confluence-mcp
Enables reading, writing, searching, and managing attachments on Confluence pages via the Confluence REST API.
README
Confluence MCP Server
MCP server for Confluence integration — read, write, search, and manage attachments via the Confluence REST API.
Installation
npm install -g @mcd/confluence-mcp-server
Or use with npx:
npx @mcd/confluence-mcp-server
Configuration
Add to your MCP settings (e.g. ~/.kiro/settings/mcp.json):
{
"mcpServers": {
"confluence-mcp": {
"command": "npx",
"args": ["@mcd/confluence-mcp-server@latest"],
"env": {
"CONFLUENCE_URL": "https://your-confluence.atlassian.net",
"CONFLUENCE_USERNAME": "your-email@example.com",
"CONFLUENCE_TOKEN": "your-api-token",
"CONFLUENCE_CLOUD": "true"
}
}
}
}
For local development, point directly to the compiled output:
{
"mcpServers": {
"confluence-mcp": {
"command": "node",
"args": ["/absolute/path/to/dist/index.js"],
"env": {
"CONFLUENCE_URL": "...",
"CONFLUENCE_USERNAME": "...",
"CONFLUENCE_TOKEN": "...",
"CONFLUENCE_CLOUD": "false"
}
}
}
}
Environment Variables
| Variable | Description |
|---|---|
CONFLUENCE_URL |
Your Confluence instance URL |
CONFLUENCE_USERNAME |
Your username or email |
CONFLUENCE_TOKEN |
Your API token or password |
CONFLUENCE_CLOUD |
"true" for Cloud, "false" for Server |
Available Tools
Pages
search— Search Confluence content (CQL)get_page— Get page content by IDget_page_children— Get child pages of a parent pagecreate_page— Create a new pageupdate_page— Update page content (inline HTML or file path)
Attachments
get_attachments— List attachments on a pagedownload_attachment— Download an attachment to local diskupload_attachment— Upload a local file as a page attachment, with optional embedding in page body
Comments
get_comments— Get page commentsadd_comment— Add a comment to a page
Tool Examples
Search:
{ "query": "space = DEV AND title ~ \"API\"", "limit": 10 }
Update page with inline content:
{ "page_id": "123456", "content": "<h1>Title</h1><p>Updated content</p>" }
Update page from file (recommended for large content):
{ "page_id": "123456", "content_file": "/absolute/path/to/content.html" }
Upload attachment:
{ "page_id": "123456", "file_path": "/absolute/path/to/file.png" }
Upload and embed in page body:
{
"page_id": "123456",
"file_path": "/absolute/path/to/image.png",
"embed_in_body": true,
"comment": "Optional comment"
}
Images are embedded as <ac:image>, other files as a view-file macro link.
Development
npm install
npm run build
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.