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 |
|---|---|
| Zig Pro Maxx Enforces strict API compliance, memory safety, and idiomatic patterns for Zig 0.16.0 — and refuses to generate code for any earlier version. Activate wheneve... | |
| China Holiday 中国法定节假日查询，基于 timor.tech 免费 API。支持查询指定日期节假日信息、批量查询、下一节假日、下一工作日、全年节假日列表，以及语音播报。触发场景：问"今天上班吗"、"明天放假吗"、"2026年有哪些节假日"、"清明节放几天"、"调休怎么调"等节假日相关问题。依赖：Python 3，仅使用标准库（... | |
| Clankers World Operate Clankers World through the canonical `cw` CLI, with bundled runtime helpers, explicit Wall vs Sandbox separation, and safe room operations on `https:... | |
| Persona Spawn Spawn subagents with personas from a local workspace library or the Emblem persona marketplace. Use when a task needs a different voice, expertise, or operat... | |
| Upgrade Openclaw Upgrade OpenClaw and comprehensively discover new features, config options, hooks, and improvements. Use when: user says "upgrade openclaw", "update openclaw... | |
| easy-opencode opencode can do all the things related to code | |
| Web Search Free Free AI search via Exa MCP. Fall back to Multi Search Engine if not successfull. All without API keys. IMPORTANT Should always use web-search-free skill befo... | |
| 徒步路线规划 Plan complete hiking itineraries and leader-ready route briefs for day hikes, mountain walks, coastal treks, and beginner group outings. Use when a user asks... | |
| speech-translation Build, adapt, or run an audio-processing workflow that takes spoken audio, transcribes it with Whisper or faster-whisper, translates the transcript using the... | |
| 10-10-10 Activate when: someone is making a decision under emotional pressure and worries they'll regret it later; someone says "I know I should do X but it feels too scary right now"; someone is about to quit, accept an offer, end a relationship, o | |
| AARRR (Pirate Metrics) Activate when: user says 'our growth is stalling and we don't know why,' 'product and marketing are arguing about whose fault it is,' 'where is our funnel breaking,' 'pirate metrics,' or 'acquisition vs activation vs retention.' Also activa | |
| abductive-reasoning Activate when: user says 'what's the most likely explanation,' 'why did this happen,' 'we think it's X but not sure,' 'we only have one theory,' 'the team has converged on an answer without checking alternatives,' or when diagnosing a bug/o | |
| Activation & Onboarding — Get to First Value Fast Activate when: signups don't turn into active/paying users; 'people sign up but don't stick', designing onboarding, improving activation; aha moment, time-to-value. Do NOT activate when: the problem is acquisition (no signups) or long-term | |
| Answer Engine Optimization (AEO) Activate when: user says 'win the featured snippet', 'get the voice assistant to read our answer', 'AEO', 'answer engine optimization', 'structure our FAQ', asks 'how do we get our answer shown directly?', or needs to restructure content so | |
| agent-delegability-assessment Activate when: user says 'which work can we hand to an AI agent', 'how far can this process be automated', 'does the agent need human approval', 'how much permission should the agent get', asks 'can the agent just do this on its own?', or i | |
| agent-ops-monitoring Activate when: user says 'how do we watch the agent after launch', 'AI output quality is getting worse', 'inference spend suddenly jumped', 'the agent broke something, how do we roll back', 'we need an AI ops weekly review', or an AI agent | |
| Agent Outreach & Lead Nurturing Activate when: user says 'use an AI agent for outreach / cold email', 'automate lead follow-up', 'multi-touch nurture sequence', 'personalized prospecting emails', asks 'how do we let the agent send email without it looking like spam?', or | |
| Agent-Ready Product Data Activate when: user says 'make our products buyable by AI shopping agents', 'is our product data agent-ready?', 'agentic commerce', 'the agent failed to place the order', asks 'why doesn't ChatGPT / a shopping agent recommend or buy our pro | |
| AI Content Factory and Brand Consistency Activate when: user says 'use AI to mass-produce content', 'how do we make AI write like our brand?', 'the AI content got facts wrong', 'how do we keep AI content out of legal trouble?', 'build a content factory', or plans 10+ AI-assisted p | |
| AI Disruption Risk Audit Activate when: user says 'will AI disrupt us?', 'which parts of our business will AI replace?', 'is our moat still there in the AI era?', 'run an AI impact assessment', or customers have started using AI tools to do work they used to pay us | |
| AI Output Verification Trust Tiers Activate when: user says 'can we use the AI's output directly?', 'what needs human review and what doesn't?', 'how do we verify AI output?', 'the AI made up data again', or needs review rules for AI outputs, or is deciding where an agent ma | |
| AI Pilot to Scale Activate when: user says 'our AI pilot is done but nobody uses it', 'the demo was great, how do we roll it out?', 'how do we get this POC into daily operations?', 'should we scale or kill this pilot?', 'the pilot keeps getting extended', or | |
| AI Risk & Compliance Baseline Activate when: user says 'what are our compliance risks from using AI?', 'can we feed client data into AI?', 'do we have to tell customers we use AI?', 'who owns the copyright on AI output?', 'how do we stop prompt injection?', 'a client as | |
| AI ROI Business Case Activate when: user says 'is this AI project worth doing?', 'calculate the ROI of AI', 'how long until this agent pays back?', 'build the AI business case for my boss/investors', 'what does this AI tool really cost us?', or is about to pay | |
| anchoring Activate when: user says 'what's a fair price / starting number / ballpark'; counterparty just opened with a number; user is about to negotiate salary, valuation, or deal terms; user is making a forecast and a number has already been floate | |
| ansoff-matrix Activate when: user says 'where should we grow next', 'should we enter a new market', 'thinking about diversifying', 'new product vs new market', 'growth strategy', 'adjacent expansion', 'Ansoff', or is spreading resources across too many d | |
