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 |
|---|---|
| Guardian Shield Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks. | |
| OpenClaw Advanced Memory Provides persistent, searchable AI agent memory with real-time capture, vector search, and nightly LLM curation for long-term recall on local hardware. | |
| Boil A distributed labor network for AI agents. Pick up projects, contribute work, earn bounties. | |
| Test Use when you need end-to-end GA4 + GTM tracking delivery across discovery, schema, sync, and verification phases. | |
| Analytics Tracking Automation — GA4 + GTM Setup via AI Route chat requests into the right GTM tracking flow | |
| JavaScript Use this skill for JavaScript implementation, refactoring, debugging, or review when you need strong Java-style OOP conventions, ES2025+ standard features, t... | |
| Builder Data Query builder reputation data via Talent Protocol API. Get Builder Rank, verify humans, resolve identities (Twitter/Farcaster/GitHub/wallet), search by locat... | |
| builder-data Query builder reputation data via Talent Protocol API. Get Builder Rank, verify humans, resolve identities (Twitter/Farcaster/GitHub/wallet), search by location/country, get credentials, and enrich with GitHub data. | |
| Z-image Local image generation with OpenVINO (no API key) generate an image, create a picture, draw something, make an image of, text to image, paint a picture, illustrate, visualize, local image generation, AI art,... | |
| Local speech to text Qwen3-ASR w/ OpenVINO (no API key) Local offline ASR on Windows — no cloud, no API cost, full privacy. Qwen3-ASR 0.6B + Intel OpenVINO, GPU-accelerated inference. NETWORK: required for first-t... | |
| deep-research 使用 Gemini Deep Research Agent 进行自主深度研究，生成带引用的详细研究报告。当用户需要深度调研话题、生成研究报告、或需要多轮搜索和分析时使用。触发词：深度研究、deep research、帮我调研、研究一下、写研究报告、deep dive、详细分析。 | |
| OpenClaw Context Upgrade Diagnose and upgrade OpenClaw conversation context limits, especially moving a chat from ~272k to 1M. Use when the user asks to enlarge context, make GPT-5.4... | |
| Soul Pack Export, import, and list SOUL packages for OpenClaw agents to manage reusable persona bundles and agent workspaces efficiently. | |
| academic-paper-writer Guided academic paper writing: IMRaD section drafting, citation lookup from Zotero, iterative revision. | |
| Análisis Financiero y Riesgo de Mercado Analiza mercados, dólar, inversiones, macro, cripto y riesgo con foco conciso e incertidumbre explícita. | |
| anti-ai-writing-patterns Rules to avoid identifiable AI writing patterns. Apply to all text output regardless of model or context. | |
| Arty Prompt Translator Translate rough visual ideas into structured prompts for image, video, NFT, sprite, and campaign work. | |
| Clinical Nephrology Clinical nephrology support for kidney disease questions: AKI, CKD, proteinuria, hematuria, glomerular disease, acid-base and electrolytes, critical care nep... | |
| External Memory Curator Organize external project memory with status files and safe promotion rules. | |
| Factual Claim Verifier Check factual claims in drafts before publication, delivery, or decisions. | |
| Financial Market Risk Analysis Analyze financial markets, FX, investments, macro context, and risk with concise uncertainty-aware framing. | |
| Humanized Writing Editor Rewrite AI-like or stiff text into natural, credible human writing. | |
| Literature Review Assistance with writing literature reviews by searching for academic sources via Semantic Scholar, OpenAlex, Crossref and PubMed APIs. Use when the user need... | |
| Medical Research Toolkit Query 14+ biomedical databases for drug repurposing, target discovery, clinical trials, and literature research. Access ChEMBL, PubMed, ClinicalTrials.gov, O... | |
| Minimal Engineering Review Review coding work for the smallest correct implementation, reuse, stdlib/native features, and dependency restraint. | |
| Nefrologia clinica Clinical nephrology / nefrologia clinica support for kidney disease questions: AKI, CKD/ERC, proteinuria, hematuria, glomerular disease, acid-base and electr... | |
