How to Use the Confluence MCP in LlamaIndex

Q: Does LlamaIndex support CQL searching on Confluence?

Yes, through the searchconfluence tool. Your LlamaIndex agent can generate CQL queries dynamically to find specific pages before indexing them.

Q: Can I filter which Confluence spaces LlamaIndex can access?

Absolutely. You can restrict the agent's scope by using listpages with a specific space key, or let it query listspaces to discover accessible areas.

Feed Confluence wiki data directly into your LlamaIndex vector stores for accurate RAG.

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 LlamaIndex

Create your Vinkius account to connect Confluence to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index live Confluence data into LlamaIndex

`get_page` pulls raw HTML content and version history directly into your LlamaIndex indexing pipeline. By bypassing manual exports, your RAG applications stay synchronized with the latest wiki edits. The framework takes the output of this MCP Server tool and turns it into searchable document nodes. This ensures your agent answers questions using verified, current corporate documentation.

Discover and index entire spaces

`list_spaces` identifies all available wiki directories so your agent can choose which areas to index. It then uses `get_space_details` to read descriptions and permissions, filtering out restricted content. If you need granular control, `list_pages` retrieves specific page trees with built-in pagination. This keeps your vector database clean and prevents token overflow during large ingestions.

Pull discussion threads into vector stores

`search_confluence` runs structured CQL queries to find relevant pages, blog posts, and comments in one go. This lets your LlamaIndex agent locate hidden context that standard keyword searches miss. To capture team decisions, `list_page_comments` fetches inline discussions and author details. Your RAG pipeline can index these comments to understand the context behind a wiki page update.

Setup guide

Set up Confluence MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Confluence MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Confluence tools.",
)
response = await agent.run("List recent Confluence data")

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 LlamaIndex

Use the MCP tool spec to convert the server tools into LlamaIndex tools. The agent runs `get_page` to fetch the HTML content, which you can then parse and insert into your vector index.

Yes, through the `search_confluence` tool. Your LlamaIndex agent can generate CQL queries dynamically to find specific pages before indexing them.

Absolutely. You can restrict the agent's scope by using `list_pages` with a specific space key, or let it query `list_spaces` to discover accessible areas.

The server handles the connection to Atlassian. However, when building large LlamaIndex ingest pipelines, you should implement rate-limiting in your ingestion loop to avoid hitting Confluence API thresholds.

No. All requests to read space metadata or page content pass through ephemeral, zero-trust V8 isolates. Your Confluence data is discarded immediately after the tool execution finishes.

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