Unfortunately, the solution in Claude Code now is to manually edit the json settings file, and specify the tools I want into a list there; quite a painful experience to have to copy-paste across the 91 tools GitHub has made available.
INNOVATION
-

MCP Gateways Enable Tool Management and Settings Persistence
By
–
This is where some of the latest infrastructure around MCP management comes in – MCP gateways can help you manage the tools available, and you can easily toggle which ones you want to turn on/off when using them. Not only that, your settings can now persist across different
-

Managing Large MCP Servers Token Usage Efficiently
By
–
Some of these MCP servers are huge! GitHub's server comes with 46.3k tokens out of the box, with a ton of power tools. Here's how I'm managing it:
-
Selective Tool Configuration for Model Context Protocol
By
–
This MCP is great: ton of power tools from adding comments to pending reviews, getting discussions threads, forking the repo, and more. However, in practice, I only want a subset of these tools depending on the task I'm working on.
-
Francine Bennett Uses Data Science To Make AI More Responsible
By
–
Francine Bennett Uses Data Science To Make AI More Responsible | http://
ow.ly/SucM30sOQyJ
#AI #AIio #AIInnovation #ML #DataScience #Futureofwork @demishassabis @Ronald_vanLoon @TamaraMcCleary @geoffreyhinton @goodfellow_ian @jeffdean @erikbryn -
OpenAI welcomes Statsig team and Vijay Eraji
By
–
Welcome @vijayeraji and the @statsig team to OpenAI!
-

Databricks SQL: AI-Powered Data Platform with Instant Scaling
By
–
[Demo] Databricks SQL – Instant startup + automatic scaling
– Built-in AI functions for tasks like sentiment analysis
– Comprehensive governance -
BEHAVIOR AI Robotics System Built on Nvidia Omniverse Platform
By
–
(14/N) We thank @SimovationInc for providing high-quality JoyLo teleoperation data in simulation, reflecting their deep expertise in simulation and data quality. BEHAVIOR is built upon @nvidia
’s Omniverse. We thank @nvidia for their continuous support. -
Long-Horizon Tasks and Embodied AI Scaling Laws
By
–
(10/N) Together, let’s explore:
How close are we to solving long-horizon, complex, human-centric tasks?
How to efficiently combine low-level control and high-level planning?
What are the generalization limits of current models? Are there scaling laws for embodied AI? -
Stanford AI Behavior Challenge: Submit Your Work by November
By
–
(9/N) Evaluation & Submission
Submission instructions and evaluation details are available on our website: https://
behavior.stanford.edu/challenge
Start experimenting today and get ready to compete!
Deadline: Nov. 15th
Winners announced: Dec. 1st
NeurIPS challenge: Dec. 6-7, San Diego, CA