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 |
|---|---|
| Pulmonary Dynamic Flow-Volume Loop (FEF25-75) Skill alphaparkinc/genpark-personal-agent-pulmonary-dynamic-flow-volume-loop-meff-skill Enables deterministic calculation and interpretation of spirometry flow-volume loop metrics, including FEF25-75/MMEF, FEV1/FVC, and FEF50/FIF50 ratio, to classify obstructive patterns and small-airway or upper-airway limitations. | |
| Pulmonary Dynamic Hyperinflation (IC Tracking) Skill alphaparkinc/genpark-personal-agent-pulmonary-dynamic-hyperinflation-ic-skill Enables deterministic calculation of exertional Inspiratory Capacity drop, End-Expiratory Lung Volume air trapping, and ventilatory mechanics reserve through JSON-RPC tools for LLMs and autonomous agents. | |
| Pulmonary Single-Breath Diffusing Capacity (DLCO) Skill alphaparkinc/genpark-personal-agent-pulmonary-single-breath-diffusing-capacity-dlco-skill Enables computation of hemoglobin-corrected diffusing capacity and Krogh transfer coefficient from measured values, with ATS/ERS-compliant reference comparisons and membrane-versus-volume interpretation. | |
| Pupillary Light Reflex MCP Server alphaparkinc/genpark-personal-agent-pupil-light-reflex-pupillometry-skill Enables agents to compute deterministic constriction kinetics, autonomic tone, and alertness metrics from pupillometry inputs through native JSON-RPC tool integration. | |
| Renal Fractional Excretion of Sodium (FeNa) & Urea Skill alphaparkinc/genpark-personal-agent-renal-fractional-excretion-sodium-fena-skill Enables calculation of fractional sodium and urea excretion from serum and urine chemistries, automatically selecting the appropriate index during diuretic therapy and classifying renal hydration status. | |
| Renal Transtubular Potassium Gradient (TTKG) Skill alphaparkinc/genpark-personal-agent-renal-transtubular-potassium-gradient-ttkg-skill Enables calculation and physiological interpretation of distal tubular potassium secretion from urine and plasma potassium and osmolality, with validity checks and discrimination between aldosterone-related disorders and extra-renal potassi | |
| Hypercapnic Ventilatory Response (HCVR) MCP Server alphaparkinc/genpark-personal-agent-respiratory-chemoreflex-hypercapnic-hcv-skill Enables deterministic calculation of HCVR slope, central respiratory chemosensitivity, and CO2 tolerance from end-tidal CO2 and spirometry inputs. It also provides chemoreflex loop-gain stratification for personal-agent actions. | |
| Personal Agent Respiratory CO2 Tolerance BOLT Skill alphaparkinc/genpark-personal-agent-respiratory-co2-tolerance-bolti-skill Enables calculation of Body Oxygen Level Test scores, modeling of Bohr effect tissue oxygenation and hypercapnic chemoreceptor sensitivity, and prescription of Buteyko reduced-breathing exercises through MCP tools. | |
| Respiratory Inertance & Dynamic Compliance Skill alphaparkinc/genpark-personal-agent-respiratory-inertance-airway-compliance-skill Enables non-invasive deterministic evaluation of respiratory inertance, dynamic compliance, resonant frequency, and mechanical work of breathing through an MCP JSON-RPC tool for LLM and autonomous-agent use. | |
| Respiratory Mouth Occlusion Pressure (P0.1) MCP Server alphaparkinc/genpark-personal-agent-respiratory-mouth-occlusion-p01-drive-skill It enables deterministic calculation of 100 ms mouth occlusion pressure, P0.1/MIP ratio, and central medullary drive scores and classifications through JSON-RPC tool integration for LLMs and autonomous agents. | |
| respiratory-muscle-strength alphaparkinc/genpark-personal-agent-respiratory-muscle-strength-mip-mep-skill Enables computing maximal inspiratory and expiratory pressure percentages against Black & Hyatt predicted values from age and sex, then deriving a 0–100 diaphragmatic resilience index and status. Also produces inspiratory muscle training pr | |
| Retinal Vascular Box-Counting Fractal Dimension (Df) Skill alphaparkinc/genpark-personal-agent-retinal-vessel-branching-fractal-d-skill Enables deterministic analysis of retinal vessel segmentation data to quantify microvascular branching complexity and capillary rarefaction, exposing JSON-RPC tools for LLM and autonomous-agent workflows. | |
| salivary-alpha-amylase alphaparkinc/genpark-personal-agent-salivary-alpha-amylase-sympathetic-skill Enables computational neuroendocrine modeling of sAA biomarker timeseries to compute surge deltas, reactivity ratios, clearance velocity, and a 0–100 autonomic stress resilience index with breathing-protocol guidance. | |
| electrodermal-activity alphaparkinc/genpark-personal-agent-skin-conductance-electrodermal-eda-skill Enables analyzing EDA/GSR streams by extracting tonic skin conductance, detecting phasic SCR bursts, and computing an autonomic arousal index for personal agent monitoring. | |
| Personal Agent Sleep Debt Repayment Planner alphaparkinc/genpark-personal-agent-sleep-debt-repayment-planner-skill Enables modeling cumulative sleep deficits, estimating cognitive impairment through PVT attention lapses and BAC equivalence, auditing social jetlag, and generating circadian-safe gradual sleep repayment schedules. | |
| Somatosensory Hoffmann Reflex (H-Reflex) Skill alphaparkinc/genpark-personal-agent-somatosensory-h-reflex-excitability-skill Enables deterministic calculation of Hmax/Mmax amplitude ratios, reflex latency, and spinal alpha motoneuron pool excitability to assess central neuromuscular fatigue. | |
| Somatosensory Paired-Pulse Depression PPD Analysis alphaparkinc/genpark-personal-agent-somatosensory-paired-pulse-depression-ppd-skill This server analyzes neurophysiological evoked potential data to compute the Paired-Pulse Ratio (A2/A1) and evaluate synaptic inhibition. It helps quantify sensorimotor cortex gating and inhibitory tone across different recovery regimes. | |
| stdt-temporal-discrimination alphaparkinc/genpark-personal-agent-somatosensory-temporal-discrimination-skill Enables evaluation of tactile temporal discrimination thresholds from paired-pulse staircase data, including age-adjusted normative comparisons, cortical somatosensory gating indices, clinical tiers, and sensorimotor recovery directives. | |
| Somatosensory Trigeminal Blink Reflex (R1/R2) Skill alphaparkinc/genpark-personal-agent-somatosensory-trigeminal-blink-reflex-r1-r2-skill Enables deterministic calculation of early pontine R1 and late medullary R2/R2c latencies, with bilateral crossed pathway comparison and topographical lesion mapping for trigeminal, facial, and brainstem assessment. | |
| genpark-personal-agent-subscription-stealth-price-hike-detector-skill alphaparkinc/genpark-personal-agent-subscription-stealth-price-hike-detector-skill Enables auditing recurring bank and card subscription charges to detect stealth price increases, expired trial conversions, and calculate annualized budget leakage. It also generates retention negotiation dispute letters to help users reduc | |
| Personal Agent Subscription Zombie Pruner alphaparkinc/genpark-personal-agent-subscription-zombie-pruner-skill Enables users to audit recurring SaaS and streaming charges by calculating cost per use, flag dormant zombie subscriptions, and forecast five-year compound savings from canceled fees. | |
| Personal Agent Supplement Pharmacokinetic Halflife Skill alphaparkinc/genpark-personal-agent-supplement-pharmacokinetic-halflife-skill Enables modeling supplement pharmacokinetics, tracking elimination half-life and washout, evaluating competitive absorption conflicts, and generating optimized ingestion schedules. | |
| Personal Agent Tax Deduction & Freelancer Expense Categorizer alphaparkinc/genpark-personal-agent-tax-deduction-receipt-ocr-categorizer-skill Enables agents to audit bank transactions and receipts against IRS Schedule C expense categories, calculate deductible amounts and estimated tax savings, and surface audit-risk flags. | |
| Personal Agent Ultradian Rhythm Phase Forecaster MCP Server alphaparkinc/genpark-personal-agent-ultradian-rhythm-phase-forecaster-skill Enables forecasting of ultradian alertness peaks and troughs, modeling homeostatic sleep pressure against circadian drive to prescribe restorative nap durations that avoid sleep inertia. | |
| genpark-personal-agent-unified-autonomous-copilot-skill alphaparkinc/genpark-personal-agent-unified-autonomous-copilot-skill Enables MCP-compliant clients to run a personal AI copilot with agenda tracking, autonomous sandbox execution, ambient cue handling, fast reflex actions, and episodic memory. | |
