confluence-mcp
Provides read access to Confluence pages, sections, tables, and search capabilities via the Confluence REST API v1.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@confluence-mcpGet the 'Project Overview' page from the Engineering space."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
confluence-mcp
MCP server for Confluence (Server / Data Center). Provides read access to pages, sections, tables, and search via the Confluence REST API v1.
Confluence Server / Data Center only. Uses Personal Access Token (PAT) for authentication.
Tools
Tool | Description |
| Get page content as Markdown with |
| Fetch a single heading section by title (case-insensitive), e.g. get 10 lines instead of 200K |
| Extract only tables as structured JSON — skip irrelevant wide tables eating >30% tokens |
| Search by CQL (Confluence Query Language) |
| Lightweight: title, version, author, dates, labels — no content, always fast |
| Direct child pages of a page |
| Explicit attachment list (opt-in — |
Key features
No silent truncation —
truncated: true/false+available_headingslist so the agent can suggestget_page_section()as a follow-upinclude_tables: false— hides wide tables from Markdown (they remain intablesJSON field)include_attachments: false— skips the attachment list entirely, saving 5-10K tokensSection extraction stops at the next heading of same or higher level
Related MCP server: Atlassian MCP Server
Setup
1. Install dependencies
Requires Python 3.11+.
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt2. Generate a Personal Access Token (PAT)
In Confluence: your avatar → Settings → Personal Access Tokens → Create token.
Copy the token — it's shown only once.
3. Configure environment variables
Variable | Required | Default | Description |
| ✅ | — | Your Confluence instance URL, e.g. |
| — | — | Personal Access Token (PAT). On macOS can use Keychain instead (see below) |
| — |
| macOS Keychain service name (alternative to |
| — |
| Max characters before truncation kicks in |
macOS Keychain alternative — store the token once, no env var needed:
security add-generic-password -a $USER -s confluence_pat -w <your_token>4. Add to MCP client config
With Keychain (recommended on macOS):
{
"mcpServers": {
"confluence": {
"command": "/path/to/confluence-mcp/venv/bin/python",
"args": ["/path/to/confluence-mcp/server.py"],
"env": {
"CONFLUENCE_BASE_URL": "https://confluence.example.com"
}
}
}
}Or with env var token:
{
"mcpServers": {
"confluence": {
"command": "/path/to/confluence-mcp/venv/bin/python",
"args": ["/path/to/confluence-mcp/server.py"],
"env": {
"CONFLUENCE_BASE_URL": "https://confluence.example.com",
"CONFLUENCE_TOKEN": "your_token_here"
}
}
}
}Notes
Works with Confluence Server / Data Center (REST API v1). Not tested with Confluence Cloud.
Content is converted from Confluence Storage Format (XML) to Markdown. Supports code blocks, info panels, expand macros, tables, and lists.
Token is never logged or written to disk — retrieved from macOS Keychain at runtime via
security find-generic-password.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DmitryKhali/confluence-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server