WorkOS launched Auth.md, an open protocol for AI agent registration that uses a machine-readable Markdown file at a service root to enable dynamic discovery of OAuth Protected Resource Metadata and se…
The Model Context Protocol (MCP) is becoming the standard API for LLMs, but security vulnerabilities like path traversal and broken tenant isolation are emerging. To prevent damage from autonomous age…
A developer warns that using human OAuth credentials for AI agents creates security risks, as agents operating under a person's identity can access sensitive history and cause damage attributed to the…
Anthropic's Zero Trust for AI Agents framework correctly identifies that agents require stronger security than chatbots, but its recommendation of short-lived bearer tokens fails its own test of makin…
Claude Code orchestrated a 10-agent code review of loomcycle via MCP fan-out, with reviewers running concurrently inside loomcycle and findings consolidated into a report. The review covered 86 files …
LearnThat, a new remote HTTP MCP server, enables coding agents to integrate small learning exercises into development workflows by adding coaching tools such as level assessments, micro-challenges, an…
WorkOS launched auth.md, an open protocol that enables AI agents to programmatically register with services by reading a machine-readable Markdown file at a service's root directory. The protocol allo…
GitHub has released the Agent tasks REST API in public preview for Copilot Pro, Pro+, and Max users, enabling programmatic initiation and tracking of Copilot cloud agent tasks. The API allows develope…
The Model Context Protocol (MCP) released its 2026-07-28 specification release candidate, the largest revision since launch, which introduces a stateless core that eliminates the need for sticky sessi…
Sentry engineers encountered a rate-limiting bug when Cursor Automations exhausted a human-sized bucket of 60 requests per 60 seconds in seconds, highlighting the challenge of gating MCP servers for a…
Vectoralix has introduced a managed gateway platform for securing remote Model Context Protocol (MCP) servers, implementing OAuth, bearer tokens, and scoped permissions to authenticate and authorize A…
Two 19-year-old students, a mechanical engineering student and an AI student, built AGENTIX and COVENANT to solve a critical security gap in AI agent systems. Their infrastructure gives autonomous age…
A developer has implemented per-user OAuth authentication in a Next.js MCP server, solving the problem of shared API keys that expose one user's data to another. The solution creates a new MCP server …
A developer detailed a blueprint for building production-ready enterprise AI agent workflows, emphasizing that middleware integration, multi-agent governance, and cost-latency tradeoffs are more criti…
This article provides a step-by-step guide for syncing Outlook and Gmail calendars using Amazon Quick, an AI assistant, and a custom MCP (Model Context Protocol) server. The system uses a Python scrip…
The article describes the creation of "maw token," a CLI plugin that manages Claude OAuth tokens and `.envrc` files across an Oracle fleet using the GPG-encrypted `pass` password vault. Born from the …
The article explains that the standard OAuth 2.0 Authorization Code flow has a security gap, as it cannot verify that the application exchanging an authorization code is the same one that originally r…
MCP SEP-2468, merged into the Model Context Protocol specification on May 17, 2026, implements RFC 9207's `iss` parameter to defend against OAuth mix-up attacks. The change requires authorization serv…
Per-user OAuth is essential for AI agents because it allows each individual user to grant the agent a scoped, revocable token tied to their own account, solving the security and auditability problems …
OpenAI's Agent Security Lead Fotis Chantzis argues that identity protocols like OAuth and OIDC fail for AI agents because they assume stable, predictable behavior, while agents act non-deterministical…