惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 【当耐特】
L
Lohrmann on Cybersecurity
Google DeepMind News
Google DeepMind News
Schneier on Security
Schneier on Security
Recent Commits to openclaw:main
Recent Commits to openclaw:main
The Last Watchdog
The Last Watchdog
Application and Cybersecurity Blog
Application and Cybersecurity Blog
N
News and Events Feed by Topic
P
Proofpoint News Feed
H
Heimdal Security Blog
云风的 BLOG
云风的 BLOG
H
Hacker News: Front Page
量子位
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
L
LINUX DO - 最新话题
F
Full Disclosure
小众软件
小众软件
Martin Fowler
Martin Fowler
Security Latest
Security Latest
The Cloudflare Blog
Hacker News: Ask HN
Hacker News: Ask HN
C
Check Point Blog
Security Archives - TechRepublic
Security Archives - TechRepublic
I
InfoQ
AI
AI
Blog — PlanetScale
Blog — PlanetScale
I
Intezer
H
Hackread – Cybersecurity News, Data Breaches, AI and More
M
MIT News - Artificial intelligence
V
Vulnerabilities – Threatpost
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
www.infosecurity-magazine.com
www.infosecurity-magazine.com
V
V2EX
N
News and Events Feed by Topic
C
Cybersecurity and Infrastructure Security Agency CISA
T
Troy Hunt's Blog
大猫的无限游戏
大猫的无限游戏
Hacker News - Newest:
Hacker News - Newest: "LLM"
The Register - Security
The Register - Security
Forbes - Security
Forbes - Security
Recent Announcements
Recent Announcements
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Cisco Talos Blog
Cisco Talos Blog
Microsoft Azure Blog
Microsoft Azure Blog
A
About on SuperTechFans
S
SegmentFault 最新的问题
S
Securelist
Cloudbric
Cloudbric
T
Tenable Blog
D
Docker

