docsoauth2

Confluence

Team wiki and documentation.

Verdict

Confluence via MCP is the wiki integration for orgs already in the Atlassian ecosystem. Less polished than Notion's MCP integration, but indispensable when your team's institutional knowledge lives there. What we notice: search across a Confluence space works cleanly — the model can find that runbook, that incident postmortem, that architecture decision record. Reading is fast and reliable. Writing back is more constrained: Confluence's storage format isn't the friendliest target for an LLM, so the model is best at appending plain content rather than authoring rich pages from scratch. Best for: knowledge-base lookups in Atlassian-native orgs ("what's the on-call procedure for X service", "where's the architecture doc for Y"); ADR / postmortem search; summarising old documentation when onboarding new engineers; bridging Confluence content into Linear / Jira tickets or chat conversations. Avoid for: greenfield documentation projects (Notion is friendlier for both humans and AI); workflows that need precise Confluence template handling (the model authors plain HTML-ish content; templates need work); orgs migrating off Confluence where the integration is short-term. Practical frame: free with a Confluence account; OAuth handles auth via the Atlassian connect flow. Per-call token cost depends on document length — large knowledge-base pages cost $0.10-0.30 each on Sonnet.

Common use cases

  • Draft release notes and publish to wiki
  • Tag documentation pages with sprint labels
  • Create private spaces for project kickoffs
  • Turn meeting notes into blog posts
  • Organize knowledge base by product area

Integration

Vendor
Confluence
Category
docs
Auth
OAUTH2
Tools
50
Composio slug
confluence

Tools

  • Add Content Label

    Tool to add labels to a piece of content. use after obtaining the content id to tag pages or blog posts with metadata labels.

  • Create Blogpost

    Tool to create a new confluence blog post. use when you need to publish content in a specific space.

  • Create Blogpost Property

    Tool to create a property on a specified blog post. use when you need to add custom metadata to a blog post.

  • Create Page

    Tool to create a new confluence page in a specified space. use when you need to create new documentation or content.

  • Create Page Property

    Tool to create a property on a confluence page. use when you need to add custom metadata or settings to a page.

  • Create Private Space

    Tool to create a private confluence space. use when you need an isolated workspace viewable only by its creator.

  • Create Space

    Tool to create a new confluence space. use when setting up a new knowledge area for organization.

  • Create Space Property

    Tool to create a new property on a confluence space. use after confirming the space id when adding custom metadata.

  • Create Whiteboard

    Tool to create a new confluence whiteboard. use when you need to start a collaborative whiteboard session.

  • Create Whiteboard Property

    Tool to create a new content property on a whiteboard. use when you need to attach custom metadata to a confluence whiteboard.

  • Delete Blogpost Property
    destructive

    Tool to delete a blog post property. use when you need to remove custom metadata from a specified blog post.

  • Delete Page
    destructive

    Tool to delete a confluence page. use with caution as this will permanently remove the page from the space.

  • Delete Page Content Property
    destructive

    Tool to delete a content property from a page by property id. use when you need to remove custom metadata from a page for cleanup or auditing.

  • Delete Space
    destructive

    Tool to delete a confluence space by its key. use when you need to permanently remove a space.

  • Delete Space Property
    destructive

    Tool to delete a space property. use when you need to remove a property from a confluence space after review.

  • Delete Whiteboard Content Property
    destructive

    Tool to delete a content property from a whiteboard by property id. use when you need to remove custom metadata from a whiteboard.

  • Get Anonymous User

    Tool to retrieve information about the anonymous user. use when you need to obtain guest user details before unauthenticated interactions.

  • Get Attachment Labels

    Tool to list labels on an attachment. use after confirming the attachment id to fetch its labels.

  • Get Attachments

    Tool to retrieve attachments of a confluence page. use after confirming page id to list its attachments (supports pagination).

  • Get Audit Logs

    Tool to retrieve confluence audit records. use when you need to fetch and filter audit logs for compliance or troubleshooting.

  • Get Blogpost by ID

    Tool to retrieve a specific confluence blog post by its id. use when you have a blog post id and need detailed metadata and content.