| ventilatory-efficiency alphaparkinc/genpark-personal-agent-ventilatory-equivalent-ve-vco2-efficiency-skill Enables computational CPET analysis from gas exchange timeseries, including VE/VCO2 slope and intercept with R², pulmonary dead space fraction, V-slope anaerobic threshold detection, and a cardiorespiratory efficiency index for pacing direc | |
| Personal Agent Vocal Fatigue Acoustic Strain alphaparkinc/genpark-personal-agent-vocal-fatigue-acoustic-strain-skill Enables modeling of vocal fold collision doses, dysphonia and laryngeal fatigue risk, and personalized vocal rest and SOVT recovery protocols from speaking duration, sound level, pitch, cumulative speaking hours, and hydration. | |
| Personal Agent Zone 2 Cardiorespiratory Fitness Skill alphaparkinc/genpark-personal-agent-zone2-cardiorespiratory-fitness-skill Calculates Karvonen heart-rate corridors, estimates VO2max, models fat oxidation kinetics, and prescribes weekly mitochondrial longevity volume from biometrics and current aerobic activity. | |
| genpark-personal-communication-triage-sentinel-skill alphaparkinc/genpark-personal-communication-triage-sentinel-skill Enables agents to triage personal communications and email through multi-factor urgency scoring, VIP filtering, and context-aware executive auto-drafting. Runs deterministically as a zero-dependency MCP server over JSON-RPC stdio, avoiding | |
| genpark-personal-digital-hoarding-declutter-agent-skill alphaparkinc/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, then producing prioritized decluttering recommendations. | |
| genpark-personal-habit-streak-anti-fragility-skill alphaparkinc/genpark-personal-habit-streak-anti-fragility-skill Enables personal agents to track habits and receive adaptive micro-fallbacks that degrade gracefully when a streak is missed, rather than letting the user abandon it. Surfaces prioritized queues and elastic recommendations through MCP-compa | |
| genpark-personal-inbox-cognitive-triage-skill alphaparkinc/genpark-personal-inbox-cognitive-triage-skill This MCP server enables classification of personal inbox messages by actionability, effort duration, and urgency, producing prioritized queues and elastic recommendations that help prevent attention fragmentation. | |
| genpark-personal-knowledge-vault-graph-compiler-skill alphaparkinc/genpark-personal-knowledge-vault-graph-compiler-skill Enables agents to compile a personal knowledge vault into a graph with bi-directional link indexing by parsing [[wikilinks]], tags, and unlinked mentions across notes. Runs as a zero-dependency MCP server, so MCP clients can build and query | |
| genpark-personal-sleep-recovery-chronotype-coach-skill alphaparkinc/genpark-personal-sleep-recovery-chronotype-coach-skill Enables users to calculate chronotype-aligned sleep schedules, optimize 90-minute ultradian cycles, determine caffeine cutoffs, and plan light exposure for better recovery and circadian alignment. | |
| genpark-personal-spending-impulse-friction-guard-skill alphaparkinc/genpark-personal-spending-impulse-friction-guard-skill Enables personal agents and users to evaluate purchase impulses by applying cooling-off friction timers and converting spending amounts into net work-hour wage equivalents. It returns deterministic, actionable decision output that helps del | |
| genpark-personal-vault-zero-knowledge-sanitizer-skill alphaparkinc/genpark-personal-vault-zero-knowledge-sanitizer-skill Enables local zero-knowledge encryption of a personal vault and sanitization of PII such as credentials, credit cards, and addresses before dispatch to cloud LLMs, with client-side rehydration of masked data. | |
| genpark-personalized-video-sales-outreach-script-planner-skill alphaparkinc/genpark-personalized-video-sales-outreach-script-planner-skill Enables AI agents to generate personalized video sales outreach scripts and storyboards in a Tavus style, with deterministic, dependency-free execution over MCP. | |
| genpark-predictive-churn-clv-regression-synthesizer-skill alphaparkinc/genpark-predictive-churn-clv-regression-synthesizer-skill Enables MCP-compliant clients to run deterministic customer churn prediction and 12-month CLV regression synthesis through a zero-dependency Python skill. | |
| genpark-proactive-intent-disambiguation-clarifier-skill alphaparkinc/genpark-proactive-intent-disambiguation-clarifier-skill Enables autonomous agents to detect under-specified user goals, gauge reversibility and risk, and present minimal multiple-choice clarifications before committing to high-stakes execution. | |
| GenPark AI Agent Skill - Process Cgroup OOM & CPU Quota Arbiter alphaparkinc/genpark-process-cgroup-oom-cpu-quota-arbiter-skill Enables strict resource governance for AI agent processes using Linux cgroup v2, enforcing CPU bandwidth, memory limits, and process limits to prevent resource overconsumption, runaway loops, and fork bombs. | |
| genpark-product-geoip-currency-tax-nexus-normalizer-skill alphaparkinc/genpark-product-geoip-currency-tax-nexus-normalizer-skill Enables cross-border Geo-IP-based currency conversion and dynamic VAT/tax nexus calculation, integrating with Stripe Tax. | |
| genpark-product-review-sentiment-analyzer-skill alphaparkinc/genpark-product-review-sentiment-analyzer-skill Enables aspect-level sentiment mining from customer reviews and produces satisfaction radar breakdowns with structured output for AI agents. | |
| genpark-prompt-injection-jailbreak-neutralizer-skill alphaparkinc/genpark-prompt-injection-jailbreak-neutralizer-skill Enables deterministic detection and neutralization of adversarial prompt injections and override attempts in AI agent workflows via a zero-dependency MCP server, providing structured telemetry and low-latency validation. | |
| genpark-pull-request-breaking-api-change-sentinel-skill alphaparkinc/genpark-pull-request-breaking-api-change-sentinel-skill Analyzes Git pull request diffs to detect breaking REST and GraphQL API schema changes, providing deterministic AST-level code review and breaking change alerts for CI/CD workflows. | |
| GenParkQuantBlackLittermanPortfolioRebalancer alphaparkinc/genpark-quant-black-litterman-portfolio-rebalancer-skill Enables quantitative market-microstructure analysis and portfolio optimization through MCP, covering concentrated liquidity, L2 orderbook imbalance, triangular arbitrage detection, and Bayesian allocation with covariance and risk constraint | |
| genpark-quant-concentrated-liquidity-tick-optimizer-skill alphaparkinc/genpark-quant-concentrated-liquidity-tick-optimizer-skill Enables real-time optimization of Uniswap v3/v4 concentrated liquidity ticks by balancing fee APY against impermanent loss under asset volatility, alongside L2 orderbook imbalance metrics, triangular arbitrage detection, and Bayesian portfo | |
| GenPark Quant Orderbook L2 Microstructure Imbalance MCP Server alphaparkinc/genpark-quant-orderbook-l2-microstructure-imbalance-skill Enables computing weighted orderbook imbalance, micro-price, and market-order VWAP execution slippage, alongside concentrated liquidity optimization, negative-cycle triangular arbitrage detection, and Bayesian Black-Litterman portfolio reba | |
| GenParkQuantTriangularArbitrageBellmanFordDetector alphaparkinc/genpark-quant-triangular-arbitrage-bellman-ford-detector-skill Enables real-time concentrated liquidity optimization, L2 orderbook imbalance metrics, negative-cycle triangular arbitrage detection, and Bayesian Black-Litterman portfolio rebalancing through the Model Context Protocol. | |
| genpark-quantized-model-vram-tensor-parallel-estimator-skill alphaparkinc/genpark-quantized-model-vram-tensor-parallel-estimator-skill Enables AI agents and MCP clients to estimate VRAM footprint and tensor parallelization requirements for quantized llama.cpp models, returning structured outputs without external dependencies. | |
| genpark-quantum-gate-hadamard-pauli-cnot-engine-skill alphaparkinc/genpark-quantum-gate-hadamard-pauli-cnot-engine-skill Enables simulation of quantum circuits with single-qubit Hadamard and Pauli gates, CNOT entanglement, state-vector evolution, Born-rule measurement, Bell-state generation, and Grover amplitude amplification. Integrates natively with MCP cli |
27,601–27,650 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.