Show HN

GitHub - flightdeckhq/flightdeck: Observability and control plane for AI agents. CSP Radar GitHub - Light-Heart-Labs/DreamServer: Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation. GitHub - Diplomat-ai/diplomat-agent-ts: What can your TypeScript AI agent do to the real world? Scan your code. See which tool calls have zero checks Code Block Selector - Visual Studio Marketplace Prometheus dependency graph — interactive showcase | Riftmap Show HN: I made a vi-like modal keyboard plugin for Figma GitHub - run-llama/liteparse: A fast, helpful, and open-source document parser GitHub - dalemyers/Roar: A macOS CLI tool for notifications GitHub - district-solutions/open-agent-tools-coder: Enables small-to-large self-hosted ai models to use local source code when running tool-calling agentic workloads. We actively data mine 20,900+ (2+ TB) popular github repos using large and small ai models to create reuseable: json, markdown and parquet files for local-first tool-calling models. GitHub - progapandist/stripeek: A local TUI proxy for real-time Stripe API debugging, built for navigating complex payloads fast. GitHub - sir1st/hermes-desktop: All-in-one cross-platform desktop app for Hermes Agent — bundles Python + hermes-agent + hermes-web-ui GitHub - astefanutti/shaderbang: Shebang for Shaders Show HN: Generate Claude Code Workflows using Spec Driven Development approach GitHub - nixys/nxs-universal-chart: The Helm chart you can use to install any of your applications into Kubernetes/OpenShift Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code. GitHub - tamerh/enju: Coordinating Humans, AI Agents, and Compute as Peers on a Shared Workflow Graph Show HN: Continuity-auth – Respect-weighted rate limits for the open web GitHub - luml-ai/luml: AI lifecycle platform where engineers and agents track experiments, train models, and ship to production. GitHub - mrdanielcasper/CoreTex: A UNIX-inspired, biomimetic, flat-file AI harness and knowledge engine. GitHub - clemg/pierre-github: Pierre's diffs.com and trees.software for Github GitHub - lyriks-io/unspaghettit: Behavior-driven AI development without prompt spaghetti. GitHub - sofumel/claude-handoff-revive: Resume Claude Code work after rate/usage/context limits without replaying the prior transcript. Auto-saves at 90%/95% usage. Plugin-installable, 10 languages. GitHub - dotexorg/saferpc: Typed, end-to-end encrypted RPC over any bidirectional channel. GitHub - BeeZeeAgent/beezee: Agent harness orchestration Legato Next.js Boilerplate for Internal Tools · CoreUI GitHub - clark-labs-inc/clark-hash: Clark Hash, 32x smaller searchable sketches for embeddings GitHub - ZeroPointRepo/youtube-mcp: The fastest YouTube transcript + YouTube search MCP for AI agents. Try for free. Typing Mastery — climb toward 100+ WPM, deliberately GitHub - Andebugulin/Awareen GitHub - fayzan123/claude-workflow-composer: Visual desktop app for composing multi-agent coding workflows. Drag agents, attach skills and MCPs, wire handoffs, export to .claude/ GitHub - harshaneel/humanize: Best static AI text humanizer. Two research-grounded skills that work in any LLM (Claude, ChatGPT, Gemini, Codex): humanize beats perplexity-based detectors, ai-check produces forensic scoring with evidence-quoted flags. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature. GitHub - StackOneHQ/stack-nudge GitHub - nodes-app/swift-markdown-engine: A native AppKit Markdown editor for macOS, built on TextKit 2 and bridged to SwiftUI. We hardened an LLM agent. Each defense we added made it more exploitable. GitHub - alkait/WhatsKept: Agent-queryable WhatsApp history from an iOS backup — a single Go binary. GitHub - octelium/cordium: Open-source, general-purpose sandbox platform for devs and AI agents that provides identity-based secure access to infrastructure without credentials. WAR.GOV/UFO Microfilm5 GitHub - scosman/videowright: Build animated explainer videos with your coding agent GitHub - dipankar/dscode: The code editor you can take apart. GitHub - zoharbabin/web-researcher-mcp: MCP server (Go) for AI assistants: web search, content extraction, academic/patent/news research. Multi-provider routing, 4-tier scraping, search lenses. Works with Claude, Cursor, and any MCP client. GitHub - ruvnet/RuView: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. GitHub - scanaislop/aislop: Catch the slop AI coding agents leave in your code: narrative comments, swallowed exceptions, as-any casts, dead code, oversized functions. 50+ rules across 7 languages (TypeScript, JavaScript, Python, Go, Rust, Ruby, PHP). Sub-second, deterministic, no LLM at runtime. MIT-licensed. GitHub - kouhxp/cheap-im: CPU-only voice agent approximating Thinking Machines' Interaction Models demo GitHub - unprovable/OrchidMantis: Orchid Mantis — standalone framework for Zero-Knowledge Proofs of eXploit (ZKPoX). GitHub - MarcellM01/TinySearch: Shrink the web for your local LLMs! GitHub - pileax-ai/pileax: PileaX is an all-in-one AI knowledge base system. 🍀 GitHub - TangibleResearch/Halgorithem: A Algo designed to detect AI Hallucitions GitHub - DO-SAY-GO/freelang: I love freelang GitHub - CarpseDeam/Aura-IDE: An AI coding harness that shaped itself - Planner/Worker agents, repo awareness, surgical edits, validation, recovery, and safe diff approvals. GitHub - chojs23/concord: A feature-rich TUI client for Discord GitHub - tommyjepsen/awesome-ux-skills: UX & AI Product designs skills you can use today in Claude Code GitHub - aerf-spec/aerf: Agent Evidence Receipt Format (AERF) — an open specification for tamper-evident, independently verifiable records of AI agent actions. GitHub - kklimuk/docx-cli: CLI for AI agents (Claude, Codex) to read, edit, and comment on .docx files with full format fidelity. GitHub - Jwrede/tokentoll: Catch LLM cost changes in code review. Infracost for LLM spend. GitHub - samchon/ttsc: A `typescript-go` toolchain for compiler-powered plugins and type-safe execution + 500x faster lint integrated into compiler GitHub - Higangssh/homebutler: 🏠 Manage your homelab from chat. Single binary, zero dependencies. GitHub - olalie/tapmap: See where your computer connects and what stands out on a live world map. GitHub - matisiekpl/neond: DX-focused control plane for Postgres dedicated to non-critical workloads. Your postgres:latest replacement 🐘 GitHub - Diplomat-ai/diplomat-agent: What can your AI agent do to the real world? Scan your code. See which tool calls have zero checks GitHub - Bajusz15/beacon: Open-source agent for secure remote access, monitoring, and deploys across home-lab and self-hosted machines like Raspberry Pi, N100, or any Linux server. Open web based TTY or tunnel Home Assistant and other local services securely without opening ports. BigTech AI News - Chrome 应用商店 GitHub - vinhnx/VTCode: VT Code is an open-source coding agent with LLM-native code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management. GitHub - michaelaz774/decision-engine: A decision operating system for startup founders, powered by Claude Code. Synthesizes wisdom from 25+ legendary founders and investors into interactive AI-driven decision frameworks. GitHub - Chrilleweb/dotenv-diff: Validate environment variable usage in your codebase GitHub - Lumen-Labs/brainapi2: BrainAPI is a knowledge graph–powered AI memory layer that transforms unstructured data into structured knowledge, enabling intelligent search, recommendations, and contextual memory for AI agents and applications. GitHub - familiar-software/familiar: Let AI watch you work. Familiar lets your AI update its memory, skills, and knowledge by watching your screen. GitHub - skorotkiewicz/rudo: A small, elegant dock for Wayland GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. make sidebar/address bar rounded corner toggleable
GitHub - AuthPlane/authserver: OAuth 2.1 Authorization Server for the Model Context Protocol (MCP)
AuthPlane · 2026-06-18 · via Show HN

