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 |
|---|---|
| Cb Crisis Communication Protocol Handle PR crises in any market with culturally-appropriate response protocols. Get press statements, social media responses, internal comms templates, and st... | |
| Cb Customer Journey Mapper Map complete customer journeys for any overseas market — with localized touchpoints, cultural buying triggers, and conversion barriers. Output a visual-ready... | |
| Cb Data Privacy Readiness Guide Get a practical, step-by-step privacy compliance checklist for any market — GDPR, CCPA, LGPD, PIPL, and more. Skip the legal jargon and get an actionable rea... | |
| Cb Global Content Strategy Build a localized content engine for any market — editorial calendars, SEO keyword maps, platform-native content templates, and translation-quality framework... | |
| Cb Go To Market Launch Playbook Launch in any overseas market with a complete GTM playbook — market assessment, channel strategy, launch timeline, pricing localization, and 90-day execution... | |
| Cb Influencer Marketing Playbook A practical framework for identifying, vetting, briefing, managing, and measuring creator partnerships across overseas markets. | |
| Cb Local Partnership Assessor Evaluate overseas distributors, agencies, resellers, and ecosystem partners in minutes. Get weighted scorecards, due-diligence checklists, commercial model c... | |
| Cb Overseas Talent Playbook Hire, onboard, and manage overseas talent in minutes. Get hiring sequences, role scorecards, interview rubrics, onboarding plans, and compliance checklists f... | |
| Cb Platform Selection Guide Choose the right ecommerce platform for any overseas market in minutes. Compare marketplaces, DTC, social commerce, and wholesale channels by margin, categor... | |
| Cb Pricing Psychology Advisor Publish Adapt pricing psychology for any overseas market in minutes. Get market price-perception audits, culturally appropriate discount frames, trust signals, and t... | |
| Cb Product Market Fit Validator Validate product demand in any foreign market before investing in localization, hiring, or launch. Get assumption maps, low-cost experiments, evidence scorec... | |
| Cb Seo Sem Strategy Plan search marketing for any international market in minutes. Get regional search ecosystem maps, intent-based keyword localization, multilingual SEO archit... | |
| Cb Social Channel Matrix Choose and operate the right social media channels for any overseas market in minutes. Get market-channel fit scores, audience behavior maps, content cadence... | |
| Cb User Persona Builder Build foreign-market user personas that go beyond demographics in minutes. Get multi-dimensional persona cards, cultural value overlays, jobs-to-be-done maps... | |
| ChangeBrief Change intelligence skill that compares previous and current knowledge snapshots, surfaces what was newly added, which claims changed, what conclusions are n... | |
| Changelog Weaver Generate polished changelogs and release notes from git history, PRs, and issues — auto-categorize features, fixes, and breaking changes | |
| Chat Memory Archiver Extract decisions, todos, knowledge, preferences, and risks from AI chat sessions into structured memory | |
| Cheap Find the cheapest meaningful visible price for a product across major Chinese shopping platforms | |
| China Claw Research and introduce China-based alternatives, counterparts, or "平替" products to OpenClaw, organized by company and product positioning. Use when the user... | |
| China Commerce Copilot Route shopping and ordering requests to the right China commerce skill, then frame the decision in the most useful way. Use when the user asks where to buy s... | |
| China Local Life Assistant China local-life flagship assistant. Input food delivery, restaurant, ride, hotel, flight, train, or local service needs; compare Meituan, Eleme, Dianping, D... | |
| China Shopping Recommend suitable Chinese shopping platforms for a user-provided product type, product name, or shopping need. Use when the user asks where to buy something... | |
| China Shopping Assistant China shopping flagship assistant. Input a product name or link; compare JD, Taobao, Tmall, PDD, Vipshop, SHEIN, and related shopping options by visible pric... | |
| Claim Evidence Timeline Builder Build a clear chronological timeline and proof index from user-provided events and evidence. Use when the user needs to explain what happened with supporting... | |
