Claude Code claude mcp add-json stdin support
Claude Code now accepts MCP server JSON from standard input using `claude mcp add-json <name> -`. This keeps sensitive tokens off the command line.
Loading launches from 4 labs
Thursday 19 Nov · Anthropic, OpenAI, Google, Meta
One card per launch from Anthropic, OpenAI, Google and Meta: what changed, how to try it, and every source linked.
Or sign in to save launches, follow topics and join discussions.
Claude Code now accepts MCP server JSON from standard input using `claude mcp add-json <name> -`. This keeps sensitive tokens off the command line.
Claude Desktop now lets users choose between Stable and Latest release channels to control update frequency.
Anthropic's new default model for Pro, Max, Ultra, and Team plans, built for daily knowledge work like research, analysis, and finished files. It matches Opus 5's high-effort performance at its default Medium effort.
Anthropic added fast mode support for Claude on Vertex AI across global, US, and EU regions, with automatic fallback to standard speed if fast mode is refused.
Anthropic's Claude Dashboards is now generally available as Claude Data, letting teams query connected data sources, build dashboards, and share certified metrics, data stories, and live numbers.
Anthropic adds collaborative spreadsheets, whiteboards, and data dashboards as new artifact types in Claude, plus interactive connectors that embed partner apps directly in the chat.
Claude Code's remote-control command now accepts a --settings file flag that applies configuration to every session it starts. Changes to the file require a restart to take effect.
Fast mode delivers up to 2.5x higher output tokens per second for Claude Fable 5.2 on the Claude API when requested via the speed parameter, at higher per-token pricing.
Anthropic launched Claude Fable 5.2 and Mythos 5.2 with 1M token context, 128k max output, and always-on adaptive thinking. Fable 5.2 for reasoning agents; Mythos 5.2 for verified orgs. Pricing: $8/MTok in, $40/MTok out.
New CLI command identifies latency bottlenecks in Claude API code and tests faster configurations against your evals.
A new `permissions.denyInsteadOfPrompting` setting automatically denies tool calls that would otherwise pause for permission prompts, letting the turn continue without interruption.
Claude Code now backgrounds MCP tool calls immediately and reports results when they finish, with an option to disable this behavior.
Claude Code now lets you name a session's billing group using the attributionProject setting. This helps organizations using Claude apps gateways track usage by project.
Claude Code cloud sessions on Anthropic-hosted environments now include a No repository option. Users can start a hosted cloud session without selecting a repository first.
Anthropic now applies a text watermark to content generated by Claude 4.5 and 4.6 models on supported platforms when using default sampling parameters.
Claude cloud sessions now display dedicated link cards when an MCP server asks to visit a URL. This lets users explicitly open or decline requested links rather than missing the prompt.
Anthropic added the GET /v1/organizations/analytics/cost endpoint to the Claude apps gateway admin API, enabling organization admins to track spend by developer, day, or IdP group.
Anthropic added managed.policy_mode: layered to the Claude apps gateway. Every policy matching a developer now applies and merges over the ones below it, instead of only the first matching policy.
Anthropic added pooled group budgets to the Claude apps gateway. Groups can now share a single monthly budget on top of each member's individual limit.
Anthropic raised the maximum request size for the Messages API and Token Counting API from 32 MB to 128 MB on the first-party Claude API, allowing larger payloads in a single call.