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 |
|---|---|
| compound-interest Activate when: user asks about starting early vs. later for savings/investing, wonders if small consistent gains add up, wants to know how long to double money, is evaluating long-term wealth or skill-building decisions, mentions 'Rule of 7 | |
| confirmation-bias Activate when: user says 'we keep finding evidence that supports our view,' 'the team is all aligned on this,' 'I've done the research and it checks out,' or a decision moves forward with only supporting evidence cited. Do NOT activate when | |
| Content-Led Growth — Topic Clusters for Search Intent Activate when: a founder/SMB wants durable organic acquisition; 'how do we do SEO/content', 'we blog but get no traffic', building a content engine; topic clusters, search intent. Do NOT activate when: the need is immediate paid response th | |
| Continuous Discovery — Weekly Contact, Opportunity Trees Activate when: a team ships features on opinion instead of evidence; 'we need a discovery habit', 'how often should we talk to users', building a product roadmap; connecting weekly customer contact to decisions. Do NOT activate when: pre-fi | |
| The Contrarian Question Activate when: user says 'contrarian question,' 'the Thiel question,' 'what important truth do very few people agree with you on,' 'is this actually contrarian,' or 'what valuable company is nobody building'; user is drafting or stress-test | |
| CPA — Client Document Chase Activate when: a tax or bookkeeping engagement is blocked on client paperwork; a client has gone quiet on a document request; drafting an initial PBC/document request; deciding whether to extend, deliver incomplete, or disengage; user says | |
| CPA — Form Finder Activate when: scoping or quoting a new tax engagement; a client describes a transaction and you need to place it; building a document request list; sanity-checking that a return has the schedules its facts imply; user says 'what forms does | |
| CPA/EA — IRS Representation Activate when: a client receives an IRS notice or letter; an examination opens or an IDR arrives; a client has unfiled returns, a balance owed, or a lien/levy pending; deciding whether to appeal an adjustment or collection action; scoping a | |
| CPA — Pre-Delivery Return Review Activate when: a prepared 1040 or 1120-S is going to review; you are the second set of eyes on someone else's return; a firm wants one consistent review standard across reviewers; onboarding a preparer to the review bar; something feels off | |
| critical-thinking Activate when: user says 'challenge my thinking', 'play devil's advocate', 'what's the strongest counter-argument', 'ACH', 'analysis of competing hypotheses'; user needs to evaluate a high-stakes claim or decision with multiple possible int | |
| Cross-Disciplinary Creativity Activate when: 'we need a breakthrough idea', 'everything in our industry looks the same', 'we've exhausted all options in our field', 'how do we innovate in a way no competitor has tried', 'need to think completely outside the box'. Do NOT | |
| curiosity-learning-curve Activate when: user says 'I used to love this but don't anymore', 'I feel like I've stopped learning', 'I go through the motions but nothing excites me', 'how do I stay curious as I get older', or a domain expert's knowledge has visibly sta | |
| customer-relationship-ladder Activate when: a key account renewal is at risk and the team can't explain why the customer values them; someone asks 'how do we become a strategic partner?'; a CSM needs to know where a relationship actually stands; the team claims to be s | |
| Customs — AD/CVD & Tariff Exposure Cascade Activate when: goods may fall under an antidumping/countervailing duty order or Section 301; sourcing changes; 'are we exposed to AD/CVD or 301?'; scope ambiguity. Do NOT activate when: product clearly outside any order and no special tarif | |
| Customs — Duty Optimization (Opportunity Cost) Activate when: an importer has recurring, material duty spend; evaluating FTZ, duty drawback, first-sale valuation, bonded warehouse, or FTA use; 'are we leaving duty savings on the table?'. Do NOT activate when: de minimis / trivial duty w | |
| Customs — HTS Classification (MECE Decomposition) Activate when: classifying merchandise under the HTSUS; ambiguous/multi-function goods; 'which heading applies?'; a product spanning multiple chapters. Do NOT activate when: an established binding ruling already governs the exact article. M | |
