Which Base URL should I use for my account?

If you are using the international version, use `https://api.coze.com`. For the Chinese version, use `https://api.coze.cn`.

Can I automatically list all published bots in a space?

Yes! Use the `list_bots` tool with your Space ID. Your agent will return a list of all bots that have been published and are ready for interaction.

How do I upload a new document to my knowledge base?

Use the `upload_document` tool with the target Dataset ID and the raw text content. Your agent will handle the ingestion process into the Coze RAG engine.

Coze MCP Server for CrewAI 11 tools — connect in under 2 minutes

Name: Coze
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 11 Tools Framework

Connect your CrewAI agents to Coze through Vinkius, pass the Edge URL in the `mcps` parameter and every Coze tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Coze Specialist",
    goal="Help users interact with Coze effectively",
    backstory=(
        "You are an expert at leveraging Coze tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Coze "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 11 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Coze MCP Server

Connect your AI agents to Coze (扣子), the advanced bot orchestration platform by ByteDance. This MCP provides 11 tools to manage the full lifecycle of your bots, from chat interactions to knowledge base document ingestion.

When paired with CrewAI, Coze becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Coze tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

What you can do

Bot Interaction — Chat with published bots and handle multi-turn conversations with persistent history
Knowledge Engineering — Upload, list, and delete documents in knowledge base datasets for RAG optimization
Workspace Management — List available spaces and published bots to monitor your AI ecosystem
Action Handling — Submit tool outputs when bots require human-in-the-loop or external plugin results

The Coze MCP Server exposes 11 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Coze to CrewAI via MCP

Follow these steps to integrate the Coze MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 11 tools from Coze

Why Use CrewAI with the Coze MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Coze through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Coze + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Coze MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Coze for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Coze, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Coze tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Coze against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Coze MCP Tools for CrewAI (11)

These 11 tools become available when you connect Coze to CrewAI via MCP:

clear_conversation

Clear all messages from a conversation session

create_chat

Send a message to a Coze bot and get a response

delete_document

Delete documents from a dataset by ID

get_conversation_history

Retrieve the message list from a conversation

list_bots

List published bots in a specific Coze Space

list_datasets

List knowledge base datasets in a Coze Space

list_workspaces

List available Coze workspaces/spaces

publish_bot

Publish a Coze Bot draft

submit_tool_outputs

Submit outputs for tools/plugins required by the bot

upload_document

Upload a raw text document to a Knowledge Base

upload_file_url

Upload an external file URL to Coze storage

Example Prompts for Coze in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Coze immediately.

"Chat with bot 'bot_123' and ask 'Tell me about the history of Tokyo'."

"List all active workspaces in my Coze account."

"Upload the content of 'manual.txt' to dataset 'ds_999'."

Troubleshooting Coze MCP Server with CrewAI

Common issues when connecting Coze to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Coze + CrewAI FAQ

Common questions about integrating Coze MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.