Frequently Asked Questions about the UBOS MCP Server for Confluence

Q: What is an MCP Server? A: MCP (Model Context Protocol) Server is an implementation that allows AI models to access and interact with external data sources and tools. In this case, it manages Confluence wiki pages.

Q: What can I do with the MCP Server for Confluence? A: You can automate creating, updating, deleting, and searching Confluence wiki pages programmatically. It helps streamline knowledge management workflows.

Q: What are the key technologies used to build this MCP Server? A: The server is built using Python 3.10+, FastAPI, MCP SDK, Requests (for Confluence API interaction), and ContextVars (for session management).

Q: How does the server automatically select the correct Confluence knowledge base? A: The server infers the knowledge base (e.g., alm, wpb) based on keywords in the user query. For example, queries mentioning gsna or global will target the alm knowledge base.

Q: What headers are required when making requests to the server? A: You need to provide user_name, alm_confluence_base_url, alm_confluence_api_token, and optionally wpb_confluence_base_url and wpb_confluence_api_token.

Q: Can I run this server using Docker? A: Yes, the project includes a Dockerfile for containerizing the server, making deployment easier.

Q: What kind of license does this MCP Server have? A: This MCP Server is released under the MIT License.

Q: How does this MCP Server integrate with the UBOS platform? A: The MCP Server complements the UBOS platform by providing a seamless way to incorporate Confluence knowledge into broader AI agent strategies, enhancing the platform’s ability to connect with enterprise data.

Q: What if I don’t provide the right headers for authentication? A: If headers are missing or invalid, the server will return an HTTP 400 error.

Q: Is there any way to manually specify the wiki type? A: Yes, you can manually specify the wiki_type in the request input if needed.

Q: Where can I find the API documentation? A: After starting the server, you can visit http://localhost:9999/docs for OpenAPI docs (Swagger UI) or http://localhost:9999/redoc for ReDoc docs.