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 |
|---|---|
| framing-effect Activate when: user says 'how you say it matters', 'they're spinning the numbers', 'same data but sounds different', 'is this just framing?', wants to write a persuasive message, suspects a statistic is one-sided, or is evaluating options w | |
| Freight Broker — Carrier Vetting Checklist Activate when: a freight broker is booking a carrier and must vet authority/insurance/safety before tendering a load; 'is this carrier legit', onboarding a new carrier, preventing fraud/double-brokering. Do NOT activate when: the carrier is | |
| Freight Broker — Double-Brokering & Fraud Exposure Activate when: a freight broker faces fraud/double-brokering or non-payment risk; 'the carrier that hauled isn't the one I booked', chargebacks, unpaid carriers coming after the shipper; tracing downstream liability. Do NOT activate when: a | |
| Freight Broker — Lane Pricing & Load Decision Activate when: a freight broker must quote a lane and decide accept/counter/pass on a load or carrier rate; 'what should I quote', 'is this rate any good', margin vs win-probability on a lane. Do NOT activate when: a contracted rate already | |
| Freight Broker — Shipper/Carrier Principal-Agent Balance Activate when: a freight broker must balance shipper and carrier interests and disclose their intermediary role; 'whose side am I on', margin transparency, conflicts between best rate for shipper vs relationship with carrier. Do NOT activat | |
| fundamental-attribution-error Activate when: someone says 'they're just like that,' an employee is being blamed for underperformance without examining their situation, a post-mortem is focusing on who screwed up, customer churn is being written off as 'not the right fit | |
| Goodhart's Law Activate when: our KPI is going up but the real outcome isn't improving; people seem to be gaming the metric; we're about to tie bonuses or promotions to a number; an algorithm is producing results nobody intended; a test or audit system is | |
| gravity-field-empowerment Activate when: user asks 'did this transformation actually work', 'how do I measure whether coaching/strategy/capital changed the business', 'why does our improvement not stick', 'how do I choose between competing empowerment options', or e | |
| Halo Effect Activate when: user is conducting a performance review or hiring interview; someone says 'she's great across the board' or 'everything they do is excellent';... | |
| Hanlon's Razor Activate when: someone feels a colleague/partner/company did something on purpose to hurt them; a team believes another side is acting in bad faith; someone is about to escalate based on assumed malicious intent; a pattern of bad outcomes i | |
| Herzberg Two-Factor Theory Activate when: someone says 'why isn't the team motivated,' 'we raised salaries but morale didn't improve,' 'people keep leaving for better opportunities,' 'employee engagement is low,' 'how do I retain engineers,' or when designing compens | |
| hidden-elite-advantages Activate when: 'what makes top investors/founders truly different', 'how do I close the gap with elite performers', 'what am I missing that successful people have', 'I want to learn from [elite person]', designing a personal development pla | |
| hindsight-bias Activate when: someone says 'I knew it all along' or 'we should have seen it coming'; a post-mortem is blaming someone for not predicting an outcome; a team is reviewing a past decision and the outcome is coloring the judgment; a decision-m | |
| Human–AI Role Redesign Activate when: user says 'what does this role do once the agent takes over?', 'how should KPIs change after AI goes live?', 'what new skills do our people need?', 'how do we tell the team about AI replacing work?', 'rewrite the job descript | |
| hyperbolic-discounting Activate when: user says 'I'll start tomorrow / next week / next month' repeatedly; someone intends to save / exercise / quit but never follows through; a product's free trial or subscription is creating unexpected lock-in; someone wants to | |
| incentive-design Activate when: user asks why a team keeps doing the wrong thing despite training; user is designing compensation, bonuses, or commissions; user says 'people are gaming the metric' or 'our OKRs aren't working'; user wants to fix a performanc | |
| Incremental vs. Leap Growth Activate when: growth has stalled despite good execution; a team disagrees whether a goal is 'realistic'; someone says their initiative is transformative but measures it with quarterly targets; you're designing a new market entry or capabil | |
