How to Use the Exa AI MCP in AutoGen

Q: Can Exa AI and AutoGen use the live crawl tool?

Yes. The performlivecrawl tool is available in the tool list. Your agents can trigger it when they need the absolute latest content from a URL.

Enable multi-agent debate and consensus using the Exa AI MCP Server in AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa AI MCP to AutoGen

Create your Vinkius account to connect Exa AI 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 Exa AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Agents debate using Exa AI search tools

One agent proposes a search, another challenges the source, and they negotiate the final query. This makes `advanced_custom_search` part of a group discussion. It ensures that the information retrieved via `perform_live_crawl` is vetted by your agent team. They converge on the best answer through disagreement.

Register Exa AI MCP Server tools automatically

The adapter maps the 12 tools to your agent's capability set. You don't need to write custom handlers for each endpoint. Your assistants gain immediate access to `find_similar_pages` or `keyword_search` by simply referencing the tool list. It handles the transport over HTTP automatically.

Verify search status with Exa AI

Include a monitor agent that calls `get_api_status` to ensure your search infrastructure is healthy. It catches connection issues before your main agents start their debate. This adds a layer of reliability to your multi-agent system. If the tools are offline, the agents know to wait or report the error.

Setup guide

Set up Exa AI 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 Exa AI 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="Exa AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Exa AI 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="Exa AI_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Exa AI 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 Exa AI. 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 Exa AI 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 Exa AI MCP in AutoGen

You pass the tool list from the server to your AssistantAgent. The agent then decides when to invoke the Exa AI tools during the conversation.

Yes. You can share the tool list across multiple agents. Each agent can use the Exa AI tools to gather evidence for their part of the debate.

Yes. The perform_live_crawl tool is available in the tool list. Your agents can trigger it when they need the absolute latest content from a URL.

We manage the server in an ephemeral sandbox. You only need to provide an endpoint token to authorize your agent's access to the tools.

The server does not log your search history. Your queries and the resulting content are handled within your local AutoGen environment and are never stored by us.

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