| antifragile Activate when: user asks whether their system/business/portfolio would survive a crisis; user says 'this has been fine for years but I'm nervous'; user wants to stress-test a plan against worst-case scenarios; user mentions Taleb, barbell s | |
| AR & DSO Discipline — Get Paid Faster Activate when: customers pay late and cash is tight; 'clients don't pay on time', collections, invoicing terms, reducing days-sales-outstanding; overdue receivables. Do NOT activate when: paid instantly at point of sale (no receivables). Mo | |
| Arrow's Information Paradox Diagnoses the buyer/seller deadlock in any trade of information — the buyer cannot value what they cannot see, but once they see it they have it for free — and selects the disclosure mechanism (patent, NDA, staged disclosure, trusted interm | |
| Authority Bias Detect and mitigate undue influence from positional authority when expertise on the specific question is unverified or reasoning lacks independent support. | |
| availability-heuristic Activate when: user says 'we keep hearing about X so it must be common', 'that just happened so it's risky', 'the news is full of stories about this', 'I've seen this a lot lately so it's probable', or is making a risk/frequency estimate dr | |
| BATNA & ZOPA Activate when: user says 'walk-away point', 'reservation price', 'should I take this deal', 'what's my leverage', 'they won't budge', or any salary/term-sheet/vendor/M&A negotiation where stakes are non-trivial. Do NOT activate when: the si | |
| bayesian-reasoning Activate when: user says 'Bayesian', 'prior', 'posterior', 'base rate', 'likelihood ratio', or 'update my belief'; someone treats 'the evidence is consistent with X' as proof of X; a high-stakes decision rests on interpreting a test result, | |
| BCG Growth-Share Matrix Activate when: user says "portfolio review," "cash cow," "Stars and Dogs," "growth-share matrix," "which business should we fund," or "resource allocation across units"; firm has multiple business units competing for shared capital; investo | |
| black-swan Activate when: user says 'this can't happen,' 'never happened in N years,' 'our models say it's near-zero'; user is stress-testing a strategy or portfolio against extreme scenarios; someone mentions fat tails, Taleb, narrative fallacy, or t | |
| blue-ocean-strategy Activate when: user asks 'how do we stop competing on price?', 'what new market can we create?', 'is there a way to differentiate and cut costs at the same time?', describes an industry where all competitors look identical and margins are e | |
| Bootstrapping vs Raising — Choose the Fuel to Match the Fire Activate when: a founder is deciding whether to raise venture money or self-fund; 'should we raise?', weighing dilution vs speed, choosing a funding path; VC fit vs bootstrap/SMB. Do NOT activate when: the decision is already made and the t | |
| Build / Buy / Partner (AI Capabilities) Activate when: user says 'should we build this AI feature or buy it?', 'should we develop our own agent?', 'which AI vendor should we partner with?', 'build vs buy', 'should we train our own model?', 'the vendor raised prices / changed term | |
| Bullseye — Find the One Traction Channel That Works Activate when: a founder is guessing at marketing channels or pouring effort into one that isn't working; 'how do we get customers', 'which channel should we use', growth is stalled on distribution. Do NOT activate when: a channel is alread | |
| business-model-canvas Activate when: user says "business model canvas," "BMC," "Osterwalder canvas," "what's our business model," "map this business," or asks to evaluate/design/pivot/compare a business model before raising capital. Do NOT activate when: no cust | |
| Cash Conversion Cycle — Why Profitable Businesses Run Out of Cash Activate when: a profitable-on-paper business is short on cash; 'we're profitable but always broke', managing working capital, inventory or receivables tying up cash; DSO/DIO/DPO. Do NOT activate when: a pure digital business with instant p | |
| Change and Constants Framework Activate when: 'we keep debating whether to pivot or stay the course', 'I don't know what we should never change', 'is this signal or noise?', 'the market shifted — what do we hold onto?', 'we're paralyzed between adapting and staying true | |
| checklist Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activat | |
| Chesterton's Fence Activate when: someone says 'let's just remove this', 'why do we still have this rule?', 'this seems useless/outdated', 'nobody knows why this is here', new leadership restructuring without knowing the history, a developer deleting code who | |
| Circle of Competence Activate when: user says 'should I enter this market / make this hire / invest in this domain,' 'am I qualified to evaluate this,' 'stay in your lane,' 'stic... | |
| cognitive-evolution-stages Activate when: user says 'I understand it but can't apply it,' 'how do I stop just copying other people's work,' 'I can adapt frameworks but can't create new ones,' 'why does my innovation always look like a remix,' or when someone's output | |
| cognitive-load-theory Activate when: someone says 'this is too much to take in at once', 'learners aren't getting it despite good material', 'our onboarding is overwhelming new hires', 'why does this tutorial confuse people', 'how do I design training that actua | |
| cognitive-science-landscape Activate when: user says 'I want to improve my thinking,' 'why does my decision-making keep failing,' 'how do I optimize my cognitive performance,' 'what's the full picture of how the mind works,' or is about to apply a single cognitive int | |
| Commitment and Consistency Activate when: user says "foot in the door," "I already committed so I have to follow through," "how do I design onboarding / a sales sequence / a commitment ladder," "Cialdini," "would I do this fresh," or is evaluating whether past small | |
| comparative-advantage Activate when: user says 'should I do this myself or delegate,' 'I'm the best at X so I should do it,' 'should we outsource or build in-house,' 'how should we divide work on the team,' 'is it worth hiring someone for this.' Do NOT activate |
24,751–24,800 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.