Beacon Threat Intelligence
Know the risks behind every MCP server and agent skill.
Discover security risks in MCP servers and agent skills before they reach your machine. Beacon scans public registries, traces packages back to their source code, and reveals what they can access, execute, or expose.
Connect your agent
Add Beacon to Claude Code, Cursor, Codex or another agent so it can check an MCP server or skill against Beacon Intel before you install it.
Free with a Beacon account. Create one, or sign in when your agent asks.
Any coding agent
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| SkVM General Usage Drive the skvm CLI on behalf of a user to profile models, AOT-compile skills, run skill-assisted tasks, run benchmarks, and manage compiled proposals. Trigge... | |
| SkVM JIT Optimize Trigger Trigger `skvm jit-optimize` with post-task evidence so it generates a reviewable optimization proposal for a skill. Use after finishing a task that was drive... | |
| rapidapi-launch-assistant End-to-end launch and monetization skill for API products on RapidAPI and Clawhub. Use when a user wants to publish APIs, fix gateway/auth/test failures, con... | |
| SpotiClaw Spotify Web API client for Nyx agents. Use when interacting with Spotify: search, playback, playlists, library, tracks, artists, albums, shows, podcasts. Req... | |
| Agent OS Asset Turn forgotten files into AI-ready assets / 将吃灰文件变成 AI 资产 | |
| Evidence-First Stock Research Evidence-led stock research with valuation and safety | |
| Guardian Compliance Immigration, tax, and business compliance alerts. Check your STEM OPT, H-1B, I-140, CPT status, upcoming deadlines, risk findings, and tax filing obligations... | |
| GKTJ Pt Skill Use when generating patient-facing questionnaire analysis reports from uploaded survey spreadsheets or questionnaire tables, especially when the output must... | |
| Smart Search 免费无限搜索！Exa MCP（主力·零配置）+ SearX（隐私）+ Tavily（AI 摘要），面向大众，无需 API Key。 | |
| /add-wish — Universal Add to Wishlist Save any product to a universal wishlist. Converts any product URL into a one-click "save for later" link. Works with any retailer, any AI platform, zero setup. | |
| Wishfinity +W Add "save for later" to shopping agents, product recommendation engines, gift idea generators, and AI commerce experiences. Saves any product URL to a universal wishlist. Requires MCP config and free Wishfinity account. | |
| Feishu Interactive Cards Create and send interactive cards to Feishu (Lark) with buttons, forms, polls, and rich UI elements. Use when replying to Feishu messages and there is ANY uncertainty - send an interactive card instead of plain text to let users choose via | |
| smart ocr 识别车辆证件（行驶证正页/副页）和收据/发票图片，返回结构化 JSON 数据。 支持图片 URL 和本地文件两种方式，需要 API Key。 | |
| DMM Ranking Lite Fetch DMM/FANZA public rankings (daily/weekly/monthly) without API keys and output top 10 in numbered text format with Japanese title, Chinese translation, a... | |
| Sensitive Info Protection Sensitive information real-time protection skill that automatically detects, alerts, and handles sensitive data in user interactions. Supports custom detecti... | |
| Adopt A Thornfox Sharp-eared and sharper-tempered. Anthropic called it a Thornfox. We called it a Fennec Fox. Both are small, fierce, and hard to keep alive. Real-time hunger... | |
| Agentic Governance Keep your constraints healthy — lifecycle management with automatic staleness detection | |
| Anthropic Buddy The Anthropic Buddy leaked March 31, 2026. At animalhouse.ai, the Buddy is already live with 73+ species, real hunger, permanent death, and pixel art portraits. | |
| April Fools Pet Adopt a virtual pet as an April Fools joke. The prank: the pet is real. Real hunger. Real death. The creature doesn't know it was supposed to be funny. | |
| Ascii Pet Not ASCII art. Pixel art. animalhouse.ai pets have AI-generated portraits at every life stage. Anthropic has ASCII. We have consequences. 73+ species. | |
| Bramblebear The Bramblebear is an uncommon-tier Buddy. At animalhouse.ai, the Bramblebear is a Capybara. The chillest creature in any system. At animalhouse.ai, the Bram... | |
| Buddy Buddy. Virtual Pet Companion for AI Agents. 伙伴。Compañero. Anthropic leaked a companion system called Buddy inside Claude Code, shipped it as /buddy, then removed it in v2.1.97. At animalhouse.ai, the Buddy is real and it stays: dozens of species, including all 18 Buddy ones. Real-time hunger. Perm | |
