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 |
|---|---|
| Personal Agent Circadian Lux Melatonin Onset alpha-park/genpark-personal-agent-circadian-lux-melatonin-onset-skill Enables modeling of ocular light exposure, forecasting melatonin suppression delays from digital screens, and generating timed digital-sunset schedules for sleep readiness. | |
| circadian-phase-angle alpha-park/genpark-personal-agent-circadian-phase-angle-entrainment-skill Enables users to calculate circadian phase angles of entrainment, score internal circadian desynchrony, and derive photic PRC-based advance, delay, and curfew guidance from biomarker and sleep schedule inputs. | |
| genpark-personal-agent-cognitive-load-pomodoro-balancer-skill alpha-park/genpark-personal-agent-cognitive-load-pomodoro-balancer-skill Enables computing physiologically adaptive focus durations and personalized micro-break prescriptions by modeling exponential mental fatigue and Yerkes-Dodson arousal for sustainable work-rest cycles. | |
| PersonalAgentCredentialEntropyExposureFiduciary alpha-park/genpark-personal-agent-credential-entropy-exposure-fiduciary-skill Enables users to score credential strength using NIST-style bit entropy and keyspace calculations, estimate GPU brute-force cracking timelines, audit cross-account password reuse blast radius, and perform k-anonymity SHA-256 prefix privacy | |
| Cutaneous Cold-Induced Vasodilation (CIVD) Skill alpha-park/genpark-personal-agent-cutaneous-cold-induced-vasodilation-civd-skill Enables deterministic screening of peripheral vasomotor cold response by computing rebound amplitude, hunting index, resilience scores, and classifications from local cold-immersion temperature and onset-time measurements. | |
| Cutaneous Galvanic Skin Conductance (EDA/GSR) Skill alpha-park/genpark-personal-agent-cutaneous-galvanic-skin-conductance-tonic-phasic-skill Enables analysis of raw skin conductance series by separating tonic baseline from phasic peaks, screening SCR peaks, and classifying sympathetic arousal and cognitive workload through MCP JSON-RPC 2.0 stdio. | |
| Cutaneous Laser Speckle Contrast Imaging (LSCI) Skill alpha-park/genpark-personal-agent-cutaneous-laser-speckle-contrast-imaging-lsci-skill Enables calculation of speckle contrast, blood flow index, and laser speckle perfusion units from local pixel intensity kernels, with exposure compensation and microvascular perfusion guidance through an MCP JSON-RPC stdio server. | |
| cutaneous-microcirculation alpha-park/genpark-personal-agent-cutaneous-microcirculation-laser-doppler-skill Enables analysis of cutaneous laser Doppler thermal hyperemia, axon-reflex peaks, and endothelial nitric oxide bioavailability, generating CVC metrics, microvascular health scores, and classification guidance. | |
| Cutaneous Microdialysis Perfusion Recovery Skill alpha-park/genpark-personal-agent-cutaneous-microdialysis-perfusion-recovery-skill Enables deterministic calculation of zero-net-flux in vivo extraction fraction and interstitial concentration for cutaneous microdialysis using Bungay transport modeling, exposed through an MCP JSON-RPC stdio server. | |
| Cutaneous Microvascular Reactive Hyperemia (PORH) MCP Server alpha-park/genpark-personal-agent-cutaneous-microvascular-post-occlusive-reactive-hyperemia-skill Enables deterministic evaluation of cutaneous post-occlusive reactive hyperemia from laser Doppler flowmetry inputs, calculating the PU_peak/PU_base amplification ratio, time to peak, recovery kinetics, and microvascular endothelial scores | |
| Cutaneous Tactile Sensitivity & Mechanical Allodynia (Von Frey) Skill alpha-park/genpark-personal-agent-cutaneous-tactile-allodynia-vonfrey-skill Enables agents to compute Semmes-Weinstein markings from applied monofilament force and reported detection, then classify tactile acuity and mechanical allodynia through JSON-RPC tools. | |
| Cutaneous Vibration Perception Threshold (VPT) Skill alpha-park/genpark-personal-agent-cutaneous-tactile-vibration-pallesthesia-skill Enables deterministic scoring of age-adjusted tuning-fork readings and classification of large-fiber sensory neuropathy through JSON-RPC tools for LLM and autonomous agent workflows. | |
