Has anyone solved scoped permissions in multi-agent systems? For instance, if a user asks an orchestrator agent to:

1) Search GitHub for an issue in their repo.

2) Fix the issue and push it to GitHub.

3) Search Jira for any tasks related to this bug, and update their status.

4) Post a message to slack, notifying the team that you fixed it.

Now, let’s assume this agent is available to 1000 users at a company. How does the system obtain the necessary GitHub, Jira, and Slack permissions for a specific user?

The answer is fairly obvious if the user approves each action as the task propagates between agents, but how do you do this in a hands-free manner? Let’s assume the user is only willing to approve the necessary permissions once, after submitting their initial prompt and before the orchestrator agent attempts to call the GitHub agent.

If anyone could offer any advice on this, I would really appreciate it. Thank you!

Does MCP solve authentication on user's behalf which stifled OpenAI's GPTs?

Tools often need access to data sources but I don't want to hard code passwords.

Since you’re in SF, have you tried Monkeybrains?

Edit for disclosure: I’m a former employee, but I have no present affiliation with the company.

For years I've wondered why a general purpose, high quality, good UX, browser based DB browser has not existed. I've implemented 3 such (not general-purpose) browsers in my career. But I'd be really happy to stop doing that and use this instead.

I would love to see a Firestore driver implemented (maybe I'll take a crack at it some day), as I'm stuck in GCP land for the time being.