Skip to main content

MCP server providing Confluence Server/Data Center integration: page management, search, spaces, and more.

Project description

www-confluence-mcp

MCP (Model Context Protocol) server providing Confluence Server/Data Center integration — page management, search, spaces, comments, labels, attachments, and more.

Gives AI assistants (Qoder, Claude Desktop, Cursor, etc.) the ability to read and write Confluence content through a single MCP server with 24 tools.

Note: This server targets Confluence Server/Data Center only (v1 REST API). Confluence Cloud is not supported.

System Requirements

Requirement Version
uv Install guide
Python 3.10+ (managed automatically by uv)
Confluence Server 5.6+ / Data Center 6.0+

Install uv

macOS / Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows (PowerShell):

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

macOS (Homebrew):

brew install uv

Installation

Option 1: Run directly with uvx (recommended)

No clone needed. Runs from PyPI. Updates automatically on each run:

uvx www-confluence-mcp

MCP client config:

{
  "mcpServers": {
    "www-confluence-mcp": {
      "command": "uvx",
      "args": ["www-confluence-mcp"],
      "env": {
        "CONFLUENCE_URL": "https://confluence.example.com",
        "CONFLUENCE_PERSONAL_TOKEN": "your-pat-here"
      }
    }
  }
}

Option 2: Install as a uv tool

# From PyPI
uv tool install www-confluence-mcp

# After installation, the command is available globally:
www-confluence-mcp

To update or reinstall:

uv tool upgrade www-confluence-mcp
# or force reinstall latest:
uv tool install --force www-confluence-mcp@latest

Option 3: Run from local source (for development)

git clone https://github.com/naifs/www-confluence-mcp.git
cd www-confluence-mcp
uv sync
uv run www-confluence-mcp

To update:

git pull && uv sync

MCP client config (local source):

{
  "mcpServers": {
    "www-confluence-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "/absolute/path/to/www-confluence-mcp",
        "www-confluence-mcp"
      ],
      "env": {
        "CONFLUENCE_URL": "https://confluence.example.com",
        "CONFLUENCE_PERSONAL_TOKEN": "your-pat-here"
      }
    }
  }
}

Option 4: Install from built wheel

cd /path/to/www-confluence-mcp
uv build
uv tool install dist/*.whl

Authentication

The server supports two authentication methods for Confluence Server/Data Center:

Method Environment Variables
Personal Access Token (PAT) (recommended) CONFLUENCE_PERSONAL_TOKEN
Basic Auth (username + password) CONFLUENCE_USERNAME + CONFLUENCE_PASSWORD

PAT takes priority if both are configured. CONFLUENCE_API_TOKEN is accepted as a legacy fallback for CONFLUENCE_PASSWORD.

Environment Variables

Variable Description Default
CONFLUENCE_URL Confluence Server/DC base URL (required)
CONFLUENCE_PERSONAL_TOKEN Personal Access Token for PAT auth
CONFLUENCE_USERNAME Username for Basic auth
CONFLUENCE_PASSWORD Password for Basic auth
CONFLUENCE_SSL_VERIFY Verify TLS certificates (system trust store via truststore) true
CONFLUENCE_SSL_PATH Optional path to extra CA certs (PEM file or OpenSSL-hashed dir), loaded in addition to the system trust store
CONFLUENCE_TIMEOUT HTTP request timeout in seconds 30
CONFLUENCE_MAX_RESULTS Default max results per query (1..100) 25
CONFLUENCE_READ_ONLY Disable write tools (true/false) true
CONFLUENCE_SPACES_FILTER Comma-separated space keys to filter searches
CONFLUENCE_HTTP_PROXY HTTP proxy URL
CONFLUENCE_HTTPS_PROXY HTTPS proxy URL
CONFLUENCE_DEBUG Enable debug logging (1/true/yes/on) false

Provided Tools

Read Tools (12)

