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 Credential Entropy Exposure Fiduciary alphaparkinc/genpark-personal-agent-credential-entropy-exposure-fiduciary-skill