How to Use the DeepSeek MCP in CrewAI

Q: Can a CrewAI agent use DeepSeek to reason about its own past actions?

Yes. You can have one agent use the listrequesthistory tool to get a log of actions. Then, it can pass that log to another agent equipped with the deepreasoning tool to analyze the history for patterns or errors.

Equip your CrewAI agents with DeepSeek's reasoning. Assign roles for research, analysis, and execution to build autonomous teams.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepSeek MCP to CrewAI

Create your Vinkius account to connect DeepSeek 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 DeepSeek with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble a DeepSeek Research Crew

Create a team of agents with specific jobs. An 'Idea Agent' uses `chat_completion` to generate strategies. A 'Critique Agent' then takes that output and uses `deep_reasoning` to analyze the logic and find flaws. CrewAI lets these agents pass work back and forth, refining the result with each step. The DeepSeek MCP server gives them the distinct tools they need to perform their specialized roles, creating a true collaborative process.

An Agent Crew to Manage Your Account

Set up a 'Billing Agent' whose only job is to watch your DeepSeek account. It periodically calls `get_balance` and `get_token_usage`. This is its entire world. If a threshold is crossed, it passes the task to an 'Action Agent.' That agent can then use other tools to send a notification or pause less critical tasks. CrewAI's role-based structure makes this a clean and powerful pattern.

The DeepSeek MCP Server for Auditing

Designate an 'Auditor Agent' in your crew. This agent's sole task is to use `list_request_history` to review what the other agents have been doing. It's a built-in check on your autonomous system. The Auditor can even use `chat_prefix_completion` to generate structured JSON reports on API usage patterns. This isn't just about getting work done; it's about building a system that can monitor itself.

Setup guide

Set up DeepSeek 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 DeepSeek tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent DeepSeek 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 DeepSeek. 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 DeepSeek 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 DeepSeek MCP in CrewAI

When you define an Agent in CrewAI, you can pass a filtered list of tools to it. This means your 'Billing Agent' can be limited to only the `get_balance` and `get_token_usage` tools from this MCP Server, and nothing else.

Yes. You can have one agent use the `list_request_history` tool to get a log of actions. Then, it can pass that log to another agent equipped with the `deep_reasoning` tool to analyze the history for patterns or errors.

A simple, effective setup is a two-agent crew. Agent one, the 'Monitor', runs on a schedule and calls `get_token_usage`. If it hits a limit, it delegates a task to agent two, the 'Notifier', which sends an alert.

No, it's simple. You just pass the Vinkius MCP URL directly into the `mcps` parameter when creating your Agent. CrewAI and Vinkius automatically negotiate the best protocol.

Vinkius uses ephemeral, zero-trust sandboxes. Each request for data like `billing_details` or `token_usage` runs in a completely new, isolated environment that is destroyed the moment the request is complete. Your data is never stored.

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