How to Use the Exa MCP in AutoGen

Give your AutoGen agents neural web search capabilities to debate with real-time, conceptually accurate data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa MCP to AutoGen

Create your Vinkius account to connect Exa 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 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Power AutoGen debates with neural search

The `exa_search` tool provides your agents with conceptually relevant web results rather than simple keyword matches. During a debate, a research agent can query the web to back up its arguments with real-time facts. This MCP Server returns page text, highlights, and relevance scores. Your agents can parse these scores to negotiate and converge on the most accurate decision based on solid evidence.

Extract clean web text for agent analysis

The `exa_get_contents` tool pulls clean, structured text from specific URLs, removing the HTML clutter that confuses conversational agents. This allows your security or performance agents to review actual page text without getting bogged down by raw code. Because the text is pre-cleaned, your agents save token budget during long deliberations. They can focus their reasoning cycles on the actual content instead of parsing junk.

Discover alternative viewpoints for AutoGen consensus

The `exa_find_similar` tool identifies web pages semantically related to a seed URL, giving your agents a way to discover opposing or alternative viewpoints. This is crucial when building consensus-driven systems where agents must challenge each other's assumptions. This MCP tool allows an agent to feed a competitor's URL into this tool to quickly gather alternative sources. The team of agents can then debate the merits of each source before delivering a final report.

Setup guide

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

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

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

Install the extension package and use the HTTP server parameters to fetch the tools. Pass the resulting tool list directly to your agent constructor.

One agent can run a search query, while another agent analyzes the relevance scores and highlights to verify the claims before making a final decision.

Yes. The server handles concurrent requests in isolated sandboxes, allowing multiple agents to run searches or extract page contents in parallel during a debate.

Yes, you can set the search type to deep for a thorough sweep of the web, or instant when your agents need fast answers to maintain conversational flow.

Your raw search queries and scraped URLs are processed within a zero-trust, ephemeral V8 sandbox on Vinkius. No query logs or scraped page data are stored on our servers, keeping your multi-agent conversations private.

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