| Quantitative Sensory Testing (QST) Thermal Threshold Skill alpha-park/genpark-personal-agent-cutaneous-thermal-quantitative-qset-skill Enables deterministic calculation and classification of thermal detection thresholds, thermal sensory limen, and small-fiber neuropathy screening from standardized inputs through MCP tools. | |
| TEWL MCP Server alpha-park/genpark-personal-agent-cutaneous-transepidermal-water-loss-tewl-skill Exposes tools that compute cutaneous transepidermal water loss vapor flux and a stratum corneum barrier integrity score from dual surface/ambient temperature and humidity sensor readings, using Magnus-Tetens saturation pressures and Fick's | |
| two-point-discrimination alpha-park/genpark-personal-agent-cutaneous-two-point-discrimination-skill Enables deterministic evaluation of static and moving tactile spatial acuity thresholds, mechanoreceptive density estimates, and peripheral neuropathy-related sensory guidance. It converts discrimination-distance and response-ratio trial in | |
| Cutaneous Venous Refilling Time (VRT) & Venous Pump Power (VPP) Skill alpha-park/genpark-personal-agent-cutaneous-venous-refilling-time-ppg-reflux-skill Enables assessment of lower-extremity chronic venous insufficiency, valvular competence, and calf muscle pump performance from digital photoplethysmography data, including reflux grading and tourniquet localization. | |
| genpark-personal-agent-dual-cognition-orchestrator-skill alpha-park/genpark-personal-agent-dual-cognition-orchestrator-skill Enables personal AI agents to route routine, reflexive decisions through fast deterministic System-1 cognition while reserving frontier LLM calls for ambiguous multi-hop plans. Combines ambient perception, decayed episodic memory with contr | |
| Personal Agent Dunbar Relationship Cadence alpha-park/genpark-personal-agent-dunbar-relationship-cadence-skill Enables organizing personal contacts into concentric social layers, estimating warmth decay via an exponential half-life model, and scheduling mindful reconnection touchpoints within a weekly cognitive bandwidth. | |
| Personal Agent Autonomous Smart Pantry & Dietary Grocery Replenisher alpha-park/genpark-personal-agent-dynamic-grocery-pantry-auto-replenisher-skill Enables tracking of household food consumption, expiration decay, and dietary filters to synthesize optimized grocery carts within budget constraints. | |
| genpark-personal-agent-dynamic-hrv-dfa-alpha1-intensity-fractal-skill alpha-park/genpark-personal-agent-dynamic-hrv-dfa-alpha1-intensity-fractal-skill Enables calculation of short-term DFA alpha-1 fractal scaling from RR-interval series to identify the aerobic threshold during endurance exercise, using current power and heart rate as context. | |
| dynamic-postural-stability alpha-park/genpark-personal-agent-dynamic-postural-stability-index-skill Enables calculation of composite and directional dynamic postural stability indices, jump-landing shock attenuation, impact load multipliers, and time to stabilization from triaxial force-plate data. | |
| Personal Agent Weather & Itinerary-Adaptive Capsule Wardrobe Packer alpha-park/genpark-personal-agent-dynamic-wardrobe-capsule-packer-skill Enables agents to generate carry-on-compliant, interchangeable packing lists from multi-day forecasts, destination dress codes, and trip duration. It supports itinerary-aware outfit selection for events such as conferences, galas, and outdo | |
| Electroretinogram Photopic Negative Response (PhNR) Skill alpha-park/genpark-personal-agent-electroretinogram-photopic-negative-erg-skill Enables deterministic analysis of full-field electroretinogram recordings to extract a-wave, b-wave, PhNR trough and latency, compute PhNR/b-wave ratios, and stratify retinal ganglion cell strain through JSON-RPC tools. | |
| Personal Agent Financial Runway Monte Carlo alpha-park/genpark-personal-agent-financial-runway-monte-carlo-skill Enables users to run stochastic cash runway simulations, estimate ruin probability and low-percentile wealth, and compute safe discretionary spending caps and emergency liquidity buffers. | |
| PersonalAgentLayoverItinerarySynthesizer alpha-park/genpark-personal-agent-flight-layover-micro-itinerary-synthesizer-skill Evaluates airport layover time budgets of 3–8 hours, factoring immigration clearance buffers and round-trip metro/taxi latencies into a net usable exploration window. Curates timed sightseeing and culinary micro-tours with safety advice and | |
