How to Use the Wrike MCP in LangChain

Q: Can I use LangChain to find all projects in Wrike?

Yes. You simply instruct your agent to call the listwrikeprojects tool. The output gives you an immediate list of active projects, which can then be used as context for other actions.

Build complex workflows with LangChain's ReAct agents and the 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 LangChain

Create your Vinkius account to connect Wrike to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining Tools for Complex Discovery

Your agent doesn't just call a tool; it chains calls together. First, you can ask your agent to run `list_wrike_spaces` to see what areas exist. Then, the output of that list feeds directly into calling `list_wrike_projects`, allowing your workflow to narrow down scope automatically. This multi-step reasoning means your AI client doesn't stop after one function call. It decides which tools it needs and in what order—all based on intermediate results.

Retrieving Detailed Wrike Task Information

Need more than just a list of tasks? Use the `get_task_details` tool to pull everything about a single task, like due dates and assigned owners. You can combine this with a broader search using `list_wrike_tasks`, giving you both the overview and the deep data points. This level of detail means your agent doesn't guess; it gets verified, comprehensive information for every record.

Managing Wrike Resources with MCP Server

The entire `wrike-mcp` server lets your client manage core resources. You can first get an inventory of all available projects using `list_wrike_projects`. Then, you use the resulting project IDs to call `list_wrike_tasks`, filtering the task list down to only relevant items. It’s about building a reliable pipeline where one resource listing guides the next operation.

Setup guide

Set up Wrike MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Wrike tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "wrike-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Wrike transactions"
    })
    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 LangChain

The MCP Server makes every tool call a link in your chain. Your agent uses its reasoning capabilities to determine the optimal sequence of calls—for instance, running `list_wrike_contacts` first, and then passing those names into a subsequent task lookup.

Yes. You simply instruct your agent to call the `list_wrike_projects` tool. The output gives you an immediate list of active projects, which can then be used as context for other actions.

The setup supports stateless operation by default, but you'll use `client.session()` to maintain persistent context throughout a complex workflow or reasoning chain with your AI client.

The server handles tasks, projects, folders, and contacts. You can get comprehensive details on specific tasks via `get_task_details`, or list out groups of resources like all available spaces with `list_wrike_spaces`.

The server touches core organizational data, including task details, project lists, and user contacts. All interactions are managed through the single endpoint token provided by 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