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 |
|---|---|
| post-exercise-epoc alpha-park/genpark-personal-agent-post-exercise-epoc-recovery-skill Enables deterministic modeling of excess post-exercise oxygen consumption, bi-exponential recovery kinetics, cumulative oxygen debt and calorie burn, and post-workout fuel partitioning to guide hydration and refueling directives. | |
| postural-sway alpha-park/genpark-personal-agent-postural-sway-center-of-pressure-skill This server processes 2D Center of Pressure (COP) data to calculate metrics such as 95% confidence ellipse area, sway velocity, and the Romberg Quotient for postural stability analysis. | |
| Video Head Impulse Test (vHIT) & Vestibular Gain Skill alpha-park/genpark-personal-agent-postural-vestibular-head-impulse-vhit-skill Provides deterministic JSON-RPC tools for calculating angular VOR gain from head and eye velocity, quantifying corrective saccades, and assessing gaze stability for LLM and autonomous agent workflows. | |
| Forced Oscillation Technique (FOT / IOS) MCP Server alpha-park/genpark-personal-agent-pulmonary-airway-resistance-fot-oscillometry-skill Enables deterministic calculation and classification of respiratory impedance, peripheral airway resistance (R5–R20), and reactance from oscillometry measurements through JSON-RPC tools for LLM and agent workflows. | |
| genpark-personal-agent-pulmonary-alveolar-dead-space-bohr-enghoff-skill alpha-park/genpark-personal-agent-pulmonary-alveolar-dead-space-bohr-enghoff-skill This server provides a deterministic calculation for the Bohr-Enghoff Alveolar Dead Space Fraction (V_D/V_T) and the alveolar-arterial oxygen gradient. It applies physiological equations and the Alveolar Gas Equation to evaluate ventilation | |
| Pulmonary Closing Volume & Nitrogen Washout (SBN2) MCP Server alpha-park/genpark-personal-agent-pulmonary-closing-volume-nitrogen-washout-skill Enables agents to compute single-breath nitrogen washout closing volume, closing capacity, age-predicted reference intervals, and peripheral small airway patency through deterministic JSON-RPC tools. | |
| Pulmonary Dynamic Airway Closing Pressure Skill alpha-park/genpark-personal-agent-pulmonary-dynamic-airway-closing-pressure-pel-skill Enables deterministic calculation of dynamic airway closing pressure, static recoil pressure, and transmural gradients using Mead's Equal Pressure Point formulation, with JSON-RPC stdio access for assessing dynamic airway closure risk. | |
| Pulmonary Dynamic Flow-Volume Loop (FEF25-75) Skill alpha-park/genpark-personal-agent-pulmonary-dynamic-flow-volume-loop-meff-skill Enables deterministic spirometry analysis through MCP JSON-RPC, calculating mid-expiratory flow metrics and classifying flow-volume loop patterns such as obstruction, variable extrathoracic obstruction, and isolated small airway disease. | |
| Pulmonary Dynamic Hyperinflation (IC Tracking) Skill alpha-park/genpark-personal-agent-pulmonary-dynamic-hyperinflation-ic-skill Enables deterministic calculation of exertional Inspiratory Capacity drop, End-Expiratory Lung Volume air trapping, inspiratory reserve volume compression, and ventilatory mechanics/dyspnea risk through JSON-RPC tools for LLM agents. | |
| Pulmonary Single-Breath Diffusing Capacity (DLCO) Skill alpha-park/genpark-personal-agent-pulmonary-single-breath-diffusing-capacity-dlco-skill Enables calculation of single-breath DLCO, ATS/ERS hemoglobin-corrected values, and KCO, with comparisons to predicted references for differentiating alveolar-capillary membrane impairment from volume restriction. | |
| Quantitative Pupillary Light Reflex (PLR) Skill alpha-park/genpark-personal-agent-pupil-light-reflex-pupillometry-skill Enables LLMs and autonomous agents to compute validated pupillometric metrics—constriction velocity, amplitude percentage, and redilation rate—and assess autonomic balance and central nervous system alertness through deterministic JSON-RPC | |
| Renal Fractional Excretion of Sodium (FeNa) & Urea Skill alpha-park/genpark-personal-agent-renal-fractional-excretion-sodium-fena-skill Enables computation of sodium and urea fractional excretion from serum and urine chemistries, automatic diuretic-aware switching to urea-based assessment, and classification of prerenal hypoperfusion versus intrinsic acute tubular necrosis. | |
