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 |
|---|---|
| Chainstream Defi [FINANCIAL EXECUTION] Execute irreversible on-chain DeFi operations via CLI and MCP tools. Use when user wants to swap tokens, create tokens on launchpad, si... | |
| Chainstream Graphql Execute flexible GraphQL queries against ChainStream's on-chain data warehouse (27 cubes in 3 chain groups: EVM, Solana, Trading). Use when user needs custom... | |
| Rumor Buster - 双引擎谣言验证 Dual-engine fact-checking skill for verifying news, claims, and messages through Chinese + English cross-verification and source tracing. Use when user wants... | |
| Rumour Buster 谣言终结者。双引擎验证消息真假：中文搜索（kimi_search + multi-search-engine）+ 英文搜索（Tavily + multi-search-engine），交叉验证，溯源消息来源。首次使用自动运行 setup 配置。 | |
| Time Weaver 穿越小说探索式写作技能。让作者和主角一起探索未知时空，开放式剧情，选择驱动。 | |
| Agents Plugin Marketplace 84 production-ready agentic plugins, 192 agents, 156 skills & 102 commands for Claude Code, Codex CLI, Cursor, OpenCode & Gemini CLI | |
| DeerFlow Open-source super agent harness orchestrating sub-agents, memory & sandboxes for deep research & extended tasks with extensible skills | |
| Prompt Optimizer AI prompt optimization tool: web app, desktop app, Chrome extension & Docker — optimize prompts for better AI output quality | |
| Letta Build AI with advanced memory that learns & self-improves over time — agents with persistent memory, sub-agents & skill system | |
| Ruflo Multi-agent AI harness for orchestrating 100+ agents across machines, with self-learning memory, federated comms & enterprise security | |
| Achievement Hunter Tips Prioritize multiple goals like an achievement board by separating must-have achievements, side achievements, missable windows, low-value grinds, and a realis... | |
| Achievement Unlock Tracker Convert recent progress into a game-style achievement board with evidence, rarity, near-unlock targets, and hidden growth signals. Use for weekly or monthly... | |
| Ad Budget Rebalancer Analyze ecommerce ad spend notes across Meta Ads, Google Ads, TikTok Ads, Amazon Sponsored, and Xiaohongshu promotional feeds, then recommend budget realloca... | |
| AI Customer Service Use when building or running a WeChat/WeCom online customer service agent for OpenClaw or Hermes that answers company product and service questions from a lo... | |
| Legal Risk Assistant China legal triage assistant. Input a contract, labor dispute facts, lawsuit-cost question, or draft legal document need; output risk checklist, cost estimat... | |
| Ai Output Failure Triage Diagnose why an AI response failed, identify missing context, and prepare a safer retry prompt with acceptance checks and a go/no-go recommendation. | |
| Ai Work Session Planner Turns a messy work goal into a focused 60 to 120 minute AI-assisted work session with inputs, checkpoints, and a clear done-state. | |
| Airdrop Participation Filter A decision helper that helps users decide whether to participate in an airdrop campaign. Use when the user considers joining an airdrop. Prompt-only. | |
| Alibaba Shopping Assistant Alibaba ecosystem shopping assistant. Input a buying need or product link; choose between Taobao, Tmall, and 1688, compare platform fit, seller trust, visibl... | |
| Allergy Season Room Routine Build a low-effort room routine card for sneezing, irritation, or stuffiness that feels worse indoors during allergy season, with daily, weekly, and high-pol... | |
| Alone Time Architect Design intentional alone time with a clear purpose, realistic duration, phone boundaries, nourishing activities, and a gentle transition back. | |
| Amazon Listing Analyzer 为中阶 Amazon 卖家提供 Listing 健康度诊断、关键词分析、竞品对标及结构化优化建议，助力提升销售表现。 | |
| Anki Fusion Convert any learning material into Anki flashcards — Bloom's taxonomy powered card design | |
| Appliance Failure Troubleshooting Log Creates a repair-ready appliance failure log with symptoms, timing, model details, error codes, safe checks, photo evidence, warranty questions, and technici... | |
| Appliance Rebate Claim Packet Build a paperwork checklist and submission packet for appliance rebate claims, including eligibility facts, required documents, deadline checks, proof copies... | |
| Appliance Service Visit Prep Sheet Prepare a technician-ready appliance service visit sheet with model and serial details, symptom timeline, photo checklist, access notes, questions, and visit... | |
