How to Use the Webiny CMS MCP in LangChain

Q: How do I use Webiny CMS and LangChain together?

You chain the tools. Your agent first calls listmodelentries to check existing records, then it might call createcmsentry if a new draft is needed. The output of the list becomes the context for the creation step.

Q: Can I read live content with Webiny CMS and LangChain?

Yep. Use executegraphqlquery and set the apitype to 'read.' This gives you access to published data, keeping your agent's reasoning focused only on what users actually see.

Q: How does Webiny CMS interact with LangChain for updates?

You use updatecmsentry by providing the specific entry ID and a JSON object detailing the field changes. The agent decides this update is necessary after gathering data from other sources.

Q: What happens if I delete an entry using Webiny CMS and LangChain?

The deletecmsentry action permanently removes content revisions. Since the tool description warns that this action is irreversible, your agent needs explicit confirmation before running it.

Q: Does Webiny CMS support different locales when using LangChain?

Yes. When executing a GraphQL query via executegraphqlquery, you must specify the locale parameter. This ensures your multi-step chain handles localized content correctly.

Build multi-step workflows with Webiny CMS and LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Webiny CMS MCP to LangChain

Create your Vinkius account to connect Webiny CMS 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 Webiny CMS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Content Drafts

The `create_cms_entry` tool lets your agent draft new content by providing a JSON object. It's ideal for starting complex writing tasks where the first step is generating metadata or structure. You can then use this initial entry as context for subsequent steps, letting the ReAct agent decide if it needs to run `update_cms_entry` later on.

Run Complex GraphQL Queries

Need raw data? Use `execute_graphql_query` to hit the Webiny CMS API directly. You specify an `api_type` (manage, read, or preview) and a locale for maximum control. This query output can then become the input for another tool call—maybe retrieving model details using `get_model_entry_details`. It keeps your entire reasoning chain grounded in live data.

List All CMS Entries

The `list_model_entries` function lets you pull a list of all records for any content model, like 'Articles.' You must specify if you need drafts (`manage`) or live content (`read`). This output is crucial for an agent that needs to know what exists before it can decide whether to publish something via `publish_cms_entry`.

Setup guide

Set up Webiny CMS 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 Webiny CMS 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({
    "webiny-cms-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 Webiny CMS 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 Webiny. 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 Webiny CMS 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 Webiny CMS MCP in LangChain

You chain the tools. Your agent first calls `list_model_entries` to check existing records, then it might call `create_cms_entry` if a new draft is needed. The output of the list becomes the context for the creation step.

Yep. Use `execute_graphql_query` and set the `api_type` to 'read.' This gives you access to published data, keeping your agent's reasoning focused only on what users actually see.

You use `update_cms_entry` by providing the specific entry ID and a JSON object detailing the field changes. The agent decides this update is necessary after gathering data from other sources.

The `delete_cms_entry` action permanently removes content revisions. Since the tool description warns that this action is irreversible, your agent needs explicit confirmation before running it.

Yes. When executing a GraphQL query via `execute_graphql_query`, you must specify the locale parameter. This ensures your multi-step chain handles localized content correctly.

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