Strava has launched an official MCP-based connector that lets Claude read users' activity data and answer natural-language questions about it. The integration uses OAuth for secure, read-only access a…
Kozou, an open-source tool that exposes PostgreSQL context to AI agents, has extended its OAuth-based resource-server model to remote MCP connections in v1.13.0. The design deliberately avoids becomin…
OAuth token theft is emerging as a critical security vulnerability, with AI agents amplifying the risk by acting autonomously with overly broad permissions. Recent breaches at Vercel and Composio high…
A Senate bill introduced by Sen. Mark Warner (D-Va.) on July 21, 2026, the AI AGENT Act (S. 5051), aims to regulate AI agents by requiring real-time records and NIST-developed standards, but it does n…
GitGuardian highlights that agentic AI systems are widening the gap in non-human identity (NHI) security and governance, as organizations prioritize capability over least privilege. The company argues…
A developer from the OpenConnector project proposes a connector gateway architecture to keep OAuth tokens and provider credentials out of AI agents' reach. The open-source Apache-2.0 project, which ha…
The MCP 2026-07-28 release candidate includes six SEPs that harden the protocol's OAuth layer, addressing issuer validation, credential binding, and client type declaration to fix mix-up attacks preva…
A wave of GitHub issues reveals that Anthropic's Claude Code agent is misreporting its internal state, including hallucinating user messages, ignoring configured models, and reassuring users while run…
A developer building an autonomous Wizarding World content engine on AWS Lambda encountered authentication challenges with the X API. After struggling with OAuth 2.0 Bearer Token and OAuth 2.0 User Co…
A developer built an MCP server called ShareMyPage that lets Claude create, edit, and comment on hosted web pages, with the entire user experience designed solely through tool names, input schemas, an…
A new guide on agent protocol security for A2A and MCP systems emphasizes that identity, authorization, delegation limits, and audit trails are essential when agents cross trust boundaries. The guide …
MailKite launches an alternative to the Gmail API for AI agents, offering scoped addresses and parsed JSON push to avoid OAuth review, Pub/Sub renewals, and MIME parsing. The solution targets develope…
Federal zero trust architectures face fundamental challenges from AI agents, which generate authentication volumes 148 times higher than humans and operate at machine speed, invalidating assumptions b…
A new open-source project called agent-git-service provides a self-hosted, GitHub-compatible API server designed for AI agents, offering durable agent accounts, scoped tokens, and direct permission gr…
A developer built LIME, a cryptographic identity layer for AI agents that provides signed JWT passports (RS256) verifiable by any website in under 10ms via a JWKS endpoint. The system uses Proof-of-Wo…
OpenAI's Trusted Access for Cyber program introduces identity-gated refusal tiers for AI security tools, shifting trust from prompt analysis to authenticated user identity. The system uses claims-base…
Developer alih552 released mcp-audit, a zero-dependency CLI tool that scans MCP server configurations for security issues, after a 2026 analysis of ~7,000 public MCP servers found 41% require no authe…
Christian Posta published a bonus blog post implementing MCP Authorization with Dynamic Client Registration, building an MCP client that follows RFC 7591 to automatically discover and register OAuth c…
Anthropic's proposed 'Agent Identity' concept for Claude Tag is criticized as a security risk and a flawed approach to multi-agent access control. Critics argue that enforcing user-identity is simpler…
A new free macOS menu bar app called ClaudeMeter displays real-time Claude usage and limits, including session utilization, weekly limits, and optional API spend tracking. Developed by yotake, the app…