  • Get Blog Post Content Properties

    Tool to retrieve all content properties on a blog post. use when you need to list metadata properties set on a specific confluence blog post.

  • Get Blogpost Labels

    Tool to retrieve labels of a specific confluence blog post by id. use after obtaining the blog post id to list its labels.

  • Get Blogpost Like Count

    Tool to get like count for a confluence blog post. use after confirming the blog post id to retrieve total likes.

  • Get Blogpost Operations

    Tool to retrieve permitted operations for a confluence blog post. use after confirming the blog post id to see allowed actions.

  • Get Blogposts

    Tool to retrieve a list of blog posts. use when you need blog post ids.

  • Get Blog Posts

    Tool to retrieve a list of blog posts. use when you need a paginated list of confluence blog posts.

  • Get Blog Posts For Label

    Tool to list all blog posts under a specific label. use when you have a label id and need to retrieve associated blog posts.

  • Get Blogpost Version Details

    Tool to retrieve details for a specific version of a blog post. use when you have a blogpostid and versionnumber and need detailed metadata for that version.

  • Get Blogpost Versions

    Tool to retrieve all versions of a specific blog post. use when you have a blogpostid and need to list version numbers.

  • Get Child Pages

    Tool to list all direct child pages of a given confluence page. use when you have a parent page id and need to discover its direct descendants.

  • Get Content Restrictions

    Tool to retrieve restrictions on a confluence content item. use when you need to see who can view or edit a page or blog post.

  • Get Current User

    Tool to get information about the currently authenticated user. use when you need to check user details or permissions.

  • Get Inline Comments for Blog Post

    Tool to retrieve inline comments for a confluence blog post. use when you need inline comment details by blog post id.

  • Get Labels

    Tool to retrieve all labels in a confluence site. use when you need to list or page through labels.

  • Get Labels for Space

    Tool to list labels on a space. use when you need to retrieve labels for a specific space.

  • Get Labels for Space Content

    Tool to list labels on all content in a space. use when you need to retrieve or filter content labels by space, with pagination and optional prefix filtering.

  • Get Page Ancestors

    Tool to retrieve all ancestors for a given confluence page by its id. use when you need the full page hierarchy.

  • Get Page by ID

    Tool to retrieve a confluence page by its id. use when you have a page id and need its detailed metadata and content.

  • Get Page Content Properties

    Tool to retrieve all content properties on a page. use when you need to list metadata properties set on a specific confluence page.

  • Get Page Labels

    Tool to retrieve labels of a specific confluence page by id. use after obtaining the page id to list its labels.

  • Get Page Like Count

    Tool to get like count for a confluence page. use after confirming the page id to retrieve total likes.

  • Get Pages

    Tool to retrieve a list of pages. use when you need a paginated list of confluence pages.

  • Get Page Versions

    Tool to retrieve all versions of a specific confluence page. use after confirming the page id to audit its edit history.

  • Get Space by ID

    Tool to retrieve a confluence space by its id. use when you need detailed metadata of a specific space.

  • Get Space by ID

    Tool to retrieve a confluence space by its id. use when you need detailed metadata of a specific space.

  • Get Space Contents

    Tool to retrieve content in a confluence space. use when you need to list pages, blogposts, or attachments of a specific space key.

  • Get Space Properties

    Tool to get properties of a confluence space. use when you need to retrieve custom metadata or settings stored as space properties.

  • Get Spaces

    Tool to retrieve a list of confluence spaces. use when you need a paginated list of spaces with optional filtering.

  • Search Content

    Searches for content by filtering pages from the confluence v2 api with intelligent ranking. since the native search endpoint is deprecated, this action: 1. fetches pages from the v2 pages endpoint with pagination (up to 300 pages) 2. appli

Setup

Setup guide

  1. 11. In Switchy, open your workspace settings and navigate to the Integrations tab. 2. Find Confluence in the MCP directory and click Connect. 3. You'll be redirected to Atlassian's OAuth consent screen — sign in with an account that has permission to create spaces and pages. 4. Grant the requested scopes: read and write access to Confluence content, spaces, and labels. 5. After authorization, Switchy redirects you back and confirms the connection is live. 6. Open any Space in Switchy and type '@Confluence list spaces' to verify the MCP responds with your Confluence spaces. 7. To create a page, @mention Confluence and specify the space key, page title, and body content in your prompt. 8. Check your Confluence instance to confirm the page appears with the correct metadata and labels.

