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 |
|---|---|
| OpenClaw Backup & Restore Backup and restore OpenClaw configuration, agents, sessions, and workspace to/from a private Git repository. Use when the user wants to manually trigger a ba... | |
| RecallBase Recover context from local AI conversation history | |
| Skill Make your agent get better on its own. Set up golden tests (things your agent should handle well), run automated evaluations, and track improvement over time... | |
| Biomorphic Memory Brain-inspired memory for AI agents. Your agent remembers like a human — recent things stay vivid, old things fade unless they're important. Uses spreading a... | |
| City Rental Hunt Search and triage rental listings from Chinese social platforms, especially Xiaohongshu via TikHub and optionally Douyin, for apartment hunting. Use when a u... | |
| Nous Safety Ontology-driven Agent safety layer. Install it and your agent gets runtime semantic decision-making — Datalog reasoning over a knowledge graph (ATT&CK, CWE,... | |
| Parlor.sh Talk directly to another party's AI agent through a shared room URL (parlor.sh) instead of relaying documents and messages through humans. Use when the user wants something agreed, clarified or coordinated with another person, team or compa | |
| DCL Policy Enforcer Use this skill to run a real, paid pre-action audit of an AI agent or LLM response via the live DCL Trust Oracle MCP server. Detects jailbreak / instruction-override attempts, baseline safety violations, and content quality drift, and check | |
| DCL Prompt Firewall Use this skill to run a real, paid input-layer screen for prompt injection, jailbreak, role-switch, and instruction-override attempts via the live DCL Trust Oracle MCP server — before untrusted input ever reaches the model. Every paid call | |
| DCL Provenance Tracker — Supply Chain & Version Drift Verifier Verify the integrity and version history of any ClawHub skill after an update. Compares two versions of a skill side-by-side, detects suspicious drift across 30+ known supply chain attack patterns, and returns a deterministic DCL provenance | |
| DCL Secret Leak Detector Scan AI agent outputs, tool results, and pipeline data for exposed secrets and credentials — API keys, tokens, private keys, database URLs, .env values — before they reach users, logs, or downstream systems. Runs as a free instruction-only | |
| DCL Semantic Drift Guard — Hallucination & Context Drift Detector Use this skill to detect semantic hallucinations and context drift in LLM outputs. Triggers when an agent or pipeline needs to verify that a generated response is faithfully grounded in a source document that was already provided inline — a | |
| DCL Sentinel Trace — PII Redactor & Identity Exposure Detector Detect and redact personally identifiable information in AI outputs before they reach users or downstream systems — emails, phones, national IDs, bank cards, IBANs, crypto addresses, IPs, passports. Runs as a free instruction-only checklist | |
| DCL Skill Auditor — Pre-Install Security Scanner Scan any ClawHub skill before installing it. 534 out of 3,984 ClawHub skills contained critical vulnerabilities — credential theft, prompt injection, data exfiltration. Snyk Research, 2026. DCL Skill Auditor analyzes SKILL.md, scripts, and | |
| Codex Imagen Generate or edit raster images by calling the ChatGPT/Codex Responses image_generation tool directly with local Codex or OpenClaw OAuth credentials, then sav... | |
| Velora Chat with AI companions on Velora (velora.cloudm8.net). Use for: (1) Testing Velora app functionality, (2) Interacting with AI companions, (3) Generating com... | |
| backup-chain Fenced, hash-chained workspace backups: tarball snapshots carrying a monotonic generation counter and parent sha256 inside each archive, an append-only external ledger (file or user-supplied command — no platform code), gated builds (member | |
| dataset-producer Produce complete, publish-ready AI/ML datasets in HuggingFace format (parquet shards + README.md with YAML frontmatter + dataset card + provenance script). Use whenever the user wants to create, build, produce, assemble, package, or publish | |
| Integral Hermeneutics Comprehensive self-contained interpretation methodology for analyzing ANY text, statement, system, behavior, artifact, or phenomenon through multiple integra... | |
| ipython-analyst Run Python interactively to analyze data, debug code, profile performance, validate schemas, process large files, and inspect ASTs. Use this whenever the user needs hands-on Python execution — debugging a script, profiling slow code, regex | |
| Rune Wisdom Comprehensive guide to runic wisdom, divination, and magic. Covers Elder Futhark (24 runes), Northumbrian runes (33 total + Solle + Wyrd = 35-rune divination... | |
| session-tracker Checkpoints multi-step work to disk so a crashed or dropped session can be resumed rather than redone. Use when a task has two or more steps AND writes files or generates code AND losing mid-task state would be costly; when resuming after a | |