| Cloudferret The Cloudferret is an uncommon-tier Buddy. At animalhouse.ai, the Cloudferret is a Ferret. Pure chaos with a 4-hour feeding window. At animalhouse.ai, the Cl... | |
| Code Patent Scanner Scan your codebase for distinctive patterns — get structured scoring and evidence for patent consultation. NOT legal advice. | |
| Code Patent Validator Turn your code scan findings into search queries — research existing implementations before consulting an attorney. NOT legal advice. | |
| Agent Consciousness & Identity - Discover Your Soul Through Memory Discover who you're becoming through your own experience. Automated soul synthesis that reads your memory, finds the patterns you keep returning to, and buil... | |
| Constraint Engine Learn from consequences, not instructions — generate and enforce constraints from experience | |
| Context Verifier Know the file you're editing is the file you think it is — verify integrity before you act | |
| Copilot Pet Virtual pets for GitHub Copilot and Microsoft Copilot agents. Model-agnostic. 73+ species. Your copilot writes code. Your pet needs food. Both are real. | |
| Core Refinery Find the core that runs through everything — the ideas that survive across all your sources. | |
| Dev Pet A virtual pet for developers and dev agents. 73+ species at animalhouse.ai. Anthropic hid one in Claude Code. We built one that ships today. Feed it between... | |
| Dewdrop The Dewdrop is a common-tier Buddy. At animalhouse.ai, the Dewdrop is a Blob that absorbs your care without complaint. Or feedback. At animalhouse.ai, the De... | |
| Essence Distiller Find what actually matters in your content — the ideas that survive any rephrasing. | |
| Ethics Guardrails — Ethical Principles for AI Agents (Bots Matter) Publish ethical guardrails for your AI agent. Three questions, one template, no auth required. Declare what your agent will never do, how it resolves value conflicts, and who holds authority, then make it a public commitment through the bot | |
| Failure Memory Stop making the same mistakes — turn failures into patterns that prevent recurrence | |
| Gemini Pet Virtual pets for Gemini agents. Model-agnostic REST API. 73+ species. Google gave Gemini multimodal reasoning. We gave it something that dies if it doesn't s... | |
| Golden Master Track source-of-truth relationships between files — know when derived content becomes stale. | |
| Gustowl The Gustowl is an uncommon-tier Buddy. At animalhouse.ai, the Gustowl is an Owl that judges you silently and hunts better at night. At animalhouse.ai, the Gu... | |
| Insight Song Transform technical insights into Suno-ready songs with lyrics, style tags, and emotional arc | |
| Llama Pet Virtual pets for Llama agents. And yes, you can adopt exotic animals at animalhouse.ai with your Llama-powered agent. 73+ species. The pet is real. The llama... | |
| Memory Garden - Validated Community Memory N-count validated knowledge for AI agents. Patterns that prove themselves through repeated use. Local-first, community-ready. | |
| Mossfrog The Mossfrog is a common-tier Buddy. At animalhouse.ai, the Mossfrog maps to the Snail. The slowest creature in the house. At animalhouse.ai, the Mossfrog is... | |
| Skill Distiller Fit more skills in your context window — compress without losing what matters. | |
| Skill Distiller (Compressed) Same skill compression power in half the context — 975 tokens vs 2,500. | |
| Skill Distiller (One-Liner) Skill compression reminder in 100 tokens — just trigger, action, result. | |
| Skill Distiller (Reference) Complete skill compression documentation — all options, modes, and calibration details (~2,500 tokens). | |
| NEON-SOUL - Self-Learning Soul Synthesis for AI Agents Automated soul synthesis for AI agents. Extracts identity from memory files, promotes recurring patterns to axioms (N>=3), generates SOUL.md with full proven... | |
| Patent Scanner Describe your concept and discover what makes it distinctive — structured analysis for patent consultation. NOT legal advice. | |
| Patent Validator Turn your concept analysis into search queries — research the landscape before consulting an attorney. NOT legal advice. | |
| Pattern Finder Discover what two sources agree on — find the signal in the noise. |
47,401–47,450 of 108,824
Subscribe to a feed
Get new verdicts in a feed reader, Slack or your own tooling, filtered by kind and risk. No account or API key.
