How to Use the Confluence MCP in Mastra AI

Q: How do I register the Confluence tools using the Mastra AI MCP client?

Instantiate the MCPClient with the Vinkius SSE endpoint URL, then call listTools on the client. Spread those returned tools directly into your agent's tool configuration array during initialization.

Q: How do I require human approval before Mastra AI edits Confluence?

Set the requireToolApproval flag on your Mastra agent configuration for the createpage and addpagecomment tools. This pauses the workflow and waits for manual confirmation before making any changes.

Build self-healing Confluence workflows in TypeScript using Mastra AI 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 Mastra AI

Create your Vinkius account to connect Confluence to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated Space Auditing and Setup

The `get_space_details` tool reads metadata, homepages, and permission structures for any Confluence space inside your Mastra AI agent workflow. Mastra AI agents use this tool to map out existing documentation before running multi-step document generation tasks. If a Confluence space is missing or misconfigured, this MCP setup lets you write logic to trigger conditional Mastra AI branches to correct the setup. You can verify Confluence permissions and automatically log the outcome inside your Mastra AI workflow.

Mastra AI Driven Multi-Page Syncing

The `list_pages` tool retrieves lists of pages from Confluence with pagination support via start offset and limit parameters inside your Mastra AI runtime. This lets your Mastra AI agent crawl entire Confluence spaces systematically to find outdated documentation or broken links. When the Mastra AI agent finds a Confluence page that needs an update, it triggers a workflow step that uses `create_page` to post the revised content. If the Confluence API rate limits your request, Mastra's automatic exponential backoff retries the call until it succeeds.

Moderated Feedback Loops on Wiki Pages

The `list_page_comments` tool extracts inline and footer comments along with author details from any specific Confluence page using the MCP toolset to pull data into your Mastra AI agent. It gives your Mastra agent the exact context needed to draft replies or escalate issues. You can enforce a human-in-the-loop step by setting `requireToolApproval` on the Mastra AI agent before it calls `add_page_comment` on Confluence. This ensures no automated replies hit your production Confluence wiki without a quick manual check from your team.

Setup guide

Set up Confluence MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Confluence tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "confluence-mcp-client",
  servers: {
    "confluence-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Confluence Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Confluence tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Confluence transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the `MCPClient` with the Vinkius SSE endpoint URL, then call `listTools` on the client. Spread those returned tools directly into your agent's tool configuration array during initialization.

Yes, Mastra's workflow engine has built-in automatic retries with exponential backoff. If `create_page` or `add_page_comment` hits a rate limit, the workflow pauses and retries the operation automatically.

Set the `requireToolApproval` flag on your Mastra agent configuration for the `create_page` and `add_page_comment` tools. This pauses the workflow and waits for manual confirmation before making any changes.

It uses Confluence Query Language (CQL). You pass standard CQL strings to the `search_confluence` tool to target specific page types, spaces, or text matches.

Your raw HTML page bodies, comments, and space configurations flow directly through an ephemeral, zero-trust V8 sandbox. Vinkius does not store any of this Confluence data, and the transport layer uses encrypted SSE connections that terminate immediately after your workflow step completes.

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