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 |
|---|---|
| Mortgage — Loan Program Matching Activate when: matching a borrower to Conventional/FHA/VA/USDA/Jumbo/Non-QM; deciding fixed vs ARM; 'which program fits this borrower?'; borderline DTI/LTV/credit. Do NOT activate when: borrower is pre-committed to one specific product with | |
| Mortgage — Rate & Terms Anchoring (Defense + Framing) Activate when: a borrower anchors on a headline/teaser rate they saw; presenting rate+points+APR trade-offs; competitor 'lowball' quote; 'why is your rate higher than the ad?'. Do NOT activate when: simply disclosing final locked terms. Mor | |
| Mortgage — TRID Timeline Compliance Checklist Activate when: an application hits the 6-item threshold (LE clock starts); approaching closing (CD clock); any change-of-circumstance / re-disclosure; 'did we send the LE in time?', 'does this trigger a new 3-day wait?'. Do NOT activate whe | |
| Mr. Market Activate when: user says 'the market is telling us X', 'valuation has dropped/risen so we should act', 'everyone is selling/buying so I should too', or is making an investment/fundraising decision based on a quoted price under emotional pre | |
| Minimum Viable Product Activate when: someone says 'MVP', 'minimum viable product', 'smoke test', 'concierge MVP', or 'Wizard of Oz'; a team is scoping a build and hasn't named the assumption they're testing; engineers are about to build for months on an unvalida | |
| narrative-fallacy Activate when: user is reading a business case study or founder biography and drawing lessons; a post-mortem produced a neat single root cause; someone says 'the story is too clean' or 'that explanation is too convenient'; a pundit explains | |
| narrow-gate-strategy Activate when: user says 'this is taking too long', 'everyone else is doing X', 'should we take the easier path', 'is this worth it', 'we need to build a moat', 'choosing which capability to invest in long-term', or 'should we persist or pi | |
| nash-equilibrium Activate when: user asks 'what will they do if we do X', 'how will competitors react to our pricing', 'how do I design this auction or mechanism', 'we keep ending up in a bad outcome even though everyone prefers better', or is analyzing a s | |
| network-effects Activate when: user says 'we have network effects,' 'winner-take-most,' 'two-sided platform,' 'Metcalfe's law,' 'marketplace liquidity,' or 'the more users the better'; user is building a marketplace, social product, communication tool, or | |
| neurological-levels Activate when: 'we keep trying to change this and it reverts,' 'people know what to do but don't do it,' 'the training didn't stick,' someone hits a knowing-doing gap repeatedly, or a culture change effort has failed more than once. Do NOT | |
| Nine-Level Cognitive Tower Activate when: user says 'how do I level up my thinking', 'why do I keep copying others', 'I don't know what I don't know', 'how do I develop independent judgment', or their reasoning shows systematic deference to authority, inability to fo | |
| Non-Consensus Thinking Activate when: user says 'everyone agrees on this,' 'the obvious move is X,' 'why go against the grain?'; user is entering a crowded market where the right strategy feels obvious; user has an early signal conflicting with the mainstream nar | |
| Non-Zero-Sum Activate when: someone says 'this is win-lose,' 'we can't both win,' 'what's in it for them to cooperate,' 'is there a deal here,' or 'how do we get past this standoff'; a negotiation or conflict feels deadlocked; you're designing a platfor | |
| north-star-metric Activate when: teams are fighting over which metric to optimize; someone says 'north star metric,' 'NSM,' 'OMTM,' or 'one metric that matters'; a dashboard has 30+ metrics with no clear priority; a leading indicator is needed that predicts | |
| nudge-theory Activate when: user says 'nudge,' 'default,' 'opt-in vs opt-out,' 'choice architecture,' or 'why do people know they should but don't?'; user has a behavior gap between intent and action; user is designing product onboarding, policy enrollm | |
| Objection Handling — Surface, Understand, Resolve Activate when: deals stall on 'too expensive', 'not now', 'need to think about it', 'send me info'; a founder gets flustered by pushback; improving close rate. Do NOT activate when: the prospect is genuinely unqualified (then disqualify, do | |
| Occam's Razor Activate when: user says 'simplify this', 'which is more likely', 'are we overcomplicating this?', 'what's the most likely explanation?', or presents multiple competing hypotheses/designs/diagnoses to rank. Do NOT activate when: only one ex | |
