How to Use the Wrike MCP in AutoGen

Q: Can I get comprehensive project status using AutoGen and Wrike?

Yes. You can assign an agent to list all projects (listwrikeprojects) and another agent to check the task details (gettaskdetails) for each one, forcing them to reconcile any discrepancies in their findings.

Q: Is it possible for multiple agents to reference the same Wrike folder?

Absolutely. Agents can independently call listwrikefolders or pass a specific folder ID into listwriketasks, and their resulting data feeds into the conversation for debate.

Force consensus: AutoGen's multi-agent debate framework with Wrike MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wrike MCP to AutoGen

Create your Vinkius account to connect Wrike to AutoGen 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 Wrike with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Project Strategy with AutoGen

You can set up multiple agents to argue over project planning. One agent calls `list_wrike_projects` for an overview, while a second agent uses `get_task_details` to check the specific status of key tasks within those projects. The final decision isn't just one tool call; it’s a consensus reached after agents challenge and refine their initial findings.

MCP Server for Multi-Agent Planning

The `wrike-mcp` server provides the raw data points that agents debate. For instance, Agent A lists available spaces using `list_wrike_spaces`. Agent B then checks which projects fall into those spaces using `list_wrike_projects`, debating the best next steps based on conflicting information. This forces a discussion that leads to a robust outcome.

Coordinating Wrike Contact Management

Imagine two agents talking: one needs to know who's available, so it calls `list_wrike_contacts`. The other agent then uses the returned contacts list to verify task assignments using `list_wrike_tasks`. They debate which contact is best suited for a specific role before finalizing the plan.

Setup guide

Set up Wrike MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Wrike tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Wrike_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Wrike data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Wrike_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Wrike data")
    print(result.messages[-1].content)

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 Wrike. 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 Wrike 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 Wrike MCP in AutoGen

The server's tools are provided to multiple agents as potential actions. The agents then debate which tool should run and what the optimal parameters are, leading to a collective decision rather than a single execution.

Yes. You can assign an agent to list all projects (`list_wrike_projects`) and another agent to check the task details (`get_task_details`) for each one, forcing them to reconcile any discrepancies in their findings.

The server supports all core Wrike resources: tasks, projects, folders, spaces, and contacts. The agents use these different data types to negotiate a final plan.

Absolutely. Agents can independently call `list_wrike_folders` or pass a specific folder ID into `list_wrike_tasks`, and their resulting data feeds into the conversation for debate.

The server touches organizational resources including task details, project listings, folder structures, and user contacts. All access is governed by the single endpoint token managed through Vinkius.

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