mcp-server-atlassian-bitbucket and mcp-server-atlassian-confluence
These tools are complements because one enables AI interaction with Bitbucket for code management, and the other enables AI interaction with Confluence for documentation, allowing an AI system to manage both code and related content across the Atlassian platform.
About mcp-server-atlassian-bitbucket
aashari/mcp-server-atlassian-bitbucket
Node.js/TypeScript MCP server for Atlassian Bitbucket. Enables AI systems (LLMs) to interact with workspaces, repositories, and pull requests via tools (list, get, comment, search). Connects AI directly to version control workflows through the standard MCP interface.
Implements six generic REST tools (GET, POST, PUT, PATCH, DELETE, clone) that map directly to the Bitbucket Cloud 2.0 API, allowing LLMs to access any endpoint without hardcoded integrations. Supports both legacy App Passwords and Atlassian's newer scoped API tokens for authentication, with STDIO transport for seamless integration into Claude Desktop, Cursor AI, and other MCP-compatible clients. Includes JMESPath filtering to reduce token usage by transforming API responses before returning to the LLM.
About mcp-server-atlassian-confluence
aashari/mcp-server-atlassian-confluence
Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get spaces & pages (content formatted as Markdown) and search via CQL. Connects AI seamlessly to Confluence knowledge bases using the standard MCP interface.
Supports token-optimized TOON output format (reducing API response sizes by 30-60% compared to JSON) and JMESPath filtering for selective field extraction. Implements five generic HTTP tools (`conf_get`, `conf_post`, `conf_put`, `conf_patch`, `conf_delete`) providing direct access to the Confluence v2 API, enabling AI assistants to create/update pages and comments alongside read operations. Integrates with Claude Desktop, Cursor AI, and any MCP-compatible assistant via stdio transport, with flexible credential management through environment variables, `.env` files, or `~/.mcp/configs.json`.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work