get_pageLABSCO SUMMARY
Confluence stops being a place you go and becomes something you ask.
The win is the round trip: find the page with a CQL search, read it as markdown, and write the edit back with the original markup intact — without opening a browser tab or hand-converting storage format.
What it is
An MCP server for Confluence. It authenticates with a personal API token, fetches pages and spaces through the REST API, and cleans the content on the way out so a model reads prose rather than XHTML.
What you get
- A page fetched by ID, returned as text or as markdown
- The original Confluence Storage Format markup alongside it, so an update can preserve the existing formatting
- Search across pages with CQL, the query language the Confluence UI itself uses
- The spaces your account can reach, listed
- New pages created, and existing pages updated
- Comments read and added
- Attachments listed and uploaded
Requirements
Bun v1.0.0 or higher — the server is built and run with Bun, not Node. Three environment variables: a personal API token, your instance URL ending in /wiki, and the email address that token belongs to. There is no published package to npx: clone the repository and bun run build before pointing a client at dist/index.js.
Setup effort
Build from source — git clone https://github.com/cosmix/confluence-mcp.git
USE CASES
01
Finding the doc nobody can name
Search with CQL across a space and its labels, then open the one that matches and read it as markdown.
02
Editing a page without wrecking its layout
Pull the page with its storage-format markup, change the part you mean, and write it back.
03
Writing up something that happened outside Confluence
Check which spaces you can post to, then create the page in the right one.
04
Catching up on a decision thread
Read the comments on a page and add your reply in place.
05
Attaching the artefact to the write-up
See what is already attached to the page, then upload the file that was missing.
9 tools
Listed in project docs. Your client may show a different list.
search_pagesget_spacescreate_pageupdate_pageget_commentsadd_commentget_attachmentsadd_attachmentBEFORE YOU INSTALL
What to know first
Tools you get
9 tools named in the project's documentation.
Requires
- Bun v1.0.0 or higher
- CONFLUENCE_API_TOKEN in your environment
- CONFLUENCE_BASE_URL in your environment
- CONFLUENCE_USER_EMAIL in your environment
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/cosmix/confluence-mcp.git
cd confluence-mcp
bun install
bun run buildMCP Clients
Claude Desktop, Cline
JSON
{
"mcpServers": {
"confluence": {
"command": "bun",
"args": [
"<YOUR_PATH_TO_CONFLUENCE_MCP>/dist/index.js"
],
"env": {
"CONFLUENCE_API_TOKEN": "<YOUR_CONFLUENCE_API_TOKEN>",
"CONFLUENCE_BASE_URL": "<YOUR_CONFLUENCE_INSTANCE_URL>/wiki",
"CONFLUENCE_USER_EMAIL": "<YOUR_CONFLUENCE_USER_EMAIL>"
}
}
}
}
