confluence-mcp

confluence-mcp

Provides read access to Confluence Server/Data Center pages, sections, tables, and search via the Confluence REST API v1.

Category
Visit Server

README

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 Get page content as Markdown with truncated flag — agent always knows if the page was cut
get_page_section Fetch a single heading section by title (case-insensitive), e.g. get 10 lines instead of 200K
get_page_tables Extract only tables as structured JSON — skip irrelevant wide tables eating >30% tokens
search_pages Search by CQL (Confluence Query Language)
get_page_metadata Lightweight: title, version, author, dates, labels — no content, always fast
get_page_children Direct child pages of a page
get_page_attachments Explicit attachment list (opt-in — include_attachments: false skips it)

Key features

  • No silent truncation — truncated: true/false + available_headings list so the agent can suggest get_page_section() as a follow-up
  • include_tables: false — hides wide tables from Markdown (they remain in tables JSON field)
  • include_attachments: false — skips the attachment list entirely, saving 5-10K tokens
  • Section extraction stops at the next heading of same or higher level

Setup

1. Install dependencies

Requires Python 3.11+.

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

2. 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
CONFLUENCE_BASE_URL ✅ — Your Confluence instance URL, e.g. https://confluence.example.com
CONFLUENCE_TOKEN — — Personal Access Token (PAT). On macOS can use Keychain instead (see below)
CONFLUENCE_KEYCHAIN_SERVICE — confluence_pat macOS Keychain service name (alternative to CONFLUENCE_TOKEN)
CONFLUENCE_MAX_CHARS — 50000 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.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured