Open source 80
livetennisapi/livetennisapi-mcp
MCP server for the Live Tennis API — give Claude, Cursor and other LLM agents real-time tennis scores, odds and model win-probability
mcpmodelsdeveloper-workflow
Review primary source Editorial monitor
AI signals selected for review.
A rolling shortlist of official releases, open-source activity, research, and developer discussions related to MCP and AI developer workflows.
Automatically selected 8
Candidate window 7 days
Last generated Jul 31, 2026, 11:14 PM UTC
Automatic shortlist
Review before turning a signal into content.
Open source 76
modelcontextprotocol/python-sdk v2.0.0
MCP Python SDK v2 Stable Release This is v2.0.0, the stable v2 release of the MCP Python SDK. It supports the 2026-07-28 revision of the Model Context Protocol and serves every earlier revision from the same server. pip install mcp now installs 2.x. pip install "mcp[cli]" or uv add "mcp[cli]" Documentation Rewrite The documentation has the full tutorial and…
mcpdeveloper-workflow
Review primary source Open source 76
modelcontextprotocol/typescript-sdk @modelcontextprotocol/fastify@2.0.0
Patch Changes #2402 a400259 Thanks @felixweinberger! First beta release of SDK v2 with support for the MCP 2026-07-28 specification revision. See the migration guides for upgrading from v1 (docs/migration/upgrade-to-v2.md) and adopting the 2026-07-28 revision (docs/migration/support-2026-07-28.md). #2405 f172626 Thanks @mattzcarey! Ship CommonJS builds alon…
mcpdeveloper-workflow
Review primary source Open source 76
openai/openai-agents-python v0.19.0
Key Changes This minor release does **not** introduce a breaking change. The minor version bump reflects a significant new OpenAI Responses feature area: Programmatic Tool Calling. Highlights: Added agents.tool.ProgrammaticToolCallingTool, which lets supported OpenAI Responses models generate JavaScript to coordinate eligible tools. It supports per-tool all…
agentsdeveloper-workflow
Review primary source Research 75
The Ethics of Autonomous AI Agents for Offensive Security
LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling -- deterministic, narrowly scoped, and operated by trained practitioners -- agentic security tools exhibit \textit{indeterminacy} along three independent dimensions. First, their actions are drawn from a non-deterministic policy whose outputs resist…
researchagentsmodelsdeveloper-workflow
Review primary source Open source 75
TryCaspian/caspian-sdk
Agent communication SDK. The open-source agent communication layer for AI agents — email, WhatsApp, Slack, Discord, Telegram, SMS. Python & TypeScript.
agentsdeveloper-workflow
Review primary source Open source 71
modelcontextprotocol/specification 2026-07-28
This release marks the **stable release** of the 2026-07-28 revision of the Model Context Protocol. The specification is available on the official Model Context Protocol website. For a detailed overview of changes, see 2026-07-28 changelog.
mcpofficial
Review primary source Developer discussion 71
VulnHunter: Capital One's agentic AI code security tool
Open the primary source to review the change and supporting details.
developer-discussionagentsdeveloper-workflow
Review primary source Latest scan
New candidates found in the latest collection.
Research 68
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout commercial AI products, but are rarely disclosed to the public or regulators, creating a serious trust and accountability gap in the wide deployment of AI systems. In this paper, we introduce Artificial Intellige…
researchmodelsdeveloper-workflow
Watching: score below 70
Review primary source Research 68
AI systems and the reproduction of (standard) language ideologies in World Englishes
The rapid growth of large language models (LLMs) has resurrected age-old questions in sociolinguistics and world Englishes, such as who decides what counts as legitimate English, whose English is suspect etc. This paper examines how AI systems, their uses and discourse on them reflect, reinforce, and occasionally challenge (standard) language ideologies, wh…
researchmodelsdeveloper-workflow
Watching: score below 70
Review primary source Open source 67
0xwilliamortiz/ratchet
Your agent reads the rules. This checks whether it followed them.
agents
Watching: score below 68
Review primary source Developer discussion 66
Show HN: What should the GUI for AI agents look like?
Open the primary source to review the change and supporting details.
developer-discussionagents
Watching: score below 68
Review primary source Open source 66
uczltw6/trace-file-lineage
Find which script, notebook, data, command, or AI agent produced a file — locally, with evidence and honest uncertainty.
agents
Watching: score below 68; fewer than 100 GitHub stars
Review primary source