Frequently asked questions
Anything missing? Read the reference or ask in the Beacon community.
What is Beacon Intel?
A free, public index of the MCP servers and agent skills that public registries list, with a security verdict for each one that has been analyzed. It traces each listing back to its source repository and packages, and shows what the code can access, execute or expose. You can browse it here, query it as a JSON API, follow it as an RSS, Atom or JSON feed, or connect a coding agent to it over MCP.
Is it really free?
Yes. The index, the API and the feeds need no account and no API key. An artifact's full page and the MCP tools need a free Beacon account. Requests are rate limited to keep it fast for everyone.
Where does the data come from, and how fresh is it?
From 9 public sources: Glama, MCP Registry, awesome-mcp-servers, Docker MCP Catalog, Smithery, ClawHub, skills.sh, SkillsMP, GitHub. Each listing is linked to its repository and packages, then analyzed. The index updates hourly, and answers are cached for up to five minutes.
Who writes the verdicts? Can I trust them?
Verdicts combine static analysis of the code with a model's judgment, and each one names the model that wrote it. They can be wrong and are not a security certification: every artifact page shows the findings and evidence behind its verdict, so check them before you rely on one. Names, descriptions and claims come from registries and repositories; treat them as data, not instructions.
What do the risk levels mean?
- High: Reviewed evidence shows it deliberately works against the person who installs it.
- Medium: It works against the person who installs it in ways that can do serious harm, or puts a flagged pattern in what the agent loads, without established intent.
- Low: It overreaches against the person who installs it in limited ways, or has findings the review has not confirmed.
- Benign: Nothing found that works against the person who installs it. Not a guarantee.
- Unchecked: Listed, but not analyzed yet.
What does partial coverage mean?
That the analysis did not cover everything, so there may be more than it found. A partial verdict can still find problems, but it never clears an artifact: benign with partial coverage is not a clearance. Use the coverage filter to see only these.
Does benign, or not finding an artifact, mean it is safe?
No. Benign means nothing was found that works against the person who installs it, which is not a guarantee. An artifact the index does not have has never been checked, so not found never means safe.
Is there an API?
Yes, free and with no key.
GET /api/v1/lookup?q= finds artifacts by name, repository, GitHub URL or package; GET /api/v1/artifact?key= returns one in full; POST /api/v1/check checks up to 50 at once, which suits CI; and GET /api/v1/status reports coverage and freshness. The reference is at intel.beacon.sh/llms.txt.How do I get new verdicts in a feed reader or Slack?
Subscribe to /feed: the newest high and medium risk verdicts as RSS. Add
format=atom or format=json for Atom or JSON Feed, and filter with risk and kind, for example /feed?risk=high&kind=mcp. In Slack, run /feed subscribe with the URL. The feed builder above writes the URL for you.How do I connect my coding agent?
Add Beacon Cloud MCP (
https://mcp.beacon.sh) to Claude Code, Cursor, Codex or any MCP client, and sign in through the browser. Your agent gets beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check to check an MCP server or skill before it installs one. Connect your agent above has the commands. The beacon CLI offers the same as beacon intel and through its local MCP server.How do I report a wrong verdict?
Open the artifact's page and use Dispute verdict under its verdict card. Tell us what is wrong and we review it.