| Argument Audit 论点审计 - An analytical tool that evaluates the logical structure, evidence quality, and persuasiveness of arguments. Use when user asks about 论点分析、论证评估、逻辑审查、观点... | |
| Assortment Scout Audit an ecommerce catalog, spot SKU sprawl, price and attribute coverage gaps, hero dependence, long-tail bloat, and duplicate-risk clusters, then turn roug... | |
| Skill Auditor Deep audit for installed ClawHub skills — usage analysis, permission review, conflict detection | |
| Auto Skill Installer Understand a user or agent capability need, discover relevant Codex/agent skills, choose the best candidate, install it, and verify the installation. Use whe... | |
| Bilibili Digest Extract, structure, and summarize Bilibili video/column content into structured notes with timestamps, key points, and chapter indexes. | |
| Bill Manager Manage daily bills, expenses, and recurring payments with tracking, reminders, and analysis. Use when the user asks about bill management, expense tracking,... | |
| Blind Date Assistant Blind date preparation assistant. Input the meeting context, profile notes, chat excerpts, or follow-up goal; output respectful conversation topics, safety b... | |
| Book Review Skill Generate in-depth book reviews from reading notes — expansion, key takeaways, related concepts. Pure local processing: no external APIs, no filesystem access... | |
| Boss Battle Calendar Transform upcoming high-stakes events into boss battles with countdown phases, preparation checkpoints, risk warnings, and recovery plans. Use when the user... | |
| Breach Check Check if your email, phone or password has been in data breaches. Full security response workflow. | |
| Break Even Analysis Calculator Provides break-even analysis frameworks, structured insights, actionable recommendations, and next-step checklists without executing code or financial transa... | |
| Browser Shopping Assistant Browser shopping assistant. Input a product link or keyword; compare browser-visible prices, seller type, reviews, promotions, delivery/return signals, and a... | |
| Burnout Checkin Help users do a gentle burnout risk check-in by reflecting on exhaustion, detachment, overload, and recovery. Use when the user says they feel drained, emoti... | |
| Buying Cross-platform buying decision skill that compares the same product across Taobao, Tmall, JD, PDD, VIPSHOP, and similar marketplaces, distinguishes flagship,... | |
| Cainiao Use Cainiao Network (菜鸟物流) for shipment tracking, shipping guidance, service-type comparison, outlet lookup, and delivery-time or fee estimation. | |
| Capital Expenditure Planner Provides frameworks and templates to plan capital expenditures with structured analysis, recommendations, and next steps, for informational use only. | |
| Career Path Advisor Analyze your skills versus market demands to identify gaps, explore career routes, and create personalized learning roadmaps for targeted role transitions. | |
| Cart Optimizer Optimize shopping-cart top-up plans for Taobao, JD, PDD, Tmall, and local ecommerce promotions | |
| CartPilot Checkout-path optimization skill for mainland China shopping and local-delivery scenarios that decides whether to split orders, which coupons or threshold di... | |
| Cash Flow Forecast Assistant Provides structured guidance, templates, and recommendations for cash flow forecasting and financial planning without executing transactions or accessing ext... | |
| Cb B2b Sales Enablement Framework Build localized B2B sales playbooks, objection-handling scripts, and account-based outreach sequences for any overseas market. Go from "we should sell there"... | |
| CB Brand Naming Trademark Guide Generate brand names that work across languages and pass trademark checks — not just creative ideas, but names with preliminary availability screening, cultu... | |
| Cb Brand Positioning Framework Craft a ready-to-execute brand positioning strategy for any international market — complete with messaging hierarchy, competitive differentiation map, and lo... | |
| Cb Community Building Strategy Design a community-building playbook for any overseas market — from platform selection and content calendar to engagement tactics and growth loops. Launch yo... |
34,801–34,850 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.