KS-GEN-AI/confluence-mcp-server

Overview

An early, experimental connector between your AI assistant and Confluence, letting it search and read pages so questions about your team's documentation can be answered in conversation. The project is explicitly a small test build with minimal documentation and no active maintenance, so treat it as a proof of concept rather than something to depend on for daily operations. Worth a look if you want to prototype AI access to Confluence before committing to a more established option.

Best for

Best for
Teams wanting to prototype AI access to Confluence documentation before committing to a tool

Use cases

• Search Confluence for an answer buried in team documentation
• Prototype AI-assisted access to a Confluence knowledge base
• Test how an assistant might read and cite existing wiki pages

How to use

Install

npx -y @smithery/cli install @KS-GEN-AI/confluence-mcp-server --client claude

Tested with

Claude Desktop

Example client config

{\n  "mcpServers": {\n    "Confluence communication server": {\n      "command": "node",\n      "args": ["/PATH_TO_THE_PROJECT/build/index.js"],\n      "env": {\n        "CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net/wiki",\n        "CONFLUENCE_API_MAIL": "Your email",\n        "CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens"\n      }\n    }\n  }\n}

Notes

A minimal, experimental Model Context Protocol (MCP) server for Atlassian Confluence, implemented in JavaScript. It allows MCP-compatible clients to query and interact with Confluence content via the standard MCP interface.

13 stars on GitHub. Last updated 2026-04-23. Licensed MIT.

Use cases

• Connecting AI assistants or chatbots to Confluence for document retrieval
• Building custom automation tools that read from Confluence spaces
• Prototyping MCP-based integrations with Confluence APIs

Pros

• Open source with a permissive license
• Lightweight JavaScript implementation easy to fork or modify
• Demonstrates MCP integration with a popular knowledge base platform

Cons

• Very early stage (13 stars, labeled as a test) with minimal documentation
• Limited testing and real-world reliability unknown
• No active maintenance or community evident beyond initial commit

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.