There are two issues here:
1. invalid_scope error — Robinhood's OAuth server is rejecting the scope=internal that the MCP server requests. This is a bug or misconfiguration on Robinhood's side, not something we can fix locally.
2. "No OAuth flow in progress" — the MCP server's in-memory state also isn't persisting between tool calls.
Both of these point to issues with Robinhood's MCP server itself. A few things worth trying:
- Check if there are any prerequisites — the Robinhood trading MCP might be gated/limited access. Did they send any setup instructions or require account enrollment?
- Remove and re-add the MCP — run claude mcp remove robinhood-trading then re-add it, in case something is stale
- Contact Robinhood — the invalid_scope error specifically means their OAuth server is rejecting the scope their own MCP is requesting, which is a server-side bug they'd need to fix
@HedgieMarkets I think it's partly to blame on the companies. The layoffs have driven a fear of low usage being first cut so employees are competing to burn tokens to keep them from being the bottom of the list.
@ClaudeDevs any tips for speeding up agent sdk? personally i fire off a haiku request to use as the greeter while agent sdk + opus is taking a long time to respond.
@scottastevenson I create a tab group for each feature I'm working and just cycle through them like my sc2 control groups, I'm going from command center to barracks to factory to star port. Keep the agents unblocked and building. Don't get supply blocked!
days like today, my premium engine strategy keeps me feeling somewhat comfortable. given the married put position is easy to maneuver in these down trends.
when i started these positions, i bought a 55 delta long put ~120dte and then sold calls against the position. times like these when we're way down, i like to roll in the put, get it exercised so all my shares get called away above my cost basis. i'm flat to up in all these positions because i've been selling calls and puts the entire time making 1-2% a week.
if only i didn't also have some leaps and short puts to go with the shares that are also in trouble. it's not all roses when you're trying to collect premium every week.
i can manage the puts easily. the few leap calls i'm holding on the other hand... those deltas are dying on the vine. i'll be happy to have the cash/buying power back on monday from my shares. hope we get some peace soon.
https://t.co/pQXm45Hi8z
@pbakaus it's really hard to remember all the commands and skills. is there a simple catch all /impeccable or /design-review skill that will incorporate the whole thing?
@noahzweben I loop an on duty engineer that checks for new bugs in sentry and auto triages and fixes bugs. Then it keeps all open branches up to date with main. Then reviews server performance. Works Well! Need to try the new server tasks next.
@danshipper reminds me of @rands stables vs volatiles. the volatiles are having a blast and the stables have more to clean up than ever. win/win - https://t.co/EYh5iDTMTv
@euboid That's better than what I have setup. I have a Claude loop for my on duty engineer skill that checks sentry for any new crashes. Then it checks all prs and looks for merge conflicts and out of date branches with main.
@sterlingcrispin i do the same but also add in cursor's bugbot as well. they both find bugs claude doesn't. claude still builds the original system better than both of them though. go figure. :D
@startupideaspod i build ui's in my app to test the api's easier than going through chat, then expose everything that the dashboards/ui can do to the chat via mcp so the users can talk to ai/agents runs instead of doing it themselves.
Did you know that RODY has friends?
One of his friends is Theta Fortress aka T-Fort. This friend has some serious security that will back you up while you collect that sweet ass income
For RODY, T-Fort, or other strategies feel free to check out @robotoole website
See comments