| industry-learning-sprint Activate when: user is entering an unfamiliar industry and needs a working mental model fast; user says 'I need to understand this sector before a meeting next week'; user is evaluating an acquisition or investment in a domain they don't kn | |
| Insurance Agent — Sales Compliance Checklist Activate when: an insurance agent/agency must not skip licensing, disclosure, suitability, and replacement steps on a sale; 'am I compliant on this policy', selling/replacing a policy, onboarding a producer. Do NOT activate when: the questi | |
| Insurance Agent — Coverage-Gap Premortem Activate when: an insurance agent should stress-test a client's coverage before a claim exposes a gap; 'is this client actually covered', policy review, exclusions/limits/underinsurance; E&O risk. Do NOT activate when: no coverage is being | |
| Insurance Agent — Renewal & Retention Ladder Activate when: an insurance agent wants to keep clients renewing and buying more lines; 'how do I stop losing clients at renewal', cross-sell/round-out accounts, book retention; 'my retention is dropping'. Do NOT activate when: the agent ha | |
| Insurance Agent — Suitability & Principal-Agent Conflict Activate when: an insurance agent's compensation conflicts with the client's best coverage; 'which product do I recommend', commission-driven product choice, captive vs independent conflicts, best-interest duty. Do NOT activate when: no rec | |
| intrinsic-drive Activate when: user says 'I've lost motivation', 'I'm burning out', 'the excitement is gone', 'I keep starting things but can't sustain them', 'I'm going through the motions', 'I don't know what drives me anymore', or describes a flat feeli | |
| inversion Activate when: user says 'do a pre-mortem', 'what could go wrong', 'why might this fail', 'invert the question', 'what would have to be true for this to be a disaster'; a plan keeps generating enthusiasm with no risks named; an investment t | |
| Jobs to Be Done (JTBD) Activate when: user says 'customers aren't switching to us even though we're better,' 'our churn surveys aren't predicting who actually leaves,' 'we're debating features instead of what the customer actually needs,' 'who is our real custome | |
| K-Factor and Viral Coefficient Activate when: user says 'viral coefficient,' 'K-factor,' 'going viral,' 'our product is viral,' 'referral program,' 'invite mechanic,' 'built in sharing,' growth plateauing despite viral elements, or a growth forecast is being justified by | |
| Knowing and Doing as One Activate when: user says 'I know I should but I haven't', a team is stuck in analysis paralysis going in circles, you need to assess whether someone actually learned from a past experience, a strategy or lessons-learned doc has produced no | |
| Kotter's 8-Step Change Model Activate when: user says 'our change initiative is stalling', 'people aren't adopting the new way', 'we launched the transformation but nothing changed', 'how do we overcome resistance to change', 'why do transformation efforts fail', or as | |
| Landing Page Conversion — Clarity Beats Cleverness Activate when: traffic arrives but doesn't convert; 'our landing page doesn't work', launching a new offer page, improving signup/lead rate; messaging, CTA, friction. Do NOT activate when: there's no traffic yet (fix acquisition first) or t | |
| last-mover-advantage Activate when: user asks 'does being first even matter here?', 'who wins this market in the end?', 'will this business still be around in 10 years?', 'should we race to ship or wait and own the category?'; a strategy is justified mainly by | |
| lateral-thinking Activate when: user says 'we've tried everything,' 'think outside the box,' 'we need a breakthrough,' 'challenge assumptions,' or 'how might we'; a team keeps cycling through the same 2-3 options; an industry assumption has gone unchallenge | |
| latticework Activate when: user says 'I don't know which framework to use', 'our analysis keeps missing something', 'we need a second opinion on our model', 'how do we stress-test this decision from multiple angles', 'one framework isn't enough here', | |
| lean-startup Activate when: user says 'lean startup', 'build-measure-learn', 'MVP', 'validated learning', 'pivot or persevere', 'should we just build it?', 'we need to test this idea before building', or 'how do we know if anyone wants this?'; team is a | |
| lifestage-value-curve Activate when: someone asks 'what should I focus on at my age,' 'I feel like I'm wasting my best years,' 'how do I plan my career long-term,' 'what does my 40s/50s demand,' or a person is clearly investing for the wrong life stage (Heroic A | |