What teammates see: by default, memories from Confluence are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.

Works well with

Top models

Compatibility data appears once enough Spaces have used this MCP together with a given model.

How Switchy teams use it

Not enough Spaces yet to publish anonymised usage stats (we require ≥ 50 Spaces per week).

Starter prompts

Publish Feature Spec

@Confluence create a page in the PROD space titled 'User Profile Redesign Spec' with sections for background, user stories, technical requirements, and open questions.
Open in a Space →

Tag Sprint Pages

@Confluence add the label 'sprint-24' to the pages titled 'API Rate Limiting' and 'Mobile Onboarding Flow' in the ENG space.
Open in a Space →

Create Team Space

@Confluence create a space with key 'GROWTH' and name 'Growth Team Hub' with description 'Experiments, metrics, and launch plans for growth initiatives.'
Open in a Space →

Post Weekly Update

@Confluence create a blog post in the EXEC space titled 'Week of Jan 20: Shipping Summary' with bullet points on feature launches, bugs fixed, and next week's priorities.
Open in a Space →

Attach Metadata Property

@Confluence create a property on the page 'Security Audit Checklist' with key 'owner' and value 'security-team' so we can filter by responsible group.
Open in a Space →

Example outputs

Illustrative - representative of the model's voice and quality, not literal recordings.

Prompt

@Confluence search for all pages labeled 'product-roadmap' in the Engineering space and list their titles with last-modified dates

Output

Found 7 pages in the Engineering space with the 'product-roadmap' label: 1. Q1 2024 Feature Priorities (last modified: Jan 15, 2024) 2. API v3 Migration Plan (last modified: Jan 12, 2024) 3. Mobile App Roadmap (last modified: Jan 8, 2024) 4. Infrastructure Upgrades (last modified: Dec 20, 2023) 5. Customer Feedback Integration (last modified: Dec 18, 2023) 6. Security Audit Findings (last modified: Dec 10, 2023) 7. Q4 2023 Retrospective (last modified: Dec 5, 2023) This is an illustrative example showing how search results might appear. Actual results depend on your Confluence instance's content and label usage.

Notes

This example demonstrates read-only search and filtering capabilities. Requires OAuth scope to read space content. Label-based searches work best when your team consistently tags documentation — inconsistent labeling will return incomplete results. No side effects; this is a safe exploratory query.

Prompt

@Confluence create a new page in the Product space titled 'Launch Checklist - Mobile v2.0' with sections for QA sign-off, marketing assets, and support documentation

Output

Created page 'Launch Checklist - Mobile v2.0' in the Product space (page ID: 98765432). The page includes three sections: - QA Sign-off: Placeholder for test results and approval - Marketing Assets: Space for campaign materials and messaging - Support Documentation: Area for help articles and FAQs Page URL: https://yourcompany.atlassian.net/wiki/spaces/PRODUCT/pages/98765432 This illustrative example shows the structure created. You can now edit the page directly in Confluence or use additional @Confluence commands to populate sections.

Notes

This example shows content creation with structured sections. Requires OAuth write permissions for the target space. The MCP creates basic page structure — you'll need to add detailed content through follow-up edits or manual work in Confluence. Be aware that creating pages in high-traffic spaces may trigger notifications to watchers.

Prompt

@Confluence pull all pages modified in the last 7 days across our Sales and Marketing spaces, then summarize the main themes and any conflicting information about our Q1 pricing strategy

Output

Retrieved 14 pages modified in the last 7 days. After analysis: **Main themes:** - Q1 pricing adjustments for Enterprise tier (mentioned in 6 pages) - New discount structure for annual contracts (4 pages) - Competitive positioning against Vendor X (3 pages) **Conflicting information identified:** The Sales Playbook (modified Jan 14) lists Enterprise tier at $499/seat, while the Marketing FAQ (modified Jan 16) shows $549/seat. The Pricing Strategy Overview (modified Jan 13) mentions a 15% annual discount, but the Sales Email Templates (modified Jan 15) reference 20%. This illustrative example shows how cross-space synthesis might surface inconsistencies in your documentation.