| clause redraft Redraft unclear or risky contract clauses into clearer, more balanced language. Use when the user asks about 条款改写、改合同、条款优化、合同措辞、改写这句话、条款润色, or wants to impro... | |
| ClawHub Publisher Stats Fetch live ClawHub publisher metrics for a specific user, including published skills, author rank, total downloads, stars, current installs, all-time install... | |
| Clawhub Skill Monitor Query public skills published by a ClawHub user from the real public API. Returns skill list, versions, timestamps, and metadata. Does not fabricate installs... | |
| Clawpilot Clawpilot is your skill installation advisor. It analyzes task intent, recommends suitable skills, compares tradeoffs, explains risk, and suggests an install... | |
| Closet Seasonal Swap Checklist Create a calm seasonal closet swap checklist for rotating clothes, shoes, accessories, storage bins, repairs, weather readiness, and reset tasks without dona... | |
| CN Contract Audit Review Chinese contracts for risky clauses — labor lease purchase NDA. Built-in 20+ rule sets. | |
| CN Contract Review Review Chinese contracts for risky clauses — labor lease purchase NDA. Built-in 20+ rule sets. | |
| China E-Commerce Shopping Guide China E-Commerce Shopping Guide - Focused on recommending mainstream Chinese e-commerce platforms such as Taobao, Tmall, JD.com, and Pinduoduo. Based on prod... | |
| Co Op Mission Planner Turn a shared task into a co-op mission with clear roles, handoff points, sync rhythm, fallback coverage, and low-conflict alignment language. Use when two o... | |
| Code Review Checklist 代码审查清单 - A comprehensive code review checklist and guidance tool. Use when user asks about 代码审查、代码检查、PR review、代码质量, or wants to conduct or prepare for a cod... | |
| Codebase Radar Scan codebase for dependency graph, tech debt hotspots, and module health scores | |
| Cognitive Reframe Helps users identify negative thinking patterns and try seeing situations from a more balanced perspective. A CBT-based thought exercise tool for daily self-... | |
| Cold Flu Home Recovery Log Create a short-term home recovery log for a cold, flu, or similar illness, including symptom timeline, temperature entries, hydration and rest notes, user-en... | |
| Color Sense Generate usable color systems for creative and design work. Use when the user asks for a palette, color direction, visual mood through color, brand/UI/poster... | |
| Commerce Bi Copilot Turn ecommerce exports, KPI notes, and natural-language business questions into metric alignment notes, anomaly diagnoses, operator-ready summaries, and prio... | |
| Competitor Watchtower Build a lightweight competitor monitoring brief across DTC sites, marketplaces, social channels, and promo surfaces. Use when a team needs pricing or promo s... | |
| complaint draft Generate civil complaint document frameworks based on case facts. Use when the user asks about 起诉状、起诉书、怎么起诉、民事起诉、我要起诉、写诉状, or wants to draft a civil complain... | |
| Consumer Rights Generate complaint letters, 12315 filings, and escalation paths for consumer disputes in China. | |
| Commerce Content Generator Commerce content generator. Input a product brief, evidence, audience, and channel; output Xiaohongshu notes, Douyin scripts, ad/email/listing variants, and... | |
| Context Preserver 上下文保持器 - 自动快照、按需恢复、会话恢复、版本管理和上下文导出工具。conversation-recovery 已合并到本入口。 | |
| 知识账本 Evidence-first knowledge auditing skill that upgrades connected knowledge into an auditable conclusion card. It traces which sources support a conclusion, ma... | |
| Contract Clause Extractor Extract & classify key clauses from contract PDFs into a structured risk summary — with bilingual (CN/EN) support. | |
| Contract Review Ai Chinese contract risk intelligence — scan, annotate, and explain clauses in labor, rental, service, NDA, and 15+ other contract types under PRC law. | |
| Contract Risk Helper Contract risk helper. Input Chinese or English contract text; identify common risky clauses, classify severity, and suggest negotiation or revision points. B... | |
| Contract Risk Scan Redirect Redirect: contract-risk-scan has been merged into contract-risk-helper. Use contract-risk-helper for local contract risk scanning, common clause checks, seve... | |
| Conversation Recovery Redirect Redirect: conversation-recovery has been merged into context-preserver. Use context-preserver for session snapshots, recovery, task handoff, context export,... |
34,851–34,900 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.