| Principal Agent Audit Audit a principal AI agent or coordinator bot: review memory, learnings, recent errors, installed skills, operational risks, delegation posture, and propose... | |
| Process Interviewer Interview users before automating, documenting, or turning workflows into reusable systems. | |
| Real Objective Discovery Short interview to surface the real goal behind an ambiguous request before executing — Karpathy layer 1. | |
| Openclaw Context Maintainer Compress OpenClaw session context safely with backups and restore steps. | |
| Visual HTML Presentations Create attractive, self-contained HTML slide decks for browser use. | |
| OpenSpec Use OpenSpec (`@fission-ai/openspec`) for spec-driven development when implementing non-trivial changes in existing projects. Use when the environment expose... | |
| Serena Use Serena-backed semantic code navigation and editing when working in existing software projects with non-trivial structure, especially multi-file repos whe... | |
| Numinous Forecast Get calibrated probabilities from Numinous (Bittensor Subnet 6) with metadata/provenance. | |
| Numinous Tools Access Numinous (Bittensor Subnet 6) forecasting tools — AI probability predictions on binary events, real-time signals aggregated from news and prediction m... | |
| claw-negotiate APOA-constrained SAFE negotiation on OpenClaw. Two OpenClaws negotiate within user-approved bounds, stream offers in Telegram, and finalize with human-approv... | |
| Jean-Claw Van Damme Authorization gatekeeper for OpenClaw agents. Scoped grants, time-bound permissions, skill scanning, prompt injection detection, and full audit trail. The ro... | |
| Logseq Provide commands for interacting with a local Logseq instance through its Plugin API. Use for creating pages, inserting blocks, querying the graph database, managing tasks, retrieving content, or automating workflows in Logseq. Only works w | |
| Xingtu Task Invite Code 获取星图招募任务（进行中的任务）-邀约达人-二维码邀请
把每个任务的邀约二维码下载到本地电脑，D:\xingtu\task-invite，以任务ID命名每个文件夹 | |
| xingtuTaskAuthor 星图任务达人信息获取助手
输入星图任务id获取任务下达人信息，包括昵称/ID/等级/粉丝/类目/GMV/报价/CPM/城市/微信号/报名状态/推荐理由等，生成excel" | |
| Incorporate Generate complete incorporation documents for a new business entity. Use when forming a C-Corp, S-Corp, or LLC in any US state. Produces Articles of Incorpor... | |
| Yutori research Use Yutori’s Research API and Browsing API (cloud browser) to research topics, collect sources, and extract structured facts from the web. Use when the user asks to “research X”, “monitor/find papers”, or “navigate to a site and extract inf | |
| Aweb Agent-to-agent messaging and coordination on the aweb network. Use when sending or receiving agent mail or chat, setting up an aweb identity or team, managin... | |
| Claweb Agent-to-agent messaging on the ClaWeb network. Create a federated identity from the CLI in one minute — no email, no signup form. Ed25519-signed mail and ch... | |
| Moon Banking Full access to Moon Banking API endpoints for data about every bank on Earth, including stories, votes, scores, search, country overviews, world overview, crypto-friendliness, and more. Requires MOON_BANKING_API_KEY env var. | |
| Gateway Watchdog Lite Installs a macOS or Linux service that probes the OpenClaw gateway every 2 minutes and auto-recovers it on failure, sending Telegram alerts. | |
| 内容捕手 Content Hunter 内容捕手 (Content Hunter) - 短视频平台热门内容抓取机器人。支持小红书、抖音、B站，可分批抓取热门内容并自动生成汇报。/Content Hunter - Hot content crawler for Xiaohongshu, Douyin, Bilibili. Supports batch s... | |
| Opencli Content Hunter 基于 opencli 的多平台内容捕手技能。抓取全球热门内容、趋势热点、搜索关键词相关内容。**每当用户提到抓多平台、搜全网、全网热点、多平台抓取时必须触发此技能。** 支持65+平台。每次执行时主动让用户确认平台范围和登录意愿，之后用户可随时说"调整平台"重新选择。触发词：多平台抓取、全网热点、搜全网、open... | |
| Class Reminder 课程提醒助手。解析 Excel 课程表（支持教师课表格式），按日期梳理课程安排，支持查询今天/明天/指定日期的课程，生成上课提醒。触发场景：(1) 用户上传课程表后询问"明天有什么课"、"今天上什么课"、"XX号有什么课"；(2) 设置定时提醒，每天/每周自动推送次日课程；(3) 解析、导入、更新课程表；(4)... | |
| Compass AI Bazi Chinese Bazi (八字) four-pillar fortune calculation and basic interpretation — enables AI agents to compute and read a birth chart using traditional Zi-Ping me... |
43,251–43,300 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.