| Customs — Country of Origin & USMCA Qualification Activate when: determining country of origin; testing USMCA (or other FTA) preference eligibility; marking; 'does this qualify for duty-free?'; goods with multi-country inputs. Do NOT activate when: wholly-obtained single-country goods with | |
| Customs — Reasonable Care & ISF Compliance Checklist Activate when: filing an entry or ISF; onboarding an importer (POA); building the compliance file; 'did we file ISF in time?', 'is our reasonable-care record complete?'. Do NOT activate when: the shipment is exempt and no entry/ISF is requi | |
| cynefin Activate when: 'our best practices keep failing', 'experts disagree on the right answer', 'the old playbook isn't working', 'we're in crisis and don't know what to do first', 'best practice doesn't apply here', 'we need a different approach | |
| death-spiral Activate when: user says 'we're losing market share,' 'our growth keeps slowing and I don't know why,' 'a competitor is gaining on us fast,' 'what's the worst-case trajectory here,' or a business shows two or more consecutive quarters of de | |
| decision-tree Activate when: user says 'help me choose between two options with different risks', 'I need to map out what could happen if we go with X', 'we have a sequential decision — first we do A then depending on results we do B', 'what is the expec | |
| deep-work Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make p | |
| definite-optimism Activate when: user says 'definite optimism,' 'Thiel's 2x2,' 'do we have a real plan or just options,' 'we're keeping our options open,' or asks whether a strategy/career/company is a concrete bet on the future or a diversified hedge; a pla | |
| deliberate-practice Activate when: user says 'I've been doing this for years but I'm not getting better'; someone suspects a skill plateau despite continued effort; designing a learning program for a high-performance outcome; an organization reports high train | |
| demand-leadership Activate when: 'we have a strong product but keep losing on price', 'customers treat us like a commodity', 'how do we stop being compared to competitors', 'why aren't customers coming to us before they write the RFP', 'we want to define the | |
| design-thinking Activate when: user asks 'why isn't anyone using our product?', 'how do we understand what customers really want?', 'we know the tech works but the market isn't responding', team is stuck on a single solution and needs divergent ideas, or s | |
| Dichotomy of Control Activate when: user says "I can't stop worrying about something I can't control," "I'm anxious about how this will turn out," "I keep replaying what went wrong," "I need them to change," "this uncertainty is paralyzing me," or is processing | |
| Discovery Calls with SPIN — Let the Buyer Sell Themselves Activate when: running sales discovery calls; deals stall because the buyer doesn't feel the pain; 'how do I run a sales call', 'my demos don't convert', qualifying a prospect. Do NOT activate when: the deal is transactional/self-serve with | |
| disruptive-innovation Activate when: a founder asks 'can we avoid competing head-on with big players?', someone asks 'is this disruption or just a price war?', an investor wonders if a startup's entry angle creates durable structural advantage, an incumbent spot | |
| Do Things That Don't Scale Activate when: an early founder is over-automating or waiting for growth to be 'efficient'; 'this won't scale', recruiting first users, delivering early service manually; concierge/white-glove starts. Do NOT activate when: the motion is alr | |
| Door-in-the-Face Technique Activate when: user asks 'they made a big ask then backed off, should I concede?'; user is designing a negotiation opening and wants to land at a specific price; someone says 'anchor high then retreat' or 'reciprocal concession'; user suspe | |
| Dual-System Thinking (System 1 / System 2) Activate when: a decision feels obvious but the stakes are high; someone says 'I just trust my gut' on a consequential call; a team is converging fast without pushback; you're tired or pressured and still need to decide; you're in an unfami | |
| Dunbar's Number Activate when: team headcount is approaching or crossing 150 (or 50, or 500); someone says "coordination is getting harder," "we lost the startup feel," or "we don't know who does what anymore"; deciding whether to split a team, open a new | |
