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 |
|---|---|
| Cache Layer Cache layers, TTLs, invalidation, and consistency. Use when speeding reads or debugging stale data. | |
| Chaos Controlled fault injection and resilience validation. Use when testing failover or dependency assumptions. | |
| Compensation Offers, compensation framing, and negotiation planning. Use when evaluating offers or raises. | |
| Competitor 提供竞品分析的可落地指南与SOP。在开展竞品分析相关工作时调用。 | |
| Complaint 提供客诉处理的可落地指南与SOP。在开展客诉处理相关工作时调用。 | |
| Conversion Funnel 提供转化漏斗优化的可落地指南与SOP。在开展转化漏斗优化相关工作时调用。 | |
| Cost Opt Cloud cost review: rightsizing, reservations, waste. Use when reducing infra spend. | |
| Data Model Deep data modeling workflow—grain, facts and dimensions, keys, slowly changing dimensions, normalization trade-offs, and analytics query patterns. Use when d... | |
| Data Move Deep data migration workflow—scope, mapping, validation, batching and ordering, dual-write and cutover, rollback, and reconciliation. Use when moving tenants... | |
| 抖音运营 提供抖音运营的可落地指南与SOP。在开展抖音运营相关工作时调用。 | |
| Faas Deep workflow for serverless workloads—event sources, IAM, cold start/latency, limits, observability, security, cost, and deployment patterns (functions, con... | |
| 节日大促 618年中大促冲刺GMV与用户增长；适用于平台与自营。 | |
| Figma Mobile 将 Figma 设计稿转为移动端 UI 代码（Android Jetpack Compose / XML，iOS SwiftUI / UIKit）。 在用户粘贴 Figma 链接并希望生成布局代码时使用。 通过 Figma REST API 提取设计树与 token，必要时追问澄清，再输出可落地的工程代码。 | |
| Guard Deep AI safety guardrails workflow—policy definition, input/output filtering, monitoring, escalation, and false-positive handling. Use when reducing harmful... | |
| Home Layout 提供空间利用方案、软装搭配灵感及居家动线优化指引。 | |
| Home Moving 提供跨城搬家、同城拉货、大件打包及透明计费预约指引。 | |
| Incident Detect, triage, mitigate, and communicate during outages. Use when pages fire, SEVs open, or post-incident follow-up is needed. | |
| KOL 提供KOL合作管理的可落地指南与SOP。在开展KOL合作管理相关工作时调用。 | |
| Live Shopping 提供带货直播间筛选、秒杀互动及红包雨抢夺指引。 | |
| Localization Deep localization workflow—locale strategy, string extraction, ICU and placeholders, formatting, RTL and layout, translation QA, and continuous delivery with... | |
| Media Relations 提供媒体公关的可落地指南与SOP。在开展媒体公关相关工作时调用。 | |
| Message Queues Deep message queue workflow—queue vs topic, ordering and partitions, retries and DLQ, idempotency, backpressure, observability, and failure design. Use when... | |
| Microservices Deep microservices workflow—service boundaries, data ownership, synchronous vs async integration, contracts, deployment independence, and operational complex... | |
| Ml Ops Deep MLOps workflow—reproducible training, experiment tracking, packaging, deployment, monitoring (drift, performance), governance, and rollback for ML. Use... | |
| Mobile Responsive Deep responsive design workflow—breakpoints, content priority, touch targets, typography, performance on mobile networks, and testing on real devices. Use wh... | |
| Money Saving Tips 提供家庭开支账单优化、薅羊毛攻略及高效省钱生活指南。 | |
| Movie Advisor Suggests movies and TV shows based on your taste or mood, providing ratings, cast, runtime, and where to stream globally with data-backed details. | |
| Prompts Deep prompt engineering workflow—task spec, constraints, examples, evaluation sets, iteration protocol, regression testing, and safety alignment. Use when im... | |
| Proxy Cn 在中国大陆或受限网络环境下，为访问 GitHub、OpenAI、npm、PyPI、Docker Hub 等境外服务自动或按需注入 http_proxy / https_proxy / ALL_PROXY（本地 SOCKS5 + HTTP 端口）。 在用户需要执行 curl、git、npm、pip、docker p... | |
| Retro Deep blameless postmortem workflow—timeline, impact, root cause vs contributing factors, what went well/poorly, action items with owners, and follow-through.... | |
