the final conclusion.

Setup guide

Set up TzKT (Tezos Indexer & Explorer API) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes TzKT (Tezos Indexer & Explorer API) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="TzKT (Tezos Indexer & Explorer API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent TzKT (Tezos Indexer & Explorer API) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="TzKT (Tezos Indexer & Explorer API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent TzKT (Tezos Indexer & Explorer API) data")
    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 AutoGen

AutoGen doesn't just execute; it makes agents debate the query. For example, if you ask about a contract bug, one agent checks `get_contract_code`, and another challenges that result by checking historical usage via `list_contracts`. The final answer is the consensus.

Yes, it excels here. You can assign agents to compare an account's movements (`get_account_report`) against the known rules defined in a specific smart contract's code (`get_contract_code`). The debate identifies mismatches.

It is. You can set up agents to argue over the meaning of a transfer: one agent checks `list_token_transfers` while another verifies if the source account had sufficient funds using `get_account`. The debate validates the movement.

Because it requires multiple agents to validate information across different tools, the resulting decision is highly vetted. It's not just one tool call; it’s a negotiated conclusion based on multiple MCP Server inputs.

The server exposes fundamental blockchain state data: contract code, account history, block headers (`get_head`), and staking records (`list_staking`).

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