Notes

This example pairs Confluence's multi-space search with AI reasoning to identify documentation drift. Requires read access to multiple spaces. The synthesis quality depends on how clearly your team writes — vague or outdated pages will produce less reliable conflict detection. Use this to audit cross-functional alignment, not as a source of truth for customer-facing numbers.

Use-case deep-dives

Onboarding doc generation from support tickets

When Confluence MCP turns Slack threads into runbooks

A 6-person support team fields the same setup questions weekly. They want an AI to draft Confluence pages from resolved Slack threads so new hires stop asking veterans. This MCP is the right call if your team already lives in Confluence and OAuth2 setup isn't a blocker. The Create Page tool handles the write, Add Content Label tags it for search, and the 50-tool scope means you can also query existing pages to avoid duplicates. The trade-off: if your docs live in Notion or GitHub wikis instead, you're adding auth overhead for a tool your team doesn't use. Buy this when Confluence is already your single source of truth and you need AI to keep it current without manual copy-paste.

Sprint retro publishing at 15-person scale

Confluence MCP for recurring team ritual documentation

A product team runs biweekly retros in Miro, then someone manually transcribes action items into Confluence. They want the AI to auto-publish a formatted blogpost after each session. This MCP works if you're comfortable with OAuth2 and your Confluence instance isn't locked down by IT. Create Blogpost handles the write, Create Space Property can tag the retro series for rollup views, and the 50-tool count suggests you can also read prior retros to spot patterns. The boundary: if your retros are under 10 people and informal, a shared Google Doc is faster than Confluence's permission model. Use this when your team is big enough that discoverability and structure matter more than speed.

Customer success case study drafting

When Confluence MCP bridges CRM data and public content

A 4-person customer success team wants to draft case studies by pulling win data from Salesforce and publishing polished pages in a public Confluence space. This MCP is borderline. Create Page and Create Space let you structure the output, but the 50 tools are overkill if you're only writing, not reading or searching. The real win is pairing this with a CRM MCP so the AI can draft from live deal notes, then publish without a human shuttling data between tools. The threshold: if your case studies need legal review before publish, Confluence's draft workflow is clunky compared to a Google Doc approval chain. Buy this when your go-to-market team already uses Confluence for collateral and you want one AI workspace to span systems.

Frequently asked

What does the Confluence MCP let Switchy do?

It lets AI agents read, create, and update Confluence pages and blog posts directly from Switchy. Agents can create new spaces, add labels for organization, and attach custom properties to pages or posts. You connect once via OAuth, then any team member can ask an agent to draft a runbook, pull specs from a page, or publish meeting notes to a specific space without leaving the conversation.

Do I need Confluence admin rights to connect this MCP?

No. Standard OAuth permissions are enough—Switchy requests scopes to read content, write pages, and manage spaces you already have access to. If your Confluence admin has locked down space creation or certain labels, those restrictions carry over. The MCP won't bypass your org's existing permissions; it just acts on your behalf within whatever access you already have.

Can the Confluence MCP search across all my spaces at once?

Yes, but only spaces you have read access to. The MCP includes tools to query content by title, label, or space key, so an agent can pull information from multiple spaces in one go. It won't surface pages from private spaces you're not a member of, and search results respect your Confluence permissions exactly as they appear in the web UI.

Why use this instead of just opening Confluence in a browser?

Speed and context. An agent can draft a page using data from three other tools—Slack threads, GitHub issues, your CRM—then publish it to Confluence without you copy-pasting between tabs. You also skip the Confluence editor's learning curve for teammates who just want to get words into a space. For reading, agents retrieve only the paragraphs you need instead of scrolling through long pages.

Who on the team should connect the Confluence MCP?

Whoever owns documentation or needs to automate page creation. If one person manages your team wiki, connect their Confluence account so agents inherit the right space permissions. Multiple people can connect separate Confluence accounts to the same Switchy workspace, but each connection only sees the spaces that account can access. Plan your setup around who actually writes and organizes your Confluence content.

Compare with

Compare with anything else →
Data last verified 7 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.