Feature Requests

[CONTEXT] we are a digital agency that relies on Hive daily. We've been trying to make the MCP IA integration work reliably with Claude since early May. What follows is a brief and only mildly bitter summary. [SECURITY PROBLEM] The connector requires embedding an API key directly in the URL. Since Claude.ai shares connectors org-wide, this meant our director-level key was accessible to every team member — a significant privacy and security issue. Your server supports OAuth 2.0, which would solve this entirely, but Claude.ai 's connector UI doesn't support OAuth discovery yet. So our workaround? We hired an additional Hive seat just to create a restricted account with a safer key. In 2026, we paid for an extra license to work around an authentication model that belongs in 2018. [STABILITY PROBLEM WE CAN´T WORK AROUND] Even with that workaround in place, the connector has now stopped loading its tools altogether in Claude.ai sessions. We're seeing this regularly: * getProjects failing while other calls succeed * Full MCP session dropping mid-workflow * Inconsistent tool availability across sessions * Generic error messages that provide zero debugging value * insertActions working while getProjects fails — which is a special kind of chaos [MID-2026 AND STILL NOT PRODUCTION-READY] MCP as a technology has been heavily pushed by Anthropic and the broader AI ecosystem since late 2025. It's been positioned as the standard for AI-tool integration going forward. We adopted it early, invested time, documented workarounds, opened support tickets, bought extra seats — and today, in the middle of 2026, our most critical business integration still can't reliably load its tools in a web session. There is a real possibility that by the time this is fully stable, the ecosystem will have moved on to something else entirely. That would be a remarkable achievement. What we're actually asking for * Investigate why the connector is failing to load tools in Claude.ai right now — this is a blocker for our daily operations. * Prioritize OAuth support for claude.ai so we can stop paying for a workaround seat. * Improve error messages and session diagnostics so failures are actually debuggable. * Consider project-scoped API keys as a mid-term solution. We genuinely like Hive and believe in the potential of this integration. We just need it to work.

Since our team spans multiple time zones, it would be incredibly helpful to have the ability to schedule direct messages to send at a later time. Ideally, a user could draft a DM, choose a specific delivery date and time, and have the message automatically send at that scheduled time. It would be great if the scheduling option was easily accessible directly below or beside the message text box so it feels intuitive and quick to use. An additional ideal behavior would be for the system to either: -automatically suggest the recipient’s local working hours/time zone when scheduling, or -display the recipient’s local time to help avoid after-hours notifications.

Apply text wrapping in header rows for table, list and gantt views.

With the new change, action attachments open up in a preview directly in Hive and not in a separate browser tab as before. For users who are using Hive together with external extensions, this isn't really comfortable anymore. Also, file preview takes up the entire Hive screen, blocking the action card data as well. Clicking X in the upper-right corner to stop viewing the file in Hive also completely closes the action card. The previous state allowed reviewing the file and the action data at the same time, which is helpful and more practical.

Clarify in the UI how time categories affect project budget usage and related reporting so users know which logged time counts toward budget. Acceptance criteria: Budget views explain which time categories count toward used budget. Time-entry flows provide clear guidance when a selected category does or does not count toward budget. Admin/category configuration explains budget-reporting consequences. Users can identify why logged time is not updating used budget without needing support.

Using the restricted user permission to set to block restricted users from accessing, creating and editing action card templates

Teams need stronger governance for dropdown and multi-select custom fields. Users should be able to select existing custom field values on projects and action cards, but not freely create new dropdown options unless they have permission. Current concern: Users can add new dropdown values when filling out custom fields. This can create duplicate or inconsistent reporting values. For example, teams could create slightly different versions of Business Unit, Sub-Business Unit, Functional Area, or Sub-Functional Area values. This creates dashboard and Portfolio reporting issues because similar work may be split across inconsistent field values. Requested outcome: Workspace admins, or designated field owners, should be able to control who can add, edit, or delete dropdown options for custom fields. Regular users should still be able to select from existing approved values. Permissions for managing dropdown values should be separate from permissions for filling out the field on a project or action card. Use case: Teams using dashboards and reporting views across projects and action cards need consistent field values so leaders can accurately report by categories like Business Unit, Sub-Business Unit, Functional Area, and Sub-Functional Area without manual cleanup. Business impact: Improves reporting accuracy. Reduces duplicate or messy custom field values. Helps larger teams maintain governance as usage expands. Supports broader rollout of dashboards, Portfolio views, and custom fields. Suggested product behavior: Add a setting on dropdown or multi-select custom fields: "Only admins / selected users can manage field options." Users without permission can select values but cannot add new ones. Admins or field owners can add, rename, merge, archive, or delete options.

Currently, newly created subactions default to None section. In this case, when you're using project views that group by Section (for ex. Gantt view), this would show subactions separated from the parent card because their sections differ. This requires manual action each time to assign subactions to the same section.

If meetings from Outlook etc automatically appear in the Resourcing view it will enable us to see an accurate view of how much time a team member has to work each day

I'd like to request a Hive MCP (Model Context Protocol) connector to enable native integration with Claude Cowork, Anthropic's desktop AI tool for automating file and task management. MCP is an open protocol that lets AI assistants like Claude connect directly to external tools and services. With a Hive MCP connector, Claude Cowork users could interact with their Hive workspace hands-free — without copy-pasting, switching tabs, or manual data entry. What this would enable: - Read and update tasks, projects, and assignees directly from Claude - Automatically create tasks or subtasks based on meeting notes, emails, or documents - Query project status and generate summaries or reports - Pull action items from conversations and log them to Hive instantly - Trigger Hive automations from natural language prompts How to build it: Hive would publish an MCP server (open spec at modelcontextprotocol.io ) that exposes its core API actions as MCP tools. Anthropic and the Cowork team handle the rest. This is a relatively lightweight lift with a high-visibility payoff for AI-forward teams.