How to Use the Confluence MCP in LangChain

Q: Can a LangChain agent search Confluence across multiple spaces?

Yes. The searchconfluence tool uses standard CQL, allowing your LangChain agent to run broad queries across your entire instance. You can also target specific areas by passing a space key to listpages.

Q: How does LangChain handle the HTML output from Confluence pages?

The getpage tool returns the body in Confluence storage format, which is standard HTML. Your LangChain prompt templates should instruct the LLM to parse this HTML or extract the plain text it needs.

Q: How do I set up the connection using the Vinkius MCP Server?

Install the adapter package first. Then configure the MultiServerMCPClient with the HTTP transport URL provided by Vinkius and pass the tools directly to your agent.

Connect LangChain agents directly to your wiki to read, edit, and build pages without leaving your Python pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Confluence MCP to LangChain

Create your Vinkius account to connect Confluence 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 Confluence with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run deep CQL queries inside LangChain loops

`search_confluence` lets your LangChain agent run complex Confluence Query Language queries to locate specific documentation. The agent feeds these search results directly into the next chain step, pulling full page details with `get_page` to extract context. LangSmith traces every single call, showing you the exact raw HTML and metadata your chain receives. This observability lets you debug why an agent picked a specific page version or space.

Generate Confluence pages from LangChain chains

`create_page` builds new pages at the root of a space using HTML storage format. Your chain can take raw data from another tool, format it, and publish it instantly. If a page needs feedback, the agent uses `add_page_comment` to add HTML-formatted notes. This MCP Server tool turns your autonomous chain into an active collaborator.

Map out corporate knowledge structure

`list_spaces` gives your chain a complete directory of available spaces before it starts querying. From there, `list_page_comments` fetches inline and footer discussions to capture human feedback. Using these tools in a multi-step loop lets the agent build a map of team permissions via `get_space_details`. You get a clear picture of who wrote what without manual exports.

Setup guide

Set up Confluence 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 Confluence 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({
    "confluence-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 Confluence 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 Confluence. 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 Confluence 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 Confluence MCP in LangChain

Vinkius handles the credentials for you. Your LangChain code only needs a single endpoint token to connect, meaning you don't store Atlassian API keys in your environment variables.

Yes. The `search_confluence` tool uses standard CQL, allowing your LangChain agent to run broad queries across your entire instance. You can also target specific areas by passing a space key to `list_pages`.

The `get_page` tool returns the body in Confluence storage format, which is standard HTML. Your LangChain prompt templates should instruct the LLM to parse this HTML or extract the plain text it needs.

Install the adapter package first. Then configure the `MultiServerMCPClient` with the HTTP transport URL provided by Vinkius and pass the tools directly to your agent.

Your data is safe. Vinkius runs the Confluence MCP Server in an isolated V8 sandbox, meaning your page content and comments are never stored or used for training.

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