How to Use the Confluence MCP in AutoGen

Q: How do AutoGen agents share access to the Confluence server?

You register the tools with the AutoGen AssistantAgent constructor. This lets all agents in your conversation group call tools like getpage when they need wiki data.

Q: Can one AutoGen agent write to Confluence while another reviews?

Yes. You can assign the createpage tool to a writer agent and the listpagecomments tool to a reviewer agent to build an automated editorial pipeline.

Q: How does AutoGen handle CQL query errors from Confluence?

If searchconfluence returns an error due to invalid CQL, the calling AutoGen agent can analyze the error message, debate the syntax with other agents, and try a corrected query.

Q: How do I configure the transport for this MCP Server in AutoGen?

Use the StreamableHttpServerParams helper from the AutoGen MCP extension. Point it to your Vinkius server URL, and the adapter will automatically handle the tool schema conversion.

Let AutoGen agents debate, edit, and publish Confluence pages through collaborative workflows.

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 AutoGen

Create your Vinkius account to connect Confluence 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 Confluence with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative page creation with AutoGen

`create_page` allows your writing agent to publish draft pages directly to a specific space. Meanwhile, a separate editing agent can review the content and suggest changes before final publication. This MCP Server setup enables a consensus-driven workflow where agents debate the structure of the HTML body. They only commit the page to the root space once they agree on the layout.

Drive discussion threads via agent debate

`add_page_comment` lets a reviewer agent post feedback directly onto a page in HTML storage format. This mimics human collaboration, letting agents resolve conflicts in the comment section. By using `list_page_comments`, a supervisor agent can read existing inline feedback to decide if a page needs revision. This automates the editorial review process without human intervention.

Map out wiki architecture automatically

`list_spaces` gives your discovery agent a starting point by listing all active directories. It then coordinates with other agents to explore specific pages using `list_pages` to map out the wiki structure. When the team needs specific information, `search_confluence` executes CQL queries to find matching blog posts and comments. The agents then debate which source is the most reliable before presenting it.

Setup guide

Set up Confluence 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 Confluence 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="Confluence_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Confluence 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="Confluence_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Confluence 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 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 AutoGen

You register the tools with the AutoGen `AssistantAgent` constructor. This lets all agents in your conversation group call tools like `get_page` when they need wiki data.

Yes. You can assign the `create_page` tool to a writer agent and the `list_page_comments` tool to a reviewer agent to build an automated editorial pipeline.

If `search_confluence` returns an error due to invalid CQL, the calling AutoGen agent can analyze the error message, debate the syntax with other agents, and try a corrected query.

Use the `StreamableHttpServerParams` helper from the AutoGen MCP extension. Point it to your Vinkius server URL, and the adapter will automatically handle the tool schema conversion.

Yes. The Confluence MCP Server on Vinkius runs in an ephemeral environment, meaning your HTML page body content and comments are processed in memory and never stored on our servers.

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