Claude API user profiles let platforms attribute requests and safety enforcement to individual end customers. Beta organization webhooks report restrictions, bans and their removal; access requires an Anthropic account-team request.
Celigo made MCP Management generally available, combining an MCP gateway and registry with permissions for individual tools. It supports Celigo-built and third-party servers, with user authentication and auditable activity records.
Amazon Bedrock added structured JSON outputs for Claude through both bedrock-runtime and bedrock-mantle. The feature is available in Regions where Claude models are available.
Neural Concept launched MCP Bridge for its customers, allowing agents to operate CATIA, NX, ANSA, HyperMesh and Abaqus. Built on MCP, it connects CAD, meshing and simulation workflows across Windows workstations and Linux clusters.
MiniMax M3.1 Flash is available through the MiniMax API, M Plan and MiniMax Code, with model weights to follow. Listed prices per million tokens are $0.15 for input, $0.60 for output and $0.015 for cached input.
The MCP reference servers now support protocol 2026-07-28 while retaining legacy-client compatibility. The v2.0.0 release raises the four TypeScript servers' minimum to Node 24 and publishes Fetch, Git and Time as 2026.10.19.
GitHub deprecated Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini and Grok 4.5 across most Copilot experiences on October 19, 2026. Enterprise administrators may need to enable replacement models through model policies.
Cloudflare's API MCP server now requests additional scopes when a tool needs them, while retaining permissions already granted. The feature is available in MCP clients that support step-up authorization.
Cloudflare introduced Clairic in preview on Workers AI, returning typed field values from supplied state and a schema. Pricing is $0.10 per million input tokens, with no output-token charge.
Claude Code v2.1.304 adds guided auto-mode setup using the project and recent sessions. It also adds a command that compares Managed Agents settings with Anthropic's security guide without changing them.