| lindy-effect Activate when: user asks 'should we use this old technology or switch to something newer', 'how do I know if a book is worth reading', 'this institution has been around forever — is that meaningful', 'we should modernize / this time is diff | |
| logical-fallacies Activate when: someone says 'this argument feels off but I can't explain why', 'is this a real argument or just rhetoric?', 'what's wrong with this reasoning?', an argument relies entirely on authority/emotion/popularity, or you're about to | |
| Loss Aversion and Prospect Theory Activate when: someone says 'I don't want to lose what I have', a deal is stuck because a concession feels like a loss, a pricing or incentive change gets unexpected pushback, someone is refusing a bet that looks positive in expected value, | |
| manager-development-spectrum Activate when: a promoted manager is failing without clear cause; someone says 'leadership training isn't working'; a leader asks 'why can't I get to the next level'; an org wonders why its best performers plateau after promotion; a coach n | |
| Map Is Not the Territory Activate when: a metric is improving but customers or employees are signaling problems; a strategy or process hasn't been reviewed in over a planning cycle; a team keeps disagreeing and can't resolve it with data; someone says 'the model sh | |
| Margin of Safety Activate when: user asks how much buffer to build into a budget, timeline, or investment; someone says 'I might be wrong on my estimate — how much cushion do I need?'; a project or position is running lean and someone wonders if there's eno | |
| Maslow's Hierarchy of Needs Activate when: "why isn't the bonus motivating them," "already paid well but disengaged," "what need does this product really serve," "team is in survival mode," "they need to feel safe before caring about the mission," or diagnosing why a | |
| MECE (Mutually Exclusive, Collectively Exhaustive) Activate when: user says 'decompose this', 'structure this thinking', 'MECE', 'issue tree', 'Minto Pyramid', 'how do we cover all the cases without double-counting', a problem feels too big to think about cleanly, a list of options is messy | |
| metacognition Activate when: user says 'I'm stuck and don't know why', 'I keep making the same mistake', 'my analysis feels right but I'm not sure', 'am I solving the right problem', 'I should understand this but I don't', or asks about calibration / thi | |
| The Middle Way (中庸 Zhongyong) Activate when: a decision is framed as 'X or not-X' but is really a spectrum; someone says 'we have to choose between A and B' and both seem to have problems; a debate is stuck in ideological purity and 'compromise' is being dismissed as we | |
| Minimum Viable Audience — Win a Small Specific Group First Activate when: a founder wants to appeal to everyone; 'our market is huge / everyone is a customer', picking a beachhead, a creator/SMB choosing a niche; 'who exactly is this for?'. Do NOT activate when: the business genuinely requires mass | |
| minsky-moment Activate when: user asks 'is this a bubble?', 'what's the tail risk here?', 'this time is different', 'leverage has been stable for years', 'the fundamentals support these prices', someone wants to diagnose credit cycle fragility, analyze d | |
| Momentum and Form Activate when: user says 'we have a better product but we're losing,' 'they're growing despite less funding,' 'our moat isn't protecting us,' 'the market shifted under us,' 'we just need to hire harder,' or is diagnosing why strong incumben | |
| Monopoly vs Competition Activate when: user says 'monopoly vs competition,' 'competition is for losers,' 'zero to one,' 'do we have a moat,' 'is this market too crowded,' 'how do we escape competition,' or 'start small and monopolize'; a startup or product is ente | |
| Mortgage — LO Compensation & RESPA Guardrails Activate when: designing/reviewing loan-originator compensation; considering a marketing services agreement (MSA), lead-buy, or referral arrangement; 'can we pay for these referrals?', 'can comp vary by loan?'. Do NOT activate when: unrelat | |
| Mortgage — Loan Fallout Premortem Activate when: a file is submitted or in underwriting; rate lock is ticking; 'what could kill this loan before closing?'; thin-file or borderline borrower. Do NOT activate when: clear-to-close with no open conditions. More: deciqai.com/c/mo |
24,851–24,900 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.