| Renal Transtubular Potassium Gradient (TTKG) Skill alpha-park/genpark-personal-agent-renal-transtubular-potassium-gradient-ttkg-skill Enables calculation of the urinary-to-plasma potassium gradient and interpretation of distal tubular potassium secretion and aldosterone action from urine and plasma electrolyte and osmolality inputs. | |
| Hypercapnic Ventilatory Response (HCVR) Skill alpha-park/genpark-personal-agent-respiratory-chemoreflex-hypercapnic-hcv-skill Enables personal agents to deterministically compute respiratory chemoreflex sensitivity from end-tidal CO2 and ventilation changes, classify CO2 tolerance, and assess loop-gain stability through native JSON-RPC tools. | |
| Respiratory Inertance & Dynamic Compliance Skill alpha-park/genpark-personal-agent-respiratory-inertance-airway-compliance-skill Enables deterministic, non-invasive evaluation of respiratory system inertance, dynamic compliance, resonant frequency, and mechanical work of breathing through an MCP-compatible interface. | |
| Respiratory Mouth Occlusion Pressure (P0.1) Skill alpha-park/genpark-personal-agent-respiratory-mouth-occlusion-p01-drive-skill Enables deterministic evaluation of 100 ms mouth occlusion pressure, P0.1/MIP ratio, and central medullary drive through JSON-RPC tools for personal-agent ventilatory assessments. | |
| respiratory-muscle-strength alpha-park/genpark-personal-agent-respiratory-muscle-strength-mip-mep-skill Enables assessment of maximal inspiratory and expiratory pressures against normative predictions, calculation of a diaphragmatic resilience score, and generation of inspiratory muscle training prescriptions. | |
| Retinal Vascular Box-Counting Fractal Dimension (Df) Skill alpha-park/genpark-personal-agent-retinal-vessel-branching-fractal-d-skill Enables deterministic calculation of retinal microvascular box-counting fractal dimension, arborization complexity, and vascular rarefaction from box-size and box-count data through JSON-RPC tools for LLM and autonomous agent workflows. | |
| salivary-alpha-amylase alpha-park/genpark-personal-agent-salivary-alpha-amylase-sympathetic-skill Enables deterministic assessment of acute sympathetic reactivity from biomarker time series, including surge delta, reactivity ratio, trapezoidal AUC, 30-minute clearance velocity, and a 0–100 resilience index with breathing-protocol guidan | |
| electrodermal-activity alpha-park/genpark-personal-agent-skin-conductance-electrodermal-eda-skill Enables agents to process skin conductance signals, extract tonic SCL, detect phasic SCR bursts, and score autonomic arousal for calming protocols. | |
| Personal Agent Sleep Debt Repayment Planner alpha-park/genpark-personal-agent-sleep-debt-repayment-planner-skill Enables users to model cumulative sleep deficits, estimate cognitive impairment using Van Dongen PVT kinetics, audit social jetlag, and generate circadian-safe gradual sleep repayment schedules. | |
| Somatosensory F-Wave Chronodispersion Skill alpha-park/genpark-personal-agent-somatosensory-f-wave-chronodispersion-skill Enables deterministic calculation of ENMG F-wave chronodispersion, persistence, and proximal motor nerve root conduction integrity, with native JSON-RPC tool integration for LLMs and autonomous agents. | |
| Somatosensory H-Reflex MCP Server alpha-park/genpark-personal-agent-somatosensory-h-reflex-excitability-skill Calculates Hoffmann reflex recruitment ratios, onset latency, and spinal motoneuron pool excitability from amplitude measurements, exposing deterministic JSON-RPC tools for LLM and autonomous-agent workflows. | |
| Somatosensory Paired-Pulse Depression (PPD) Skill alpha-park/genpark-personal-agent-somatosensory-paired-pulse-depression-ppd-skill Enables calculation of the somatosensory paired-pulse depression ratio (A2/A1), synaptic inhibition percentage, and interval-sensitive GABAergic gating assessments via an MCP JSON-RPC 2.0 stdio server. | |
| stdt-temporal-discrimination alpha-park/genpark-personal-agent-somatosensory-temporal-discrimination-skill Enables evaluation of tactile paired-pulse staircase data to compute composite somatosensory temporal discrimination thresholds, age-adjusted normative ratios, cortical sensory gating indices, clinical tiers, and sensorimotor recovery direc | |
