How to Use the Coze MCP in CrewAI

Q: How do I add the Coze MCP Server to a CrewAI agent?

Install crewaitools and pass the endpoint URL directly into the mcps array on your agent definition. For more control over which tools load, use MCPServerHTTP with a toolfilter.

Q: How do I restrict a CrewAI agent to only read Coze data?

Use the toolfilter parameter when setting up the connection. You can expose getconversationhistory and listbots while blocking destructive actions like deleting documents.

Deploy specialized autonomous agents to moderate Coze conversations and manage workspaces using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coze MCP to CrewAI

Create your Vinkius account to connect Coze 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 Coze with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Coze sessions with CrewAI

You cannot manually watch every user interacting with your bots. Hooking this MCP Server into your crew means a specialized monitoring agent can scan live sessions for policy violations or stuck conversations. Assign one agent to run `get_conversation_history` on a loop. If it detects inappropriate content, it flags a moderator agent. The moderator then executes `clear_conversation` to wipe the session immediately.

Delegate knowledge base updates

Managing raw text across multiple spaces gets messy fast. You can build a researcher agent that finds new information and a librarian agent that files it correctly. The researcher passes plain text to the librarian. The librarian uses `list_workspaces` to find the correct target, then fires `upload_document` to update the dataset. This MCP Server lets them handle the entire pipeline without your input.

Simulate users for bot QA

Testing complex bots requires hitting them with unpredictable inputs. A QA agent can act as a chaotic user while an analyst agent records how the bot responds. The QA agent triggers `create_chat` with edge-case prompts. If the bot requests external data, a mock-server agent provides fake responses via `submit_tool_outputs`. The crew evaluates the final output for accuracy.

Setup guide

Set up Coze 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 Coze tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install crewai[tools] and pass the endpoint URL directly into the mcps array on your agent definition. For more control over which tools load, use MCPServerHTTP with a tool_filter.

Yes. Because they share memory, Agent A can discover IDs using list_workspaces and pass that context to Agent B, who then uploads files to that specific space.

The framework supports stdio, SSE, and Streamable HTTP transports natively. You just provide the URL and the system handles the connection layer.

Use the tool_filter parameter when setting up the connection. You can expose get_conversation_history and list_bots while blocking destructive actions like deleting documents.

Your conversation logs and raw document text process entirely in memory. Vinkius spins up a dedicated sandbox for the request and destroys it the millisecond the HTTP response sends. We never log your chat history.

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