| OKRs (Objectives and Key Results) Activate when: user says 'set OKRs', 'write objectives and key results', 'our goals aren't measurable', 'teams are hitting targets but the business isn't moving', 'we need stretch goals', 'align teams around quarterly goals', or mentions Do | |
| OODA Loop Activate when: competitor outmaneuvers you despite worse resources; decisions take longer than the situation allows; team is losing a competition they should win; setting up crisis or incident response; someone says 'Boyd', 'decision cycle' | |
| opportunity-cost Activate when: user says "what could we have done instead," "what's the next-best alternative," "is this worth the cost," "what are we giving up by choosing X," "broken window fallacy," or is allocating scarce resources (money, time, attent | |
| Organic + Extension Growth Activate when: user says 'we've hit a growth ceiling,' 'should we acquire or build,' 'we're growing but not sure we can sustain it,' 'what's our M&A strategy,' or a business has achieved initial PMF and is designing its next growth phase. D | |
| Outcome-Based AI Pricing Activate when: user says 'how should we price our AI product?', 'per seat or per usage / per outcome?', 'how do we design pay-for-results pricing?', 'inference costs are eating our margin', 'price per resolution', or AI is shrinking the num | |
| overseas-expansion-framework Activate when: user says 'we want to go global' or 'expand internationally', founder is choosing between opening a local office vs. going digital-first in a new country, company has home-market traction and is planning its first internation | |
| The Pareto Principle (80/20) Activate when: user says 'Pareto,' '80/20,' 'vital few,' 'long tail,' 'where is the leverage'; a team is treating many items as equally important; a backlog has no triage; growth efforts are spread thin across too many initiatives. Do NOT a | |
| Peak-End Rule Activate when: user says 'how will they remember this,' 'experience design,' 'journey design,' 'memorable moment,' 'end-of-experience,' or 'our NPS is lower than expected'; when designing or auditing a multi-stage customer or user journey; | |
| Product-Market Fit and Crossing the Chasm Activate when: user says "PMF," "product-market fit," "crossing the chasm," "early adopter to mainstream," "whole product," "we're stuck after our beachhead," or "growth stalled after an initial good period"; startup has early traction but | |
| Point → Line → Plane → Solid (点–线–面–体) Activate when: user says 'we're good at X but not growing,' 'we need a moat,' 'we're just a feature not a platform,' 'competition keeps copying us,' 'we want to build something hard to replicate,' or asks how to move from product to platfor | |
| Porter's Five Forces Activate when: user asks 'is this a good industry to enter?', 'why is our margin so low despite solid execution?', 'what are the barriers to entry here?', 'how much power do our suppliers/buyers have?', 'should we invest in this sector?', o | |
| Positioning — Make It Obviously Awesome (Dunford) Activate when: a product is 'a better X' but nobody gets it; 'people don't understand what we do', weak conversion despite a good product, choosing a category/competitive frame; naming what you are. Do NOT activate when: positioning is alre | |
| Power-Law Distribution Activate when: user is allocating capital or resources across a portfolio and wants to know where to concentrate; user says 'our average customer / deal / employee performs at X' and is making decisions from that average; user is building a | |
| premortem Activate when: user says 'let's check what could go wrong before we commit', 'I want to stress-test this plan', 'we're about to launch and I'm worried we're missing something', 'premortem', or is about to make a hard-to-reverse decision wit | |
| Pricing Strategy Activate when: user says 'how should we price this', 'we should just charge more', 'our competitors charge X', 'willingness to pay', 'anchor price', 'value-b... | |
| Principal–Agent Problem Activate when: someone asks why an employee, executive, contractor, board member, or fund manager isn't acting in the org's interest; a compensation or incen... | |
| Prisoner's Dilemma Activate when: user asks 'why does everyone keep doing X when it's obviously bad for all of us', 'how do we get out of this race to the bottom', 'should we trust them not to defect', 'we'd both be better off cooperating but it never happens | |
