ShipSprint + ChatGPT
Connect it once from ChatGPT's Connectors settings and it reads and updates the actual board, not whatever you happened to type in about your day.
ChatGPT, with a real connection to the board
ShipSprint speaks MCP, the open standard assistants use to call real tools, and ChatGPT connects to it the same way it connects to any other MCP-compatible service: through Settings → Connectors. Once it's on, ChatGPT isn't just holding a conversation about project management in the abstract, it's reading and updating your actual workspace.
The connection is one click from your ShipSprint profile. No config files, no local install, nothing to keep running. It gets sixteen real tools: creating and updating issues, commenting, logging time, searching, and reading, writing and appending to the team wiki, each one a genuine action against the live workspace.
The practical case for this is the same one that makes any assistant integration worth having: fewer tab switches. Asking "what's overdue this week?" and getting an answer pulled from the real board, in the same window you were already writing in, beats opening ShipSprint separately just to check.
Ask, and it actually checks
The same underlying tools Claude uses, called from inside ChatGPT.
ChatGPT calls my_work and answers from what's actually assigned and due, not a generic project-management pep talk.
ChatGPT calls log_work and comment_on_issue. Both actions land in the workspace and in the audit log, attributed to you.
ChatGPT calls project_roadmap and list_issues to read the current state, rather than estimating from whatever you last mentioned about the project.
ChatGPT calls create_issue, and the task appears on the board immediately, ready for the next person to see it without you switching apps.
Permissions, and what actually gets logged
ChatGPT acts with your exact account permissions once connected. It can't see or do anything inside the workspace that you personally couldn't, so connecting it doesn't open up access anyone didn't already have. Every action it takes lands in the audit log exactly like any other, attributed to your account, the same as if you'd done it by hand in the app.
The full toolset: my_work, search, create_issue, update_issue, comment_on_issue, log_work, list_projects, list_issues, project_roadmap, whoami, list_spaces, list_pages, read_page, search_pages, create_page, update_page. Prefer to script it directly? The same actions are available as a plain REST API with personal access tokens.
Where this genuinely isn't enough
It only sees what your account can see. A non-admin asking for company-wide numbers across every team's private space won't get them, because the connection respects the same permission boundaries as the app itself. And it's a real tool call, not a guess: precise requests ("log 1.5 hours on the checkout bug") get precise results; vague ones ("log some time on stuff") don't.
Common questions
Team and Business. It isn't included on the Free plan. See the pricing page for the full breakdown.
That depends on OpenAI's own Connectors availability by plan, which is outside ShipSprint's control and can change. Check ChatGPT's current Settings → Connectors requirements directly.
Same MCP server, same sixteen tools, connected separately through ChatGPT's own Connectors settings. See the Claude integration page.
No. It acts with your account's exact permissions, so anything outside your access in the app is outside its access too.
No. It's a one-click connection from your ShipSprint profile through ChatGPT's Connectors settings, with no config files and nothing to run on your machine.
Related pages
See it on your own work.
A workspace your whole company will actually use is 60 seconds away. No card, no risk, nothing to install.
14-day full-access trial · sample project included · no card required