CI Release License: AGPL-3.0 Go Version

The self-hosted authorization server for the Model Context Protocol.

One Go binary. AGPL-3.0. MCP Authorization spec 2025-11-25, end-to-end.

AI coding agents: read AGENTS.md first — it has the deterministic workflow for adding Authplane to an existing MCP server, the SDK pins per stack, and the three byte-for-byte rules that cause >90% of invalid_token failures. If you're an agent operating from web docs (no clone), llms.txt is the same link map in the llmstxt.org convention.

Why Authplane

Building an MCP server is now a one-afternoon job. Securing it isn't. You need to issue tokens, validate them, federate to your existing IdP, and let agents act on each other's behalf without losing the user behind the chain. Authplane is the one piece of infrastructure that answers all of that.

  • Spec-compliant access tokens for any MCP server in any language — discovery, scopes, audience binding, refresh rotation, in token formats your existing resource servers already understand.
  • Federation to your existing IdP — Google, Okta, Azure AD, Auth0, anyone OIDC-compliant. Authplane handles the OAuth side; you keep the access policy.
  • Agent-to-agent delegation — one agent calls another on a user's behalf, with every hop recorded as an act-claim chain in the issued token and the audit log.
  • Upstream provider vaulting — store GitHub / Google / Slack / Linear refresh tokens encrypted at rest and vend fresh access tokens via RFC 8693, with per-user / per-agent / per-resource consent enforced at every hop.
  • DPoP proof-of-possession — bind tokens to a client-held key so a leaked token can't be replayed from another machine.
  • Built-in Admin UI — React dashboard embedded in the same binary. No separate frontend, no extra container.
  • Production storage and observability — PostgreSQL with cross-instance LISTEN/NOTIFY, OpenTelemetry traces and metrics, Prometheus, Helm chart, Vault Transit for HSM-grade signing.
  • Zero-config dev — default SQLite, auto-generated signing keys, sensible defaults.

(Full RFC inventory at the bottom — Standards & Specifications.)