| Somatosensory Trigeminal Blink Reflex (R1/R2) Skill alpha-park/genpark-personal-agent-somatosensory-trigeminal-blink-reflex-r1-r2-skill Enables deterministic calculation of early pontine (R1) and late medullary (R2/R2c) latencies, bilateral crossed pathway tracking, and topographical lesion mapping for cranial nerve and brainstem integrity assessment. | |
| genpark-personal-agent-subscription-stealth-price-hike-detector-skill alpha-park/genpark-personal-agent-subscription-stealth-price-hike-detector-skill Enables users to audit recurring bank/card subscription charges, detect sneaky fee increases or expired-trial conversions, calculate annualized budget leakage, and generate retention negotiation dispute letters. | |
| Personal Agent Subscription Zombie Pruner alpha-park/genpark-personal-agent-subscription-zombie-pruner-skill Enables users to audit recurring personal SaaS and streaming costs by cost-per-use, detect dormant charges, and forecast five-year compound savings from cancellations. | |
| Personal Agent Tax Deduction & Freelancer Expense Categorizer alpha-park/genpark-personal-agent-tax-deduction-receipt-ocr-categorizer-skill Enables auditing of bank transactions and receipts against IRS Schedule C expense categories such as home office, software, mileage, and meals. It calculates deductible amounts and estimated tax savings while flagging potential audit risks. | |
| genpark-personal-agent-ultradian-rhythm-phase-forecaster-skill alpha-park/genpark-personal-agent-ultradian-rhythm-phase-forecaster-skill Enables forecasting of 90-minute ultradian rhythm phases, alertness peaks and dips, and restorative nap windows through two-process sleep-wakefulness modeling. | |
| genpark-personal-agent-unified-autonomous-copilot-skill alpha-park/genpark-personal-agent-unified-autonomous-copilot-skill Provides a zero-dependency MCP interface that equips personal AI agents with agenda tracking, autonomous sandbox execution, ambient cue handling, fast reflex intent processing, and episodic memory. | |
| ventilatory-efficiency alpha-park/genpark-personal-agent-ventilatory-equivalent-ve-vco2-efficiency-skill Enables computational CPET analysis by calculating VE/VCO2 ventilatory equivalent slope, pulmonary dead space fraction, V-slope anaerobic threshold, and a cardiorespiratory efficiency index to support Zone 2 and threshold pacing directives. | |
| genpark-personal-agent-vocal-fatigue-acoustic-strain-skill alpha-park/genpark-personal-agent-vocal-fatigue-acoustic-strain-skill Enables quantifying vocal fold collision doses and dysphonia risk from speaking duration, sound level, pitch, hydration, and cumulative vocal load, then prescribing SOVT-based vocal rest and recovery protocols. | |
| genpark-personal-communication-triage-sentinel-skill alpha-park/genpark-personal-communication-triage-sentinel-skill Enables autonomous triage of personal communications and email through deterministic multi-factor urgency scoring, VIP filtering, and context-aware executive auto-drafting. It plugs into any MCP-compliant client to resolve routine communica | |
| genpark-personal-digital-hoarding-declutter-agent-skill alpha-park/genpark-personal-digital-hoarding-declutter-agent-skill Enables personal AI agents to triage digital clutter by classifying orphaned downloads, duplicate screenshots, and stale browser bookmarks, returning a prioritized decluttering queue with actionable recommendations. It runs locally as a zer | |
| genpark-personal-habit-streak-anti-fragility-skill alpha-park/genpark-personal-habit-streak-anti-fragility-skill Enables personal AI agents and users to reinforce habits, triage decisions, and prevent streak-break abandonment by generating adaptive micro-fallbacks and elastic recommendations. | |
| genpark-personal-inbox-cognitive-triage-skill alpha-park/genpark-personal-inbox-cognitive-triage-skill Enables personal AI agents to triage inbox items by classifying their actionability, effort duration, and urgency, producing a prioritized queue with elastic recommendations. It plugs into MCP-compliant clients such as Claude Desktop and Cu | |
