How to Use the Confluence MCP in CrewAI

Q: How do I assign Confluence tools to a specific agent in CrewAI?

Pass the Vinkius HTTP endpoint URL directly into the mcps list when defining your agent. This automatically exposes tools like getpage and createpage to that specific agent's toolkit.

Q: Can I limit which Confluence tools a CrewAI MCP agent can access?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter to expose only specific tools, such as searchconfluence, while keeping write tools restricted.

Deploy specialized agent teams to search, read, and update Confluence using CrewAI and this managed 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 Confluence MCP to CrewAI

Create your Vinkius account to connect Confluence to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Knowledge Base Search

The `search_confluence` tool executes complex Confluence Query Language (CQL) queries to find relevant pages, blog posts, and comments across your entire instance using CrewAI agent teams. A specialized researcher agent in your CrewAI crew can run this tool to gather facts before passing them to an editor agent. Because CrewAI supports shared memory, the Confluence search results found by one agent are instantly accessible to the rest of the crew. This prevents redundant Confluence API calls and keeps the entire CrewAI team aligned on the same wiki data.

CrewAI Automated Documentation Pipelines

The `create_page` tool writes new pages directly to a specified Confluence space using HTML storage format inside your CrewAI pipeline. This MCP Server tool writes new pages directly to a specified Confluence space as your CrewAI crew executes its tasks. You can configure this CrewAI pipeline to run autonomously in response to CI/CD events to publish Confluence docs. A CrewAI crew handles the entire lifecycle, from checking Confluence space details with `get_space_details` to publishing the final document.

Multi-Agent Comment Moderation

The `list_page_comments` tool pulls inline and footer comments from any Confluence page to monitor user feedback inside your CrewAI framework. Your moderator agent can scan these Confluence comments, categorize the feedback, and decide if a task needs escalation. If action is required, another CrewAI agent uses `add_page_comment` to post a structured response directly to Confluence. This MCP loop creates a fully autonomous loop that keeps your Confluence wiki documentation actively maintained by your CrewAI team.

Setup guide

Set up Confluence MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Confluence tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Confluence Analyst",
    goal="Access and analyze Confluence data via MCP.",
    backstory="Expert analyst with direct Confluence access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Confluence transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Confluence Analyst",
        goal="Access and analyze Confluence data via MCP.",
        backstory="Expert analyst with direct Confluence access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Confluence transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius HTTP endpoint URL directly into the `mcps` list when defining your agent. This automatically exposes tools like `get_page` and `create_page` to that specific agent's toolkit.

Yes. Use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter` to expose only specific tools, such as `search_confluence`, while keeping write tools restricted.

CrewAI agents use shared memory to pass context. Once one agent retrieves a page using `get_page`, the contents are stored in the crew's short-term memory, allowing subsequent agents to analyze or edit that content.

It must be in Confluence storage format, which is standard HTML. Your writing agent needs to format its output as HTML before passing it to the `create_page` tool.

Yes, Vinkius handles all authentication securely at the gateway level, so your CrewAI scripts never touch raw API tokens or passwords. All page content, comments, and space metadata are processed in transient V8 isolates that dissolve the second the agent execution ends.

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