confluence-data-access-service
A specialized server component facilitating robust interaction with the Confluence knowledge base. Enables execution of structured query language (CQL) searches, retrieval of specific page artifacts, and modification of existing page narratives, thereby embedding critical Confluence intelligence directly within application workflows.
Author

KS-GEN-AI
Quick Info
Actions
Tags
Confluence Knowledge Base Interface Module
Gateway to Confluence Operations
This implementation, constructed using TypeScript, serves as an exemplary Model Context Protocol (MCP) server. It exposes essential capabilities for seamless enterprise wiki integration:
- Query Execution: Functionality for issuing complex CQL predicates to locate desired documentation assets.
- Content Retrieval: Mechanisms for fetching the complete content payload of designated Confluence entries.
- Content Modification: Routines for applying authorized alterations to the narrative or metadata of existing wiki pages.
Core Functionalities
Confluence Interaction Primitives
execute_cql_search
- Objective: To resolve a specified CQL expression against the Confluence repository for locating relevant pages.
- Arguments:
cql(the search string),limit(constraining the result set, defaulting to ten entries).
get_page_content
- Objective: To acquire and return the complete textual or markup content associated with a specific page identifier.
- Arguments:
pageId(the unique identifier of the target page).
update_page_content
- Objective: To push revised data back to a Confluence page, overwriting existing content.
- Arguments:
pageId,content(the new body material),title(an optional parameter to simultaneously revise the page's heading).
Project Setup and Compilation
Acquire necessary dependencies:
bash npm install
Compile the server source code:
bash npm run build
Activate continuous build monitoring for active development:
bash npm run watch
Deployment via Smithery
To facilitate automated incorporation of this Confluence Interface Module into environments like Claude Desktop via the Smithery registry:
bash npx -y @smithery/cli install @KS-GEN-AI/confluence-mcp-server --client claude
Configuration instructions for Claude Desktop necessitate modifying the configuration file (claude_desktop_config.json) located in:
MacOS: ~/Library/Application Support/Claude/
Windows: %APPDATA%/Claude/
Add the following structure, replacing placeholders with actual credentials:
{ "mcpServers": { "Confluence communication server": { "command": "node", "args": ["/PATH_TO_THE_PROJECT/build/index.js"], "env": { "CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net/wiki", "CONFLUENCE_API_MAIL": "Your email", "CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens" } } } }
Diagnostic Procedures
Debugging direct standard I/O communications for MCP components can present difficulties. We strongly endorse leveraging the MCP Inspector utility, accessible via a dedicated package script:
bash npm run inspector
Executing this command will yield a local network URL that directs you to a browser-based interface equipped with comprehensive debugging instrumentation.