| probabilistic-thinking Activate when: user says 'what are the odds,' 'base rate,' 'Bayesian update,' 'calibration,' or 'what's the probability'; user is making a forecast or estimating a conversion/close/hire/outcome probability; someone claims 'I'm 90% sure' wit | |
| proprietary-data-moat Activate when: user says 'is our data a moat?', 'how do we build up proprietary data?', 'how do we set up a data flywheel?', 'investors keep asking about our data defensibility', 'data network effects', or must decide whether to invest in c | |
| Ramen Profitability & Default Alive/Dead Activate when: a founder needs to know if the company survives without more funding; 'are we default alive or default dead', deciding to cut burn or raise, bootstrapping to survival; runway math. Do NOT activate when: the company is already | |
| Real Estate — Closing Experience (Peak-End) Design Activate when: a real estate agent wants clients who refer and return; designing the closing/handoff experience, milestone moments in a transaction; 'how do I get more referrals from happy clients'. Do NOT activate when: the transaction is | |
| Real Estate — Pricing & Price-Reduction Decision Activate when: a listing isn't selling and the agent must decide list price or a price reduction; 'should we drop the price', 'how much and when', days-on-market rising, showings without offers. Do NOT activate when: the property is priced | |
| Real Estate — Sphere-of-Influence Referral Ladder Activate when: a real estate agent wants repeat + referral business instead of chasing cold leads; 'where's my next deal coming from', building a sphere-of-influence / past-client nurture, database marketing. Do NOT activate when: the agent | |
| Real Estate — Transaction & Fair-Housing Checklist Activate when: a real estate agent is running a listing/transaction and must not skip disclosure, agency, and fair-housing steps; 'what do I need to disclose', writing an ad, handling an offer, closing coordination. Do NOT activate when: th | |
| reciprocity Activate when: someone is being unexpectedly generous before making a request; you're deciding whether to accept a gift, free sample, or unsolicited concession; you're designing a sales or fundraising sequence and want to give first; a nego | |
| red-queen-effect Activate when: user says 'we keep investing but market share won't move,' 'why does nobody make money in this industry,' 'our competitor copied us again within a year,' 'we improve but the gap stays the same,' or is evaluating whether to en | |
| Referral Loop Design — Turn Customers into a Channel Activate when: a founder wants customers to bring customers; 'how do we get referrals / word of mouth', designing a referral program, improving virality; loops, incentives, timing. Do NOT activate when: the product has weak retention/love ( | |
| Regression to the Mean Activate when: someone says 'things always bounce back,' wonders why an intervention seemed to work on a struggling team, is surprised their star performer regressed, is evaluating whether a coaching/bonus/firing had an effect, or is interp | |
| regret-minimization Activate when: user says 'what would my 80-year-old self think', 'if I never try this will I regret it', 'I keep hesitating but the math is clear', 'regret minimization', or faces a major hard-to-reverse life decision (career pivot, foundin | |
| Repeated Games & Reputation Activate when: user asks how to build trust with a repeat counterparty, whether to retaliate after a partner defected, how to design a reputation system, whether a long-term relationship can survive betrayal, or says 'shadow of the future / | |
| representativeness-heuristic Activate when: user says 'this person/startup looks like a winner', 'I know one when I see it', 'they have the profile of a great hire', 'this reminds me of [famous success]', or any judgment where a vivid profile drives a probability estim | |
| resource-integration-hierarchy Activate when: user says 'I feel stuck at a ceiling in my role,' 'what separates good managers from great ones,' 'why can't we solve this class of problem,' 'how do I operate at a higher level,' or a team is consistently reactive rather tha | |
| Resource-Time Compression Activate when: user says 'this will take years', 'we need to build this from scratch', 'we don't have the resources to move faster', 'how do we compress our timeline', 'competitors are already ahead and we can't catch up sequentially', or w |
24,901–24,950 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.