MCP - Page 3
Stories from MCP come first, newest first, then stories from connected topics (AI Agents, AI Agents, prompt injection, Developer Tools, agent harness, coding agents), each labelled with where it comes from. This view is not indexed by search engines.
Latest
Tencent Cloud Open-Sources TeamAI, a Git Harness for AI Coding Agents
Tencent Cloud's TeamAI shares skills, rules and MCP settings across a team's AI coding agents via Git, under MIT. The 76% cost claim is Tencent's own.
Databricks Lets Genie One Run Code as Snowflake Starts Two Previews
Databricks put code execution in Genie One into public preview and Snowflake began previews of agent-led marketplace search and a decision model. No prices or benchmarks yet.
Grok Agents, Part 2: Tools, Connectors and Your Own Data
Part two of our Grok agent guide: tools, connectors and MCP in plain words, a safe read-only first setup, how to limit access and a short safety checklist.
What Grok Bot Connects To and What It Can Do Inside Each Service
What Grok Bot connects to, how sign-in and custom MCP connections work, what it can do inside Gmail, Drive, Notion and more, and how to limit its access.
HSBC and Ant Digital Test AI-Agent Micropayments in Tokenised Deposits
HSBC and Ant Digital say an AI agent found a service, paid a micropayment and settled it in tokenised deposits in a test, not a commercial launch.
Do AI Agents Need Elaborate Harnesses? A Minimal-Agent Study and Two New Toolkits
A preprint from EPFL researchers, listed on Apple's research site, finds a single minimal coding-agent session matched or beat elaborate machine-learning agent systems in its tests. Pasqal releases skills that let coding agents prepare quantum experiments, and Microsoft makes 30 Dynamics 365 CRM skills generally available, with Autopilot still in private preview.
AI Agent Security: Langflow’s Critical Flaw, Copilot’s Encrypted-Instruction Finding and the New Guardrails
A critical Langflow flaw let MCP server settings run any command. Researchers say GitHub's Copilot CLI followed encrypted instructions that it refused in plain text; GitHub says that is not a vulnerability. Meanwhile Atlassian has split its 220+ agent tools into read, write and destructive tiers, and OpenAI has made Codex Auto-review free. What each one confirms.
Tensorlake npm Hijack Stole AI Agent Keys as Copilot Got a Sandbox
A hijacked release of the tensorlake npm package stole tokens and AI-tool config files, and booby-trapped the stolen GitHub token so that revoking it wipes the victim's home folder. The same week, GitHub made local sandboxing for Copilot generally available, Bitdefender released a free agent guard for macOS, and Citadel AI opened early access to agent monitoring. LangChain and past.dev shipped agent tooling with access controls built in. What each one confirms.
Open source in months, not years: weights, serving and agents
Open weights, serving runtimes and agents now fit together. Why open-source AI adoption is compressing from years of glue work to months.
Flux Cloud MCP Server Lets AI Agents Deploy and Pay for Apps in FLUX
The Flux Cloud MCP server turns "deploy nginx for a month" into a signed, paid app on Flux, without an account. The catch is the keys, and...
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.