| genpark-personal-knowledge-vault-graph-compiler-skill alpha-park/genpark-personal-knowledge-vault-graph-compiler-skill Enables agents to compile a personal knowledge vault into a linked graph by indexing bi-directional links and parsing [[wikilinks]], tags, and unlinked mentions across notes. It runs deterministically over MCP without external dependencies, | |
| genpark-personal-sleep-recovery-chronotype-coach-skill alpha-park/genpark-personal-sleep-recovery-chronotype-coach-skill Enables chronotype-aligned circadian sleep architecture calculations that optimize 90-minute ultradian cycles, caffeine cutoffs, and light exposure for personalized sleep recovery coaching. | |
| Personal Spending Impulse Guard alpha-park/genpark-personal-spending-impulse-friction-guard-skill Enables personal AI agents to evaluate purchase impulses by applying cooling-off friction timers and converting costs into net work-hour wage equivalents. It returns prioritized, deterministic recommendations that help users pause, reflect, | |
| genpark-personal-vault-zero-knowledge-sanitizer-skill alpha-park/genpark-personal-vault-zero-knowledge-sanitizer-skill Enables agents to encrypt and sanitize sensitive data such as credentials, credit card numbers, and addresses locally before dispatching prompts to cloud LLMs, then rehydrate the masked values client-side. It runs deterministically with zer | |
| genpark-proactive-intent-disambiguation-clarifier-skill alpha-park/genpark-proactive-intent-disambiguation-clarifier-skill Enables autonomous agents to detect under-specified, high-stakes user goals, assess their reversibility and risk, and construct minimal multiple-choice clarifications before executing. Runs as a zero-dependency MCP server or importable Pyth | |
| genpark-process-cgroup-oom-cpu-quota-arbiter-skill alpha-park/genpark-process-cgroup-oom-cpu-quota-arbiter-skill Resource governor configuring Linux cgroup v2 controllers and arbitrating resource overconsumption, runaway loops, and fork bombs. | |
| genpark-product-geoip-currency-tax-nexus-normalizer-skill alpha-park/genpark-product-geoip-currency-tax-nexus-normalizer-skill Enables cross-border Geo-IP currency conversion and dynamic VAT/tax nexus calculation, exposing deterministic, zero-dependency tools for AI agents via the Model Context Protocol. | |
| genpark-product-review-sentiment-analyzer-skill alpha-park/genpark-product-review-sentiment-analyzer-skill Enables aspect-level sentiment mining of customer reviews, producing satisfaction radar breakdowns and structured sentiment analysis through MCP-compatible clients. | |
| genpark-prompt-injection-jailbreak-neutralizer-skill alpha-park/genpark-prompt-injection-jailbreak-neutralizer-skill Enables MCP-compatible clients to deterministically neutralize adversarial prompt injections and jailbreak overrides with zero-dependency, sub-millisecond heuristic analysis. | |
| genpark-pull-request-breaking-api-change-sentinel-skill alpha-park/genpark-pull-request-breaking-api-change-sentinel-skill Enables automated semantic analysis of Git pull request diffs to detect breaking REST/GraphQL API schema changes, integrating with MCP-compatible clients for AI-driven code review. | |
| Black-Litterman Portfolio Rebalancer MCP Server alpha-park/genpark-quant-black-litterman-portfolio-rebalancer-skill Enables agents to compute Bayesian Black-Litterman portfolio rebalancing that blends market equilibrium with subjective views under covariance and slippage/drawdown constraints. Also exposes quantitative microstructure tools such as L2 orde | |
| GenParkQuantConcentratedLiquidityTickOptimizer alpha-park/genpark-quant-concentrated-liquidity-tick-optimizer-skill Enables MCP clients to optimize Uniswap v3/v4 tick ranges by balancing fee APY against impermanent loss under asset volatility, while providing L2 orderbook imbalance, triangular arbitrage, and Bayesian portfolio rebalancing analytics. | |
| GenParkQuantOrderbookL2MicrostructureImbalance alpha-park/genpark-quant-orderbook-l2-microstructure-imbalance-skill Enables real-time L2 orderbook microstructure analysis with weighted imbalance and micro-price, concentrated liquidity optimization, triangular arbitrage detection, and Bayesian portfolio rebalancing through MCP tools. |
27,151–27,200 of 115,409
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.