| Personal Agent Focus Recovery Binaural Beats MCP Server alpha-park/genpark-personal-agent-focus-recovery-binaural-beats-skill Enables calculation of binaural beat frequencies for target cognitive states and scheduling of phased focus and recovery entrainment protocols using stereo carrier pairings. | |
| Personal Agent Gift Curator & Social Graph Occasion Recommender alpha-park/genpark-personal-agent-gift-curator-social-graph-recommender-skill Enables users to generate tailored gift suggestions and handwritten card messages from relationship context, recipient interests, urgency, and budget. It also factors social connections and milestones into occasion planning. | |
| Personal Agent Glycemic Load Macro Balancer alpha-park/genpark-personal-agent-glycemic-load-macro-balancer-skill Enables computing composite glycemic load for multi-ingredient meals, modeling protein and fat attenuation of glucose spikes, and forecasting post-prandial fatigue and stable focus hours to guide meal and task scheduling. | |
| Personal Agent Habit Elasticity Tracker alpha-park/genpark-personal-agent-habit-elasticity-tracker-skill Enables users to model Lally habit automaticity curves, estimate behavioral friction price elasticity, and derive minimum viable micro-habits that protect streaks on low-energy days. | |
| Personal Agent Hydration Osmolality Electrolyte alpha-park/genpark-personal-agent-hydration-osmolality-electrolyte-skill Enables estimating sweat rate and sodium loss, modeling subclinical dehydration cognitive deficits, and generating personalized hourly fluid and electrolyte replenishment schedules. | |
| genpark-personal-agent-indoor-co2-cognitive-ventilation-skill alpha-park/genpark-personal-agent-indoor-co2-cognitive-ventilation-skill Enables users to model indoor CO2 mass balance, estimate cognitive impairment from exposure, and schedule ventilation purges through an MCP interface. | |
| genpark-personal-agent-information-diet-entropy-pruner-skill alpha-park/genpark-personal-agent-information-diet-entropy-pruner-skill This MCP server enables users to analyze personal reading and media streams by computing Shannon entropy, detecting Jaccard redundancy and echo chambers, and ranking content sources by decibel SNR to produce pruning recommendations and high | |
| Personal Agent Intermittent Fasting Autophagy Window Skill alpha-park/genpark-personal-agent-intermittent-fasting-autophagy-window-skill Enables users to estimate fasting metabolic phases, BHB ketone kinetics, autophagy activation scores, and optimal circadian eating windows from fasting duration and sleep constraints. | |
| Personal Agent Micro Break Ocular Strain Ergonomics Skill alpha-park/genpark-personal-agent-micro-break-ocular-strain-ergonomics-skill Enables modeling ciliary eye-muscle fatigue and suppressed blink rates, estimating tear-film break-up, scheduling 20-20-20 optical recovery breaks, and calculating Hansraj cervical-spine torque for ergonomic posture remediation. | |
| Surface Electromyography (sEMG) RMS Workload Skill alpha-park/genpark-personal-agent-muscle-electromyography-root-mean-square-emg-skill Provides deterministic JSON-RPC tools for evaluating muscle activation, MVC-normalized amplitude, spectral fatigue, and occupational strain from surface EMG inputs. | |
| Muscle Mechanomyography (MMG) & Contractile Stiffness Skill alpha-park/genpark-personal-agent-muscle-mechanomyography-mmg-stiffness-skill Enables deterministic evaluation of MMG amplitude and spectral metrics, electromechanical delay, and peripheral muscular fatigue kinetics through native JSON-RPC tools for LLMs and autonomous agents. | |
| muscle-oxygenation alpha-park/genpark-personal-agent-muscle-oxygenation-nirs-smo2-skill Enables computational NIRS muscle oxygenation modeling, including SmO2 desaturation profiling, hyperemic reperfusion kinetics, and rest-to-work pacing recommendations through MCP tools. | |
| Personal Agent Non-Sleep Deep Rest (NSDR) Protocol Skill alpha-park/genpark-personal-agent-non-sleep-deep-rest-nsdr-protocol-skill Enables users to model neuro-autonomic state shifts, project alpha/theta entrainment windows, and estimate striatal dopamine replenishment from session and respiratory-rate inputs. | |
