A developer detailed how remote Model Context Protocol (MCP) servers authenticate callers using OAuth 2.1 with PKCE, metadata discovery, and bearer tokens, walking through the exact requests a client …
A developer built pr-proof, an open-source set of three Claude Code skills that validates AI code-review comments against the actual source before acting on them. Run against CodeRabbit's reviews of 5…
Developerz.ai released db-mcp-gateway, an open-source, self-hosted MCP gateway that brokers AI agent access to production databases without exposing credentials. The gateway keeps database URLs and pa…
A comparison of five enterprise AI gateways — Bifrost, LiteLLM, Kong, Cloudflare, and Vercel — evaluates each against five procurement requirements: identity, authorization, auditability, isolation, a…
A developer documented two CEL authorization pitfalls in Solo Enterprise for agentgateway, where a policy restricting LLM access by JWT country claim and requested model silently failed open. Writing …
An analysis of the Entelligence benchmark comparing GPT-5.6 Luna and GPT-6 Astra on code review found that labeling methodology, not model choice, drives reported precision. Run on 2026-09-14 against …
A code review vendor's evaluation of 50 public benchmark pull requests from Cal.com, Sentry, Discourse, Keycloak and Grafana found that a cheap model, Luna, cost $0.0030 per verified bug versus $0.061…
A comparison published by Entelligence benchmarked GPT-5.6 Luna and GPT-6 Astra on identical pull requests, finding Luna cost $0.0041 per review versus Astra's $0.113 but caught 69 verified bugs at 74…
GPT-5.6 Luna found 69 verified bugs across 50 public benchmark pull requests at a total cost of $0.20, while GPT-6 Astra found 92 at $5.66, according to an evaluation published by the AI-Code-Review-E…
Bifrost has introduced a role-based access control (RBAC) model for its AI gateway, distinguishing between configuration, policy, and authority changes to prevent unauthorized modifications to AI gove…
Suspected Chinese cyber operatives used publicly available AI tools to compromise Taiwanese government systems, including its nuclear safety agency, supply-chain vendors, and at least seven energy com…
Keycloak 26.7, released this month, adds production-ready OAuth 2.1 authorization for AI agents using the Model Context Protocol, enabling per-tool scopes and eliminating the default all-or-nothing ac…
Top Celestial Company Ltd released DROS-VEP, a sub-microsecond C-ABI binary circuit breaker for AI agents that enforces runtime tool-call authorization and privileged execution governance, directly re…
A Go developer building a production LLM agent in a regulated field warns that the most important security rule is that the server, not the model, must determine the user's identity. The developer sho…
A developer built Crumb, a runtime that stamps every AI agent action with the identity of the human who directed it, solving the audit-log gap where shared credentials or service accounts obscure acco…
AgentGateway, the Rust-based AI proxy from the AI Agent Infrastructure Foundation, now supports RFC 8693 OAuth 2.0 Token Exchange to securely delegate user identity to AI agents. The feature replaces …
Okta SAML and Keycloak can interoperate via the Identity Assertion JWT Authorization Grant (ID-JAG) draft to enable cross-app access, according to a demo by Christian Posta. The flow converts enterpri…
Logto, an open-source identity engine built on OIDC and OAuth 2.1, challenges B2B auth incumbents like Keycloak and Auth0 by offering native multi-tenancy, M2M authentication, and an MCP server for AI…
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…
Lynx, a Kubernetes-native control and data plane for agentic AI traffic, launched this week. It provides a registry, gateway, audit, authentication, policy enforcement, and agent sandboxing without re…