  • confluence_search — Search content by text or CQL query
  • confluence_get_page — Get page by ID, title+space_key, or URL
  • confluence_get_page_ancestors — Get ancestor pages (breadcrumb)
  • confluence_get_spaces — List all spaces or get one by key
  • confluence_get_pages — Get pages from a space (tree) or children of a page
  • confluence_get_comments — Get page comments
  • confluence_get_labels — Get page labels
  • confluence_get_attachments — List page attachments
  • confluence_download_attachments — Download attachments to disk (all or by IDs)
  • confluence_get_page_history — Get page version history
  • confluence_get_page_images — Get page images as base64
  • confluence_search_user — Search for users

Write Tools (10) — only when CONFLUENCE_READ_ONLY=false

  • confluence_create_page — Create a new page
  • confluence_update_page — Update an existing page
  • confluence_delete_page — Delete a page
  • confluence_move_page — Move page to another space/parent
  • confluence_add_comment — Add a comment (or reply via parent_id)
  • confluence_add_labels — Add labels to a page
  • confluence_delete_label — Remove a label
  • confluence_upload_attachments — Upload one or more files
  • confluence_delete_attachment — Delete an attachment
  • confluence_apply_template — Apply template body to multiple pages

Quick Verification

# Search Confluence
CONFLUENCE_URL=https://confluence.example.com CONFLUENCE_PERSONAL_TOKEN=your-token \
uv run python -c "
import asyncio
from www_confluence_mcp.server import mcp
asyncio.run(mcp.run(transport='stdio'))
"

# Or just run the server
CONFLUENCE_URL=https://confluence.example.com CONFLUENCE_PERSONAL_TOKEN=your-token \
uv run www-confluence-mcp

Troubleshooting

uv not found

Install uv and reopen your terminal. See System Requirements.

Dependencies missing

uv sync

MCP tools not appearing in client

  1. Check that the MCP client config JSON is valid.
  2. Ensure the --project path is absolute and correct.
  3. Reload the MCP client after config changes.
  4. Check CONFLUENCE_DEBUG=true for detailed logs.

Authentication error

  • Verify CONFLUENCE_URL points to your Server/DC instance (not *.atlassian.net).
  • For PAT: ensure the token is valid and not expired.
  • For Basic auth: ensure both CONFLUENCE_USERNAME and CONFLUENCE_API_TOKEN are set.

Wrong project path in config

The --project argument must point to the root directory of www-confluence-mcp (where pyproject.toml is located), not to the src/ subdirectory.

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

www_confluence_mcp-1.0.3.tar.gz (112.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

www_confluence_mcp-1.0.3-py3-none-any.whl (32.4 kB view details)

Uploaded Python 3

File details

Details for the file www_confluence_mcp-1.0.3.tar.gz.

File metadata

  • Download URL: www_confluence_mcp-1.0.3.tar.gz
  • Upload date:
  • Size: 112.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for www_confluence_mcp-1.0.3.tar.gz
Algorithm Hash digest
SHA256 4533003f92185a37a9ae0d59590ab1924be401f56304d8a0f187585df3ebba0a
MD5 cd102044f83cf8f15aa658937434e1a7
BLAKE2b-256 ee4b0cba37a10fe2acd88409fa66bde957ffd48e0e2c11f35d5cd92ff6defb9b

See more details on using hashes here.

Provenance

The following attestation bundles were made for www_confluence_mcp-1.0.3.tar.gz:

Publisher: ci-cd.yml on Naifs/www-confluence-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file www_confluence_mcp-1.0.3-py3-none-any.whl.

File metadata

File hashes

Hashes for www_confluence_mcp-1.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 303367d6eb7327d9e94b525a6dc3ba8024b176264197ce112b00eb67fefa0501
MD5 af570f402cde720f991925ff4c84cc5f
BLAKE2b-256 4c6931a9e17111e20d885065c2161e9ec41176beb9901da8b76c3e63351ffe1e

See more details on using hashes here.

Provenance

The following attestation bundles were made for www_confluence_mcp-1.0.3-py3-none-any.whl:

Publisher: ci-cd.yml on Naifs/www-confluence-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page