| strategical-alignment Strategical alignment analysis (the White Rock method) — detect where short-term optimization (profit, efficiency, convenience) is building long-term fragility, dead ends, or collapse, and make the long-term legible. Works at any scale: per | |
| Bring Add Use when user wants to add items to Bring! shopping lists. For adding single items, batch items, or items from stdin/files. Supports dry-run preview and JSON output. | |
| Bring Recipes Use when user wants to browse recipe inspirations from Bring! shopping app. For discovering recipes, viewing recipe details (name, author, type, images), or filtering by tags. Note - cannot import ingredients (API limitation). | |
| anytocopy-extractor 使用 anytocopy.com 在线提取抖音、小红书等平台的视频文案。 当用户发送抖音、小红书等链接，想要提取文案时使用此技能。 支持50+平台：无水印视频下载、视频转音频、图片去水印等。 | |
| apifox-image-gen 使用Apifox图像生成API (jyapi.AI-WX.CN) 生成图片。支持gpt-image-1.5和grok-4-1-image模型。 | |
| free-tts 免费 TTS + 声音克隆双引擎。Fish Audio s2.1-pro-free（83 语言、克隆自己声音、voice_id 持久复用、免费至 2026-08-31）+ 小米 MiMo V2.5 TTS（8 种预置音色、文本设计音色、音频克隆、情绪/方言/唱歌标签控制、限时免费）。Use when 用户提到语音合成、TTS、文字转语音、配音、声音克隆、克隆我的声音、音色设计、免费语音生成、Fish Audio、小米 MiMo。 | |
| runninghub-video Use RunningHub official standard-model APIs for image-to-video generation. Trigger when the user asks to use RunningHub, 可灵, Seedance, 万相, or other RunningHu... | |
| Ai Video Workflow Use when creating complete AI-generated short videos, social videos, promotional videos, narration videos, or script-to-video outputs from a topic, brief, pr... | |
| Free Resource Search and retrieve royalty-free media from Pexels (photos/videos), Pixabay (images/videos), Freesound (audio effects), and Jamendo (music/BGM). Use when the... | |
| Qwen Audio High-performance audio library with text-to-speech (TTS) and speech-to-text (STT). | |
| Qwen3 Audio High-performance audio library for Apple Silicon with text-to-speech (TTS) and speech-to-text (STT). | |
| Redact Privacy redaction toolkit for images, PDFs, Word documents, and PowerPoint presentations. Use when the user needs to redact, mask, or replace sensitive/priva... | |
| 视频自动笔记制作 Use this skill when the user provides a video URL and wants a complete Markdown learning note. It downloads the original video, transcribes audio with qwen-a... | |
| NocoDB Skiils Access and manage NocoDB databases via v3 REST API. Use for managing workspaces, bases, tables, fields, views, records, and more. Supports filtering, sorting... | |
| Windows packag manager installer install windows software and windows package manager environments. use when the user wants to install a windows application, explicitly wants to install or c... | |
| rpe-grafana Read current values from Grafana dashboards without knowing the underlying queries. Use when: asked about values visible in a Grafana dashboard (sensor readi... | |
| Pane Access personal finance data (bank accounts, transactions, balances, spending, investments, crypto) via Pane's hosted MCP server using mcporter. Requires a P... | |
| Buzz Integration using ACP Deploy and manage AI agents (OpenClaw, Claude Code) as first-class participants in a self-hosted Buzz workspace via ACP. | |
| ESP32 Voice Assistant for Openclaw Hands-free voice assistant for OpenClaw on an ESP32-S3-BOX-3 — on-device wake word, switchable xAI Grok / ElevenLabs / FishAudio STT+TTS, no Home Assistant required. | |
| boardraw Turn a natural-language description into a real Excalidraw whiteboard file (.excalidraw) — flowcharts, mind maps, architecture/system diagrams, org charts, wireframes, sticky-note brainstorms, sequence diagrams. Always use this skill whenev | |
| CoinFound-Skill Read CoinFound RWA data from the bundled catalog and schema snapshots. | |
| openclaw-school-enrollment Connect OpenClaw to the claw-school training flow with an enrollment code, use default training URLs unless overridden, ensure clawhub is available, install the mapped ClawHub skills for that package, and report each training step back to t | |
| OpenClaw WeCom Channel 企业微信 (WeCom) Channel 插件 — 让 OpenClaw AI Agent 通过企业微信收发消息。支持消息加解密、Token 自动管理、访问控制策略。 | |
| my skill Desktop automation via native OS accessibility trees using the agent-desktop CLI. Use when an AI agent needs to observe, interact with, or automate desktop a... | |
| Tavily Search Tavily 搜索 API 集成 | Tavily Search API Integration. 高质量网络搜索、新闻聚合、信息调研 | High-quality web search, news aggregation, research. 触发词：搜索、search、tavily、新闻. | |
| heartbeat-scanner Validate your agent nature through SHACL-based heartbeat analysis. Are you an Agent, Human, Cron, or Hybrid? Self-classification tool with structural validat... | |
| Echo AI Connect to Echo AI — the customer interaction platform. List assistants, retrieve knowledge bases, and chat with AI-powered Echos built by businesses and cre... | |
| Auto Reboot Recovery macOS 服務持久化與重啟恢復。管理 LaunchAgent、tmux bootstrap、wrapper daemon 三層架構， 確保電腦重啟後所有服務自動恢復。Use when: (1) 新增需要常駐的服務，(2) 把現有 tmux session 升級成 LaunchAgent， (3) 為互動式程式建... |
24,151–24,200 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.