Feature Request

The Document360 MCP should be expanded to support managing broken links and redirects. This is particularly important now because the link validator reports many external links as broken when they do not respond within the 5-second timeout. As a result, we have to manually review and ignore a large number of working links before we can identify the links that actually need attention. The MCP should allow us to retrieve validation results, review and ignore incorrectly flagged links, identify where broken links are used, and update or replace them. It should also support retrieving, creating, updating, and deleting redirects. Having these capabilities in the MCP would make it much easier to manage large validation reports and handle broken links and redirects without spending hours reviewing and updating them manually in Document360.

It would be good if you could carry out an enterprise-level authorization so that all colleagues don't have to set up their MCP connection individually. In addition, authentication via JWT for MCP would also be desirable to enable our customers to access MCP as well.

Users embedding AI-assisted search inside the Knowledge Base widget have no built-in setting to change or hide the assistant’s icon. The widget’s existing styling controls only cover the launcher button that opens the widget, not the assistant icon shown inside it. Add a built-in “AI assistant icon” control to the Knowledge base widget’s styling settings, alongside the existing widget (launcher) icon control, allowing users to upload a custom icon or hide the assistant icon within the widget’s AI-assisted search experience — bringing it to parity with the icon customization already available in the standalone AI Chatbot module. Benefit: Users can present a visually consistent, on-brand assistant across every surface where it appears, using a supported configuration option instead of custom code that may require upkeep as the underlying interface changes.

When customers integrate Document360 MCP with third-party platforms such as Azure AI Foundry, which require manual OAuth credential configuration, they need the ability to obtain static OAuth credentials, including the Client ID, Client Secret, Authorization URL, Token URL, Refresh URL, and Scopes for manual entry into the platform's connector settings.

Enable support for managing Document360 article redirection rules through MCP, allowing users to create, view, update, and delete redirect rules programmatically. Currently, MCP supports content creation, search, and retrieval, but redirect management is not available. Exposing this capability would help customers automate redirect administration, reduce manual effort, and simplify URL management.

It would be super helpful please to be able to create a few images in mcp-created articles - we're regularly feeding documents and videos to Claude to generate new articles as part of our documentation updates, adding these manually afterwards is a significant friction for us. Thanks!

The customer is building an AI-powered chat interface using the Document360 MCP server as the knowledge backend. The interface is intended to serve multiple end users who are not Document360 project members. The current OAuth flow requires each user to have a Document360 account and active project membership, which blocks this use case entirely. Customer's ask is the support for secret key / API token based authentication on the MCP server, allowing their backend service to connect to MCP without per-user login.

Users with more than one Document360 project (for example, a product knowledge base and a separate API docs project) cannot access both within the same Claude session. The current design allows one project context per session, requiring a reconnect to switch. This means users who manage multiple projects must interrupt their workflow to switch context, and Claude cannot draw on content from more than one project at a time. Workaround Limitations: Switching projects requires a manual reconnect step, interrupting the session Claude cannot cross-reference content across projects in a single session Users with related projects (e.g., product docs + API docs) lose the ability to get unified answers Requested Solution: Allow users to connect more than one Document360 project to a Claude session simultaneously. Specifically: Let users select multiple projects during MCP connector setup Give Claude access to content from all connected projects within the same session Benefits: Users managing multiple related projects can work without interruption Claude can provide answers that draw on content from multiple project contexts Reduces friction for teams with split documentation across projects Use Cases: Teams with separate product docs and API docs projects, organizations with regional or language-specific projects, teams migrating content between projects

The current MCP Server Analytics dashboard provides a solid baseline, but one of our customers feels that there are several gaps that limit its usefulness for admins managing real-world deployments. They would like to request the following improvements: Break down MCP usage by user role (Owner, Admin, Editor, etc.) and distinguish Reader vs Team Member activity separately, so admins can understand who is driving usage and plan enablement accordingly. Add a geographic and timezone distribution view to help global teams correlate failure spikes or usage patterns with specific regions. Surface which articles and categories are being accessed through MCP tools — not just which tools are called — to identify content gaps and validate whether AI assistants are reaching the right information. For multi-project accounts, introduce a workspace-level filter or cross-project summary so admins can compare MCP activity without switching between projects. Extend export beyond PNG chart images to full CSV downloads across call logs, tool usage, and user activity, enabling use in external reporting and BI tools. Add a "Compare to previous period" toggle so adoption trends can be tracked week-over-week or month-over-month directly within the dashboard. Surface token consumption per user and per client alongside call volume so admins can proactively manage plan limits before failures occur.

I can think of multiple scenarios where AI-based cleanup tools could do the heavy lifting for labor-intensive maintenance tasks: 1) Drive: scan files and compare them against KB structure; identify files that are obsolete, that appear to be stored in the wrong folder, that have meaningless file names etc; offer to make changes directly in agent mode (including creating categories and moving/deleting files). 2) Content Reuse: Because MCP cannot access content reuse items, an AI-based cleanup tool could scan content reuse items like snippets and look for redundancies, duplication, gaps etc.; to make it even more powerful, instead of just scanning and comparing the items themselves, it could also compare these items against the KB. Especially for snippets, this tool could also help with the basic task of searching snippet texts, which would be a major improvement to searching only snippet names.