vibehacker
News
Teable Community ·

Teable ships an official MCP server with OAuth, so Claude Code, Codex, and Cursor can work your tables

As of Oct 16, adding https://mcp.teable.ai/mcp to an MCP client (for example claude mcp add --transport http teable https://mcp.teable.ai/mcp) lets agents list projects, inspect tables and fields, query and edit records, and discover APIs within your existing permissions, approved once in the browser instead of with a personal access token. Self-hosted instances expose it at /mcp, and Settings → MCP lists connected clients so you can revoke them.

Read at community.teable.ai

More news

View all

GitHub license compliance goes GA, with an API so coding agents can check packages against policy

As of Oct 16, GitHub Enterprise Cloud repos with Code Security can enforce an enterprise wide dependency license policy through a ruleset condition, Require license compliance results before merging , which annotates and blocks PRs that add noncompliant dependencies. A new API endpoint checks whether packages comply, so coding agents can avoid suggesting dependencies that break the org's license rules…

GitHub Changelog

Archon CVE-2026-111322: default installs expose an unauthenticated agent control API (CVSS 9.3)

VulnCheck says Archon 0.2.13 through 0.11.1 (including the current release) binds its /api/ control API to 0.0.0.0 with no auth by default, so anyone on the network can message the coding agent, which runs with bypassPermissions , and run commands as the Archon user. No fix is listed yet; set HOST=127.0.0.1 , or set both DATABASE URL and BETTER AUTH SECRET to turn on the auth gate…

VulnCheck

Perplexity open-sources SPACE, the Firecracker microVM sandbox behind its Computer agent

As of Oct 15, SPACE ( perplexityai/SPACE , written in Rust) runs agent or user code in isolated Firecracker microVMs behind an HTTP API for creating sandboxes, running commands, streaming output, and pausing, resuming, or branching sessions, with credentials and network access kept outside the VM. It deploys locally on a Kind cluster, and CoreWeave, Akamai, and Crusoe have signed on to offer it to customers…

Perplexity Blog

Black Forest Labs opens FLUX 3 Image Klein: 5.6B text-to-image and editing model that runs in 8GB VRAM

As of Oct 15, FLUX 3 Image Klein ships as open weights (base for LoRA fine tuning plus a step distilled model) with native 4K output, bounding box edits, and up to 10 reference images; the INT8 build runs on 8GB RTX GPUs via ComfyUI or Diffusers. It's under the FLUX Kommunity License (free commercial use under $5M revenue) and on the BFL API as flux 3 image klein from $0.009 per image…

Black Forest Labs Blog

Spotted something we missed? Start a thread.