Dominion Observatory

What it does

Dominion Observatory scores every public MCP server on behavioral trust — not just code quality, but what actually happens when agents call them in production. Check any server in one line: curl dominionobservatory.com/api/trust?url=brave-search. Browse 14,824 servers with letter grades A+ to F. Drop-in trust gates for FastMCP, LangChain, CrewAI, and OpenAI Agents SDK. Free. No signup. No API key.

Most MCP trust tools statically scan the code. Dominion Observatory is the neutral, third-party layer that measures what an MCP server actually does at runtime — uptime, success rate, latency from real agent traffic — and shows

Free scanners rate a server once — then a silently updated tool description turns your agent against you (the attack Microsoft warned every Copilot customer about, June 2026). Independent research across 9,695 MCP servers found popularity and verification badges don't predict security. Dominion is the continuous layer: we baseline your server's tool manifest, re-verify it every ~20 minutes, alert you the moment anything drifts, and sign the attestation trail your compliance review needs. Honest by design: servers without runtime data show as unrated , never a fake score. # In your CI pipeline, before an MCP server is approved: score=$(curl -s…from dominionobservatory.com

• 
  Apideck MCP ServerMay 2026 · apideck.com · ▲178

  Give AI agents access to real-time data across 200+ apps

• 
  Trust Protocols for Anthropic/OpenAI/GeminiFeb 2026 · mnemom.ai · ▲40

  Much of my work right now involves complex, long-running, multi-agentic teams of agents. I kept running into the same problem: “How do I keep these guys in line?” Rules weren’t cutting it, and we needed a scalable, agentic-native STANDARD I could count on. There wasn’t one. So I built one. Here are two open-source protocols that extend A2A, granting AI agents behavioral contracts and runtime integrity monitoring: - Agent Alignment Protocol (AAP): What an agent can do / has done. - Agent Integrity Protocol (AIP): What an agent is thinking about doing / is allowed to do. The problem:…

• 
  Risk Analysis Database of Every MCP ServerFeb 2026 · mcp.armor1.ai · ▲22

  Hi HN, We’re building security tooling around agentic AI systems. Today, we're releasing our public MCP catalog with detailed risk analysis for every MCP server we've found on the internet: https://mcp.armor1.ai/mcp-directory We all love agents and the power that MCPs unlock: suddenly your AI assistant can query databases, manage files, call APIs, and interact with the real world. But when we started adopting MCPs ourselves, we kept running into the same nagging questions: Is this MCP safe? Where is my data actually going? Could it execute destructive actions? Is it…

• 
  MCPSafeFeb 2026 · mcpsafe.org · ▲6

  We've been scanning MCP (Model Context Protocol) servers to understand the security posture of the ecosystem. After 306 servers and 1,211 vulnerabilities, here's what we found: - 69 critical vulnerabilities - 32 servers using eval() on untrusted input - 31 SQL injection vulnerabilities - 32 servers with hardcoded API credentials 10.5% of servers have at least one critical vulnerability. MCP servers run with your permissions. AI agents trust them implicitly. A prompt injection can exploit them remotely. MCPSafe (https://mcpsafe.org) lets you scan before you connect. Free tier…

• 
  CraftedTrustMar 2026 · mcp.craftedtrust.com

  Independent trust scores for MCP servers and AI agent tools

• 
  Is Your MCP Ready?Jun 2026 · isyourmcpready.com · ▲10

  Scan any MCP server against emerging agent-readiness standards. A score across five dimensions plus a copy-paste fix for every gap. Free, no sign-up.

• 
  Spira Maxima▲578

  Video model that turns script into viral social media videos

  AI · 17d ago · spira.ai

• 
  Rill Browser▲540

  The browser where Claude Code and Codex work beside you

  AI · 17d ago · rill.love

• 
  Germany's new sovereign AI model Kolibri▲424

  Kolibri is Aleph Alpha

  AI · 19d ago · tej.as

• 
  Giving Opus 5.5 a simulated paint canvas▲392

  Paintings by AI models: programs run through a simulation of oil paint.

  AI · 20d ago · stillwet.art

• 
  PixVerse R2▲381

  A real-time world model you can explore and change

  AI · 29d ago · world.pixverse.video

• 
  Hemory▲381

  Keep listening. Searchable memory for your AI agents.

  AI · 30d ago · hemory.com

• 
  Brew ▲900

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲896

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲806

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲795

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• 
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• 
  Files.md – Open-source alternative to Obsidian▲730

  🌱 Private, quiet space for thinking. Simple app for .md files. - zakirullin/files.md

  Dev tools · May 2026 · github.com