How to Use the Jina AI MCP in CrewAI

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

You can pass your Vinkius connection URL directly into the mcps list when defining your CrewAI agent. The framework automatically discovers tools on the MCP server like searchweb and readurl.

Run autonomous research teams using CrewAI and Jina AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Jina AI MCP to CrewAI

Create your Vinkius account to connect Jina 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 Jina AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent research pipelines in CrewAI

Instead of one agent doing everything, CrewAI lets you deploy a team. Your researcher agent can use `search_web` to find sources, while your analyst agent uses `read_url` to extract the clean markdown for the crew. The entire process runs in the background of your CrewAI setup. Agents pass raw text chunks between themselves, using `get_embeddings` to keep track of what they have already verified.

Filter and rank information for your crew

Too much context slows down agent collaboration in CrewAI. You can assign an editor agent in CrewAI to run `rerank_documents` on the gathered data, ensuring only the most relevant text is passed to the writer agent. This keeps the CrewAI context window clean. The editor can also use `tokenize_text` to verify that the combined payload won't exceed the model's limits before triggering the next CrewAI task.

Autonomous fact-checking and verification

Let your moderator agent handle quality control in CrewAI. By exposing `check_fact` to your CrewAI setup, the moderator can automatically audit the claims made by the writer agent before final output. If a claim is flagged as false, the CrewAI moderator agent assigns a new task to the researcher to find better sources using this MCP Server. This loop runs autonomously until the data is solid.

Setup guide

Set up Jina 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 Jina AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Jina 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 Jina 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 Jina 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 Jina AI MCP in CrewAI

You can pass your Vinkius connection URL directly into the `mcps` list when defining your CrewAI agent. The framework automatically discovers tools on the MCP server like `search_web` and `read_url`.

Yes. Use the MCP server interface from the CrewAI library and apply a `tool_filter`. This lets you give the researcher agent access to `search_web` while keeping it hidden from the writer agent.

CrewAI agents use shared memory. When the researcher agent calls `read_url`, the cleaned markdown is stored in the crew's memory, allowing the analyst agent to immediately run `get_embeddings` on it.

The MCP integration supports stdio, SSE, and Streamable HTTP transports. Vinkius manages the hosting, so you just point CrewAI to the HTTP endpoint with your secure token.

Yes. All documents, queries, and scraped text chunks are processed within ephemeral V8 sandboxes. No data is cached or stored permanently on the server, keeping your research proprietary.

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