Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/MahithChigurupati/Confluence-MCP-Server.git
cd Confluence-MCP-Server
pip install -r requirements.txtRegister it in Claude Code
claude mcp add -e "CONFLUENCE_BASE_URL=${CONFLUENCE_BASE_URL}" -e "USERNAME=${USERNAME}" -e "API_TOKEN=${API_TOKEN}" confluence-mcp -- python /path/to/Confluence-MCP-Server/confluence.pyReplace any placeholder paths in the command with the real path on your machine.
CONFLUENCE_BASE_URLUSERNAMEAPI_TOKENMake your agent remember this setup
confluence-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- List and filter Confluence spaces
- Retrieve and manage page content
- Execute CQL (Confluence Query Language) searches
- List all pages within specific spaces
- Secure API token-based authentication
Tools 4
list_spacesList and filter Confluence spacesget_page_contentRetrieve and manage page contentsearch_contentExecute CQL (Confluence Query Language) searcheslist_pages_in_spaceList all pages within specific spacesEnvironment Variables
CONFLUENCE_BASE_URLrequiredThe base URL for your Confluence instance REST APIUSERNAMErequiredYour Atlassian account email addressAPI_TOKENrequiredYour Atlassian API tokenTry it
Original README from MahithChigurupati/Confluence-MCP-Server
Confluence MCP Server
A FastMCP-based server that provides seamless integration with Confluence's REST API, enabling programmatic access to Confluence spaces, pages, and content search functionality.
Key Features
- Space Management: List and filter Confluence spaces
- Page Operations: Retrieve and manage page content
- Search Functionality: Execute CQL (Confluence Query Language) searches
- Space Navigation: List all pages within specific spaces
- Authentication: Secure API token-based access
System Requirements
- Python 3.8+
- pip (Python package manager)
- Active Confluence instance with API access
- Valid Confluence API token
Installation
Installing via Smithery
To install confluence-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @MahithChigurupati/confluence-mcp-server --client claude
Manual Installation
Clone the Repository
git clone https://github.com/MahithChigurupati/Confluence-MCP-Server.git cd Confluence-MCP-ServerSet Up Virtual Environment (Recommended)
python -m venv venv source venv/bin/activate # On macOS/Linux # or .\venv\Scripts\activate # On WindowsInstall Dependencies
pip install -r requirements.txt
Configuration
Create Environment File
cp .env.example .envConfigure Environment Variables
CONFLUENCE_BASE_URL=https://your-instance.atlassian.net/wiki/rest/api [email protected] API_TOKEN=your-api-token-hereObtain Confluence API Token
- Visit Atlassian API Tokens
- Click "Create API Token"
- Enter a meaningful label (e.g., "MCP Server Access")
- Copy the generated token immediately (it won't be shown again)
Usage Guide
Starting the Server
python confluence.py
Available API Methods
1. List Spaces
response = await list_spaces(
query="engineering", # Optional: Filter spaces by name
limit=25, # Optional: Maximum number of spaces to return
start=0 # Optional: Starting index for pagination
)
2. Get Page Content
response = await get_page_content(
page_id="123456", # Required: Confluence page ID
version=2 # Optional: Specific version number
)
3. Search Content
response = await search_content(
query="project plan", # Required: Search query
space_key="TEAM", # Optional: Limit search to specific space
limit=50, # Optional: Maximum results
start=0 # Optional: Starting index
)
4. List Pages in Space
response = await list_pages_in_space(
space_key="TEAM", # Required: Space key
limit=100, # Optional: Maximum pages to return
start=0 # Optional: Starting index
)
Integration with MCP Clients
Claude Desktop Configuration
{
"mcpServers": {
"confluence": {
"command": "python path",
"args": ["/path/to/Confluence-MCP-Server/confluence.py"]
}
}
}
Location: ~/.claude/claude_desktop_config.json (macOS/Linux) or %USERPROFILE%\.claude\config.json (Windows)
Cursor Configuration
{
"mcpServers": {
"confluence": {
"command": "python path",
"args": ["/path/to/Confluence-MCP-Server/confluence.py"]
}
}
}
use which python to find python path
use pwd inside cloned repository to get the path. Don't forget to add confluence.py in the end.
Location: ~/.cursor/mcp.json (macOS/Linux) or %USERPROFILE%\.cursor\config.json (Windows)
Error Handling
Common error codes and their meanings:
401: Invalid API token or credentials403: Insufficient permissions404: Resource not found429: Rate limit exceeded
Troubleshooting
Connection Issues
- Verify CONFLUENCE_BASE_URL format
- Check network connectivity
- Confirm API token validity
Authentication Errors
- Ensure USERNAME matches Atlassian account email
- Verify API_TOKEN is correctly copied
- Check for special characters in .env file
Permission Errors
- Confirm user has required Confluence permissions
- Verify space and page access rights
Support
For issues and feature requests, please create an issue in the repository's issue tracker.
License
MIT License. See LICENSE file for full terms.