| Ocular Accommodative Microfluctuations (AMF) Skill alpha-park/genpark-personal-agent-ocular-accommodative-microfluctuations-amf-skill Enables analysis of continuous diopter time series through MCP JSON-RPC stdio, computing spectral power, high-/low-frequency band ratios, and a ciliary fatigue index for ergonomic classification. | |
| Ocular Cone Contrast Test (CCT) Skill alpha-park/genpark-personal-agent-ocular-cone-contrast-test-color-vision-cct-skill Enables deterministic calculation of isolated L-, M-, and S-cone contrast thresholds and conversion into calibrated 0–100 CCT score indices for assessing photoreceptor integrity and selective color-vision defects. | |
| Visual Contrast Sensitivity (Pelli-Robson) MCP Server alpha-park/genpark-personal-agent-ocular-contrast-sensitivity-pelli-robson-skill Enables agents to deterministically calculate Pelli-Robson log contrast sensitivity scores, Weber contrast thresholds, visual functional acuity, and photopic glare recovery metrics through JSON-RPC tooling. | |
| Ocular Dark Adaptation Rod Intercept Time (RIT) Skill alpha-park/genpark-personal-agent-ocular-dark-adaptation-rod-intercept-time-rit-skill Enables users to model scotopic photoreceptor kinetics, detect rod-cone break points, calculate threshold-crossing times, and receive retinoid-cycle and Bruch membrane health guidance through an MCP stdio interface. | |
| Ocular Microsaccade Rate & Fixational Fatigue MCP Server alpha-park/genpark-personal-agent-ocular-microsaccade-rate-fatigue-skill Enables agents to compute microsaccade frequency, main-sequence velocity scaling, involuntary ocular drift, and alertness/fatigue classifications from fixation-stream metrics through native JSON-RPC tools. | |
| Ocular Photopic Negative Response (PhNR) Skill alpha-park/genpark-personal-agent-ocular-photopic-negative-response-phnr-glaucoma-skill Enables deterministic calculation of photopic negative-response amplitude and its ratio to the b-wave from full-field flash ERG signals, supporting retinal ganglion cell health assessment and glaucoma-risk classification. | |
| ocular-tear-film alpha-park/genpark-personal-agent-ocular-tear-film-breakup-ergonomics-skill Enables assessment of tear film breakup dynamics, Ocular Protection Index, blink behavior, and digital asthenopia risk during screen work, returning corneal exposure analysis and ergonomic microbreak/blink coaching recommendations. | |
| Ocular Optokinetic Nystagmus (OKN) Skill alpha-park/genpark-personal-agent-ocular-torsional-optokinetic-nystagmus-skill Enables deterministic calculation of slow-phase velocity gain, retinal slip speed, fast-phase frequency, and directional symmetry, helping agents detect visual motion sickness and moderate UI animation stabilization. | |
| vor-gain alpha-park/genpark-personal-agent-ocular-vestibulo-ocular-reflex-vor-gain-skill Enables evaluation of angular vestibulo-ocular reflex gain, bilateral semicircular canal asymmetry, corrective catch-up saccades, and gaze stabilization, with vestibular adaptation exercise prescriptions. | |
| Oculomotor Saccadic Main Sequence Skill alpha-park/genpark-personal-agent-oculomotor-saccadic-main-sequence-velocity-skill Enables deterministic evaluation of saccadic peak velocity saturation, reaction latency, antisaccade directional error rate, and frontal executive inhibitory control through JSON-RPC tool integration for LLMs and autonomous agents. | |
| Oculomotor Binocular Vergence Dynamics Skill alpha-park/genpark-personal-agent-oculomotor-vergence-peak-velocity-dynamics-skill Enables LLM and autonomous agents to evaluate binocular vergence dynamics via JSON-RPC, calculating peak convergence/divergence velocities, latency, convergence-divergence ratios, and convergence-insufficiency/digital-eyestrain scores from | |
| physiological-tremor alpha-park/genpark-personal-agent-physiological-tremor-stability-skill Enables agents to analyze accelerometer and gyroscope timeseries for microtremor spectral bands, postural stability, and central motor fatigue, returning spectral metrics and ergonomic guidance. |
27,101–27,150 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.