How to Use the Exa AI MCP in CrewAI

Q: How do I add Exa AI tools to a CrewAI agent?

Pass your Vinkius endpoint URL directly into the agent's mcps list. CrewAI automatically connects to the MCP Server and registers tools like semanticsearch and extractpagecontent for that specific agent.

Q: Can I limit which Exa AI tools from the MCP Server a specific CrewAI agent can use?

Yes, you can use MCPServerHTTP from the crewai.mcp package along with a tool filter to expose only specific tools, such as searchbycrawldate, to your research agents.

Q: What happens if the web search tool returns too much text?

You should have your agents use getqueryhighlights instead of pulling the entire page. This keeps the token payload small and prevents your agents' context windows from overflowing.

Deploy specialized agent teams to research, filter, and analyze the web using CrewAI and Exa AI.

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 CrewAI

Create your Vinkius account to connect Exa AI 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 AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative research crews using CrewAI

CrewAI shines when you divide complex tasks among specialized agents rather than relying on a single generic model. You can assign a Researcher Agent to run `semantic_search` across the web, while an Analyst Agent processes those results to extract key insights. This collaborative setup lets you pass the output of a broad search directly into another agent's context. That second agent can then trigger `get_query_highlights` to pull precise quotes without manual coding.

Targeted domain filtering for autonomous agents

To keep your autonomous crew from wandering off into irrelevant corners of the web, use this MCP Server to restrict their scope. Your monitoring agent can force the research agent to use `search_specific_domains` when looking for technical specifications. If the agent needs to branch out, it can use `search_by_category` to discover trusted industry-specific portals. This keeps your multi-agent runs highly focused and prevents them from wasting API tokens on generic blog posts.

Deep web analysis with shared agent memory

When your crew is executing a complex, multi-turn research task, maintaining context is everything. As one agent finds a high-quality source using `find_similar_pages`, that URL is saved to CrewAI's shared memory. A secondary scraping agent can then pick up that URL from memory and run `extract_page_content` to gather the raw text. This separation of duties ensures high reliability and clean data extraction across your entire automated pipeline.

Setup guide

Set up Exa AI 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 AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Exa AI 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 AI Analyst",
        goal="Access and analyze Exa AI data via MCP.",
        backstory="Expert analyst with direct Exa AI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Exa AI 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 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 CrewAI

Pass your Vinkius endpoint URL directly into the agent's `mcps` list. CrewAI automatically connects to the MCP Server and registers tools like `semantic_search` and `extract_page_content` for that specific agent.

Yes, you can use `MCPServerHTTP` from the `crewai.mcp` package along with a tool filter to expose only specific tools, such as `search_by_crawl_date`, to your research agents.

CrewAI agents use shared memory to pass search results. For example, a research agent can run `search_with_contents` and pass the raw extracted text directly to a writer agent in the next task of the crew.

You should have your agents use `get_query_highlights` instead of pulling the entire page. This keeps the token payload small and prevents your agents' context windows from overflowing.

All search terms, target domains, and crawled content are routed through Vinkius's secure V8 isolates. Your MCP queries and extracted web texts are processed entirely in-memory and are never logged or stored permanently.

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