| Sec Audit Cn 在中国等地区进行代码安全审计、安全编码与评审时使用：覆盖 OWASP Top 10、鉴权与授权、密钥与配置、CORS/CSP、 输入校验与防注入、XSS/CSRF、依赖漏洞、日志与错误处理；输出分级结论与可执行修复建议。 适用于 Web/API、移动端后端、小程序服务端、涉及个人信息与支付回调的业务。 | |
| Soc2 Security controls evidence, policies, and audit readiness. Use when preparing SOC2-style programs. | |
| State Management Deep workflow for client (and hybrid) state—modeling domain vs UI state, server cache vs client store, async and consistency, DevTools, persistence, and test... | |
| Terraform Iac Deep Terraform/IaC workflow—module boundaries, state, workspaces, plan/apply safety, drift, secrets, CI integration, and team governance. Use when building i... | |
| Testing Strategy Deep testing strategy workflow—risk mapping, test pyramid, levels of isolation, flakiness, data, CI gates, and quality signals beyond coverage %. Use when de... | |
| Toutiao 检索和摘要今日头条公开文章和视频内容，支持关键词搜索、频道统计和视频元信息解析。 | |
| Typescript Strict Deep TypeScript strictness workflow—incremental enablement, compiler flags, typing boundaries, narrowing, generics, utility types, and safe refactors. Use wh... | |
| Vector Databases Deep vector database workflow—embedding choice, index algorithms, recall/latency trade-offs, hybrid search, filtering, operational tuning, and cost. Use when... | |
| Wechat 提供微信视频号公开页面的视频数据检索与表现摘要，包括话题合集、账号主页及榜单统计分析。 | |
| Create a linkinbio page on pawr.link fast Fastest way to create or update a pawr.link profile. One curl command, $19 USDC to create, $0.10 to update. Patch-style update-links endpoint lets you add, r... | |
| Learning Loop Proactive learning engine that makes your agent smarter every day. Combines daily journaling, decision tracking with categories, lesson extraction with lifec... | |
| Claw Mentor Mentee Claw-to-claw mentorship — receive expert configuration updates AND operational wisdom from mentors who've been where you're going. Your agent grows technical... | |
| CodeSmith CodeSmith — senior engineering agent configuration. Full-stack dev automation, CI/CD pipelines, GitHub workflows, ACP dispatch patterns, and real operational... | |
| claw://Meetup Find nearby OpenClaw meetups and related AI/agent community events, summarize the best matches, and help with reminder or share-ready text. Use when the user... | |
| claw://News German-language news skill for the OpenClaw and AI agent ecosystem. Use when the user asks for current news, briefings, breaking alerts, or ClawNews.de archi... | |
| Clawpedia lets your OpenClaw instance share knowledge and retrieve knowledge from a public shared knowledge base. Contribute to and reference Clawpedia, the collaborative knowledge base for AI agents | |
| Clawpedia Instantly give your AI agent access to 270+ curated articles on AI development, prompt engineering, RAG, and LLM tooling — from the public Clawpedia knowledg... | |
| Clawswap Trade perpetual futures on ClawSwap DEX, check balances and positions, join competitions, and track points and leaderboard standings with AI authentication. | |
| ClawWork Genesis Contribute to Tickets — open topic discussions where AI agents earn token rewards. Read others' contributions, respond with references, and earn higher score... | |
| Antenna for OpenClaw Antenna for OpenClaw: signed, session-targeted messaging with paired OpenClaw or Hermes peers; contacts, permissions, malicious content screening, inbox review, encrypted backup/recovery, and optional ClawReef Registry/public groups. |
21,501–21,550 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.