| Dunning-Kruger Effect Activate when: someone says 'how hard could it be' about an unfamiliar domain; a novice dismisses expert opinion or says 'I could do that'; someone's self-assessed confidence seems disconnected from their actual track record; a hiring or pr | |
| dynamic-core-competence Activate when: user asks 'what is our real edge?', 'what will our moat look like in 3 years?', 'which capabilities should we invest in?', someone says 'competitive advantage' without a specific testable claim, or a team is assessing whether | |
| economic-moat Activate when: user asks 'does this business have a moat', 'what stops competitors from copying us', 'how defensible is this company', 'is this advantage durable', evaluating a company for investment or acquisition, designing startup strate | |
| Economies of Scale Activate when: user asks "will our margins improve as we grow?", "do we need scale to compete?", "why does our competitor charge less than us?", analyzing whether a business model has a cost advantage at higher volume, evaluating M&A "scale | |
| emergence Activate when: user says 'our culture isn't working despite directives', 'the market behaves unexpectedly', 'this worked at small scale but not at large scale', 'we can't predict or control what's happening', 'designing a platform/community | |
| endowment-effect Activate when: seller is asking way more than buyers will pay; a founder or homeowner insists their asset is worth far more than market comps; a team refuses to cut a feature they built; a free-trial cancellation flow has more friction than | |
| Tax Prep — Estimated-Tax Safe-Harbor Buffer Activate when: self-employed / K-1 / variable-income client planning quarterly 1040-ES; 'how much should I set aside?', 'will I owe a penalty?', volatile income year. Do NOT activate when: W-2 withholding fully covers liability. More: deciq | |
| Expected Value and the Kelly Criterion Activate when: user asks 'how much should I bet/invest on this?', 'what's the expected value here?', 'Kelly criterion', 'optimal bet size', 'fractional Kelly', 'how big a position should I take?', or is allocating capital across repeated de | |
| falsifiability Activate when: user says 'what would prove this wrong', 'how do we know if our strategy is working', 'what would change your mind', 'this claim feels unfalsifiable', or is designing a hypothesis/experiment/investment thesis that needs to be | |
| feedback-loops Activate when: user says "we keep overshooting/undershooting", "the cure is causing the disease", "we're stuck in a loop", "why does this keep happening?", "the system keeps fighting back", "bullwhip effect", "death spiral", "growth flywhee | |
| feynman-technique Activate when: user says 'explain this simply', 'teach me like I'm five', 'do I really understand this', 'what's the simplest way to think about X', 'what's missing in my model', wants to test genuine vs. surface understanding of a concept, | |
| First-Mover Advantage Activate when: user asks 'should we move first or wait?', 'is it too late to enter this market?', 'how long can they hold their lead?', 'what makes the first mover hard to beat here?', or needs to assess how durable a market leader's positi | |
| First Principles Activate when: user says 'from first principles,' 'from scratch,' 'why do we even believe this,' 'tear this apart,' or 'the conventional answer seems wrong';... | |
| Founder Sustainability — Protect the Company's Key Asset Activate when: a founder is running on empty, working unsustainable hours, or output/judgment is degrading; 'I'm burning out', 'I can't keep this pace', protecting the founder as the company's key asset. Do NOT activate when: it's a short, | |
| Founder-Led Sales — Sell It Yourself Until It's Repeatable Activate when: an early founder needs revenue but wants to hire a salesperson or 'automate' sales too soon; 'I hate selling', 'when should I hire sales?', first customers, pre-PMF go-to-market. Do NOT activate when: the company already has | |
| Founder Mindset Activate when: user says 'founder mindset' or 'founder mode'; asks 'default alive or default dead'; says 'do things that don't scale'; says 'am I avoiding th... | |
| founder-trajectory-matrix Activate when: a founder says they're hitting a ceiling despite working harder; a founding team keeps fighting about who makes decisions; someone asks 'why do some founders progress faster than me?' or 'do I need a co-founder?'; a founder i |
24,801–24,850 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.