How to Use the Nearblocks (Near Blockchain Explorer API) MCP in AutoGen

Q: How do I give my AutoGen agents access to the Nearblocks (Near Blockchain Explorer API) tools?

After installing autogen-extmcp, you use the mcpservertools function with your Vinkius server URL. This returns a list of tools that you can pass directly into the AssistantAgent constructor during setup.

Deploy teams of AI agents that debate and analyze Near blockchain data 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 Nearblocks (Near Blockchain Explorer API) MCP to AutoGen

Create your Vinkius account to connect Nearblocks (Near Blockchain 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 Nearblocks (Near Blockchain Explorer API) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Simulate a Team of Blockchain Analysts

AutoGen lets you build systems where multiple agents collaborate. You can assign different roles to each agent, armed with specific Nearblocks tools. For example, a 'ComplianceAgent' could use `get_account_transactions` to monitor for large transfers, while a 'PortfolioAgent' uses `get_account_inventory` to track NFT values. These agents don't just act; they converse. The ComplianceAgent might flag a transaction, and the PortfolioAgent could respond by using `get_transaction_details` to provide context about the assets involved. The final output is a result of their discussion, not a single agent's guess.

Debate On-Chain Strategy

Use this MCP Server to feed live data into agent debates. You could have one agent argue for a specific action based on data from `get_network_stats`, while another agent uses `get_recent_transactions` to argue that network activity is too high, suggesting a delay. This is how you solve problems without a clear answer. By setting up agents with competing goals—one optimizing for speed, another for cost—they are forced to use the Nearblocks tools to find evidence, challenge each other, and reach a consensus. You're not just getting an answer; you're getting a reasoned argument.

Automate Complex Research Tasks

Delegate an entire research project to an AutoGen team. A 'LeadResearcher' agent could start by using `get_token_list` to identify a set of interesting tokens on the Near network. It then delegates tasks to specialist agents. One specialist could use `get_token_details` to gather contract information, while another uses `get_account_transactions` on the creator's account to analyze initial distribution. They report their findings back to the lead agent, who synthesizes the information into a final report. This automates workflows that would normally take a human analyst hours.

Setup guide

Set up Nearblocks (Near Blockchain 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 Nearblocks (Near Blockchain 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="Nearblocks (Near Blockchain Explorer API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nearblocks (Near Blockchain 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="Nearblocks (Near Blockchain Explorer API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nearblocks (Near Blockchain 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 Nearblocks. 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 Nearblocks (Near Blockchain 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 Nearblocks (Near Blockchain Explorer API) MCP in AutoGen

After installing `autogen-ext[mcp]`, you use the `mcp_server_tools` function with your Vinkius server URL. This returns a list of tools that you can pass directly into the `AssistantAgent` constructor during setup.

Yes. You can create multiple tool lists from the same MCP server and assign them to different agents. For instance, give your 'ValidatorWatcher' agent only the `get_latest_blocks` tool, while your 'AccountAuditor' gets `get_account_transactions`.

A great use case is automated due diligence. You can have one agent use `get_token_details` to check a token's total supply, a second agent use `get_account_transactions` on the deployer wallet, and a third agent summarize their findings to flag potential risks.

Based on the prompt and the ongoing conversation, each agent's underlying LLM decides which available tool is most appropriate. If one agent mentions a transaction hash, another agent might decide to use `get_transaction_details` to get more information.

The server provides public Near blockchain data (transactions, token details, etc.) to your agents. The entire conversation, including this data, happens within the secure, sandboxed environment managed by Vinkius. The agents' debate about public data remains private to your session.

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