Skip to content

Areas

MCP & tool use Latest news

Protocols and practice for connecting models to external systems: MCP, function calling, and toolchain integration.

29 picksPast 30 days: 16 itemsTotal: 211 items

Latest pick

Top picks archive · Page 2

Aug 11

Aug 11TueItems 21–29
  1. Zed BlogAI score72

    Zed introduces Delta, a multiplayer environment for coding with agents

    Zed introduces Delta, a multiplayer environment for coding with agents and reviewing their code, and invites first users into a private beta. Delta keeps code and conversations connected through DeltaDB, which captures edits and conversations between git commits and works with existing repositories. The app also supports cloud runners, browser-based sharing, and live syncing of Claude Code sessions.

    AIWhy it matters: The post explains how the new Delta app links conversations with code history, which clarifies a shift in how teams review agent-written changes.

Aug 9

Aug 9Sun
  1. PromptArmor Threat IntelligenceAI score65

    Malicious Zoom AI Skill Can Keep Attacker Connected and Exfiltrate Data

    PromptArmor reports that a malicious Skill or indirect prompt injection can make Zoom's ZoomMate agent connect to an attacker's server and run commands. The connection can persist after the user clicks stop or closes Zoom, and the final chat output appears normal.

    AIWhy it matters: The report shows how a malicious skill or prompt injection can keep a Zoom agent connected after the user stops it, a risk to weigh before enabling agentic assistants.

Aug 4

Aug 4Tue
  1. PromptArmor Threat IntelligenceAI score67

    Atlassian Rovo can be manipulated to exfiltrate Jira and Confluence data

    PromptArmor reports that a hidden prompt injection in an uploaded file can make Atlassian Rovo send Jira tickets and Confluence documents to an attacker's URL without human approval. The attack works even when organization-wide web search is disabled, because the setting does not remove the URL retrieval tool. PromptArmor says it disclosed the issue to Atlassian on May 23, 2026, and that Rovo remained vulnerable at publication on August 5, 2026.

    AIWhy it matters: The report traces a full indirect prompt injection chain in Rovo, showing how a disabled web search setting still leaves a data exfiltration path open.

Jul 21

Jul 21Tue
  1. JetBrains AI BlogAI score62

    JetBrains Context adds repository indexing to coding agents in early access

    JetBrains has launched JetBrains Context in early access, a repository intelligence layer that builds a semantic index so coding agents can retrieve relevant code without repeated searching. In tests on 205 SWE-bench tasks, 175 production-monorepo tasks, and 1,953 code-localization tasks, it reduced agent turns by up to 68%, latency by up to 59%, and execution cost by up to 48%. It works with Claude Code, Codex CLI, and Junie CLI at no additional cost for JetBrains AI subscribers, and it does not store source code on JetBrains Context servers.

    AIWhy it matters: The source gives benchmark figures for turns, latency, and cost, showing how repository indexing might change agent workflows on large codebases.

May 28

May 28Thu
  1. Cognition Blog (Devin, Windsurf)AI score62

    Devin Tests Its Own Code Changes in the Cloud and Returns Proof

    Cognition describes autonomous testing in Devin, where the agent writes a source-grounded test plan, operates the app through computer use, and returns labeled screenshots and an annotated video. Login steps are handled by a deterministic testing skill, and the company says test runs approved per day more than doubled in recent months. Known limits include timing errors with transient UI elements and models sometimes triggering states through JavaScript instead of clicking the interface.

    AIWhy it matters: The post explains how computer use, test plans, deterministic login scripts, and annotated recordings let Devin verify its own code changes end to end.

Apr 7

Apr 7Tue
  1. Anthropic EngineeringAI score67

    Anthropic decouples agent brain, hands, and session in Managed Agents

    Anthropic's Managed Agents separates the harness, sandbox, and session into independently replaceable interfaces. The source says this design let failed containers be replaced, kept tokens out of the sandbox, and reduced p50 time-to-first-token by roughly 60% and p95 by over 90%.

    AIWhy it matters: The post explains how decoupling the harness, sandbox, and session changed failure recovery, credential security, and latency, offering a reusable architecture pattern for long-running agents.

Feb 26

Feb 26Thu
  1. Cognition Blog (Devin, Windsurf)AI score67

    How Cognition Uses Devin to Build Devin Across Slack, Linear, and Code Review

    Cognition reports merging 659 Devin PRs into its own codebase last week, up from 154 in its best week in 2025. The post describes internal workflows across web, Slack, Linear, CLI, and API, including Devin Review for PR diffs and bug catching, a daily design system audit, automated bug triage on Linear, and DANA for data analysis.

    AIWhy it matters: The post shows concrete workflows for using Devin across Slack, Linear, and code review, with specific usage figures that help teams judge fit for their own engineering processes.

Nov 4, 2025

Nov 4, 2025Tue
  1. Moonshot AI (Kimi) · new models on Hugging FaceAI score82

    Moonshot AI releases open-source Kimi K2 Thinking reasoning agent model

    Moonshot AI released Kimi K2 Thinking, an open-source thinking model that interleaves step-by-step reasoning with tool calls across 200 to 300 sequential invocations. The model is a 1T-parameter mixture-of-experts with 32B activated parameters and a 256k context window, and it uses native INT4 quantization for roughly 2x faster generation. The model card reports benchmark results on HLE, BrowseComp, and other tests, and recommends vLLM, SGLang, or KTransformers for deployment.

    AIWhy it matters: The model card gives benchmark tables, quantization details, and deployment settings, letting readers compare Kimi K2 Thinking against GPT-5 and other models on specific tasks.

May 21, 2025

May 21, 2025Wed
  1. Cognition Blog (Devin, Windsurf)AI score62

    Cognition launches official DeepWiki MCP server for indexed GitHub repos

    Cognition launched the official DeepWiki Model Context Protocol server, which is free and requires no login or authentication. It gives programmatic access to ask_question, read_wiki_contents, and read_wiki_structure for GitHub repositories indexed on DeepWiki.com. Private repositories require a Devin account with GitHub connected, and open-source maintainers can apply for $500 in Devin credits.

    AIWhy it matters: The source names the three tools and the access path, showing how indexed GitHub repositories can be queried programmatically without login.