How to Use the Exa MCP in CrewAI

Deploy specialized research crews using Exa tools to automate complex web discovery without human intervention.

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 CrewAI

Create your Vinkius account to connect Exa to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized search for CrewAI crews

Assign `exa_search` to a specific research agent within your crew to handle data gathering. It finds conceptually relevant information that standard keyword tools overlook. Your agents work in parallel or sequence to process these findings. You get a cohesive report built from multiple, high-quality web sources.

Granular content extraction

Your analyst agents use `exa_get_contents` to pull only the relevant text from identified pages. This keeps your crew's shared memory focused on actual facts. By feeding clean content to your agents, you reduce noise in your collaborative output. The entire crew stays aligned on the right information.

Autonomous discovery loops

Use `exa_find_similar` to let agents explore related topics on their own. This creates an autonomous feedback loop where agents discover new leads without manual input. Your crew builds a deeper understanding of the subject matter over time. It’s a hands-off way to manage complex research operations.

Setup guide

Set up Exa MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Exa tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Exa Analyst",
    goal="Access and analyze Exa data via MCP.",
    backstory="Expert analyst with direct Exa access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Exa transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Exa Analyst",
        goal="Access and analyze Exa data via MCP.",
        backstory="Expert analyst with direct Exa access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Exa transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You simply add the server URL to the agent's MCP configuration. The tools become available to the crew immediately, allowing for role-based access.

Yes, you can share the MCP server across the entire crew. Each agent can call the tools independently based on their specific role and objective.

The API is optimized for speed, allowing your crew to finish tasks faster. You can choose different search types depending on whether you need instant results or deep analysis.

Vinkius handles the underlying infrastructure and authentication. You just provide the token and the endpoint, and the server stays ready for your crew.

All tool interactions are isolated and ephemeral. The server does not store your search history or the content it retrieves, ensuring your research remains 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