Quick Start

One docker run. A working OAuth 2.1 + MCP authorization server in under a minute.

export AUTHPLANE_ADMIN_API_KEY="$(openssl rand -hex 32)"
export AUTHPLANE_SESSION_SECRET="$(openssl rand -hex 32)"
echo "Save this — it's your Admin UI login: $AUTHPLANE_ADMIN_API_KEY"

docker run -p 9000:9000 -p 9001:9001 \
  -e AUTHPLANE_ADMIN_API_KEY \
  -e AUTHPLANE_SESSION_SECRET \
  -e AUTHPLANE_CLIENT_CREDENTIALS_ENABLED=true \
  -e AUTHPLANE_DPOP_ENABLED=true \
  -e AUTHPLANE_TOKEN_EXCHANGE_ENABLED=true \
  -v authserver-data:/data \
  authplane/authserver:latest serve

Open http://localhost:9001/admin/ui/ and paste the printed API key. The public OAuth endpoints are on http://localhost:9000.

Next: register your first MCP server

  • Writing an MCP server from scratch? Start at the runnable example for your language — Python · TypeScript · Go. Auth in 5 lines, end-to-end smoke in make verify.
  • Adding auth to an MCP server you already have? The retrofit example is a runnable before/after pair — same three tools in two versions, side-by-side, with a smoke-test that proves before accepts anything and after enforces auth. Python · TypeScript · Go. Or read the Connect an MCP Server guide for the prose version.
  • Already have an MCP server running elsewhere? To point this AS at your server and drive the whole OAuth flow by hand with curl — no SDK, no compose — see Run the AS standalone and point it at your own MCP server. It also reconciles this Quick Start's config with the examples/ .env style.
  • Operator quickstart (upstream providers, PostgreSQL, OIDC federation, Helm, multi-instance): docs/README.md.
  • Building from source: CONTRIBUTING.md.

The Admin UI

Authplane Admin UI

Manage everything from a browser. The Admin UI is embedded in the same binary; every operation is also exposed via the Admin REST API.

SDKs

Authserver is only half the story. The MCP server on the other side still has to validate the tokens, expose the discovery endpoint, enforce scopes per tool, handle DPoP, and decode consent errors. The Authplane SDKs do all of that in 5 lines of integration code — measured, CI-counted, in Python / TypeScript / Go alike. The full ladder (basic MCP server → calling another resource → DPoP + per-tool scopes → fronting a Broker upstream) sits between 5 and 30 lines of auth-specific code per tier; see examples/ for the numbers under each tier's banner.

Every Authplane SDK provides the same baseline:

  • JWT validation against the authserver JWKS, with caching
  • Scope enforcement, per route or per tool
  • The Protected Resource Metadata document at /.well-known/oauth-protected-resource/<mcp-path> (RFC 9728, suffixed per the MCP spec)
  • DPoP proof verification (RFC 9449)
  • A full OAuth client — Client Credentials, RFC 8693 Token Exchange, Introspection, Revocation
  • Structured ConsentRequiredError decoding for the upstream-provider Broker flow

Pick the language and the framework adapter that match the stack you're already on.

Language Repo Integration Adapters Docs
Go authplane/go-sdk
License
✓ Official MCP Go SDK (go-sdk/mcp) README
TypeScript authplane/ts-sdk
License
✓ Official MCP TypeScript SDK (@authplane/mcp)
✓ FastMCP (@authplane/fastmcp)
README
Python authplane/python-sdk
License
✓ Official MCP Python SDK (authplane-mcp)
✓ FastMCP (authplane-fastmcp)
README
Rust roadmap
C# roadmap
Java roadmap

Working examples wired against authserver live under examples/ — Python / TypeScript / Go, with four tiers each (basic MCP server, calling another resource, DPoP + per-tool scopes, MCP server fronting a Broker). Every example's make verify is exercised by make docs-smoke and the per-tier LOC budget is CI-enforced via tools/loccount.

Integration walkthroughs: Auth Client · Resource Server.

Documentation

For advanced operations and deeper reference, the docs/ tree is organized by audience:

Get started Quickstart
Configuration Configuration Guide · Schema Reference
API Reference HTTP API (all endpoints) · CLI · Audit Events · Metrics
Security Threat Model · Tokens and Claims · Key Rotation · DPoP
Deployment Docker Compose · systemd · Kubernetes
Guides Connect an MCP Server · Admin CLI & API · OIDC Federation · Observability
Grant Types Client Credentials · Token Exchange · JWT Bearer / XAA · Enterprise-Managed Auth
Architecture Architecture Overview · Authentication Flows · RFC Compliance
Full Index Documentation Index

Standards & Specifications

Authplane implements the MCP Authorization specification (2025-11-25) and the OAuth 2.1 ecosystem standards behind it. ("OAuth 2.1" is an active IETF Internet-Draft, not a finalized RFC — the MCP spec itself targets it. See Compliance for the full picture.) Here's what each one gives you, in operator terms:

Standard What it provides
MCP Authorization 2025-11-25 The contract MCP clients and servers expect: discovery endpoints, dynamic client registration, audience-bound tokens. The reason your existing MCP tooling can find and talk to authserver without custom adapters.
OAuth 2.1 The base authorization flow — authorize endpoint, token endpoint, refresh tokens, scopes. PKCE-S256 is mandatory; the older insecure flows aren't supported.
PKCE (RFC 7636) Prevents stolen authorization codes from being redeemed. Critical for public clients (CLIs, desktop apps, mobile).
DPoP (RFC 9449) Binds tokens to a client-held key. A leaked token can't be replayed from another machine.
Resource Indicators (RFC 8707) Audience-binds every token to a specific resource URI. An access token for one MCP server can't be replayed against another.
Protected Resource Metadata (RFC 9728) MCP servers advertise where their authorization server lives. Clients discover the AS automatically.
Dynamic Client Registration (RFC 7591) Clients register themselves at runtime — needed for MCP clients you don't pre-provision. Three security modes: open, approved-redirects, admin-only.
Client ID Metadata Documents (CIMD) Auto-registration by fetching client metadata from the client's URL. The MCP-native way for agents to identify themselves without a registration round-trip.
OAuth AS Metadata (RFC 8414) + OIDC Discovery The /.well-known/oauth-authorization-server and /.well-known/openid-configuration documents every OAuth client knows how to fetch.
Token Exchange (RFC 8693) Delegated identity — one client mints a narrower or differently-scoped token from an existing one. Powers the agent-to-agent delegation chain and the upstream-provider Broker flow.
JWT Bearer (RFC 7523) Trusted external IdPs assert identity directly into Authplane. The foundation for Cross-App Access (XAA) and enterprise federation.
JWT Access Tokens (RFC 9068) Default token format (at+jwt). Every token is a self-contained JWT your resource servers can verify offline against the JWKS.
Token Introspection (RFC 7662) Runtime token validation endpoint for revocation-aware verification.
Token Revocation (RFC 7009) Standard endpoint to revoke refresh tokens and their families.

Status & roadmap

Authplane is in active development. v0.1.x is production-shaped — the OAuth core, MCP discovery, and audit log are spec-compliant and tested. A few things to set expectations:

  • Rust, C#, and Java SDKs are on the roadmap; Go, TypeScript, and Python are released.
  • Upstream-provider connections (Broker flow) require manual configuration of at-rest encryption (aes_master or HashiCorp Vault Transit) before they activate — covered in docs/guides/upstream-providers/connecting-providers.md.
  • Multi-tenant isolation today means running separate instances per tenant. A first-class tenant abstraction is post-v1.0.
  • Public dynamic-registration signup UI is not in v0.1; Dynamic Client Registration works over HTTP today, a hosted signup page is a follow-up.
  • Helm chart (charts/authplane) is at v0.1.0; tested for single-instance and basic HA, expect tuning for large fleets.

If something here blocks your deployment, open an issue — the priority list is informed by what you're trying to ship.

License

AGPL-3.0-or-later — see LICENSE.

Need a different licence?

We'd love to hear from you — write to hello@authplane.ai and let's find one that fits.