How to Use the Exa AI MCP in AutoGen

Q: How do AutoGen agents share Exa AI search results with each other?

When an agent calls searchwithcontents, the resulting text is posted directly to the group chat. Other agents in the AutoGen session can then read, critique, or extract key facts from that shared context.

Q: Can my agents check their API budget during a conversation?

Yes, any agent in the group can call getapiusage to retrieve crawl statistics. This allows your coordinator agent to halt the conversation if the search budget has been exceeded.

Let your AutoGen agents debate and verify live web sources using the Exa AI MCP Server.

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

Fuel multi-agent debates with this Exa AI MCP Server

Running `search_web` allows your research agent to gather raw links, while your critic agent uses `get_contents` to verify the substance of those pages. In an AutoGen setup, a single search query isn't just executed; it is analyzed and debated. This collaborative loop prevents agents from hallucinating or accepting low-quality search results. By integrating this Exa AI MCP Server, your team of agents can cross-reference facts and reach a consensus based on real-time data.

Let agents negotiate search strategies on the fly

Calling `get_api_usage` lets your AutoGen agents check their budget and decide whether to run a broad semantic search or a targeted similarity lookup. With this MCP integration, a performance agent might push to use `get_search_links` to quickly grab URLs, while a thorough research agent demands the full text from `search_with_contents`. AutoGen allows these agents to discuss and negotiate the best approach. They can check their budget and adjust their search depth dynamically based on real-time crawl statistics.

Discover parallel perspectives using similarity tools

Using `find_similar` lets your agents challenge each other's biases by locating alternative viewpoints. If one agent finds a biased source, another agent can pass that URL to the similarity tool to locate alternative viewpoints and balance the conversation. This capability is crucial for generating objective reports. The agents can automatically fetch, clean, and compare different web sources, ensuring the final output is well-rounded and thoroughly vetted.

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

When an agent calls `search_with_contents`, the resulting text is posted directly to the group chat. Other agents in the AutoGen session can then read, critique, or extract key facts from that shared context.

Yes, you can register the MCP tools to a specific AssistantAgent. For example, you can give your Researcher agent access to `search_web` while keeping your Writer agent focused purely on drafting.

The McpToolAdapter automatically translates the JSON schemas of tools like `find_similar` into the format AutoGen expects. Your agents can call these tools natively without any manual mapping code.

Yes, any agent in the group can call `get_api_usage` to retrieve crawl statistics. This allows your coordinator agent to halt the conversation if the search budget has been exceeded.

All target URLs and search queries are transmitted directly to the Exa API via encrypted tunnels. The local runtime does not cache or store your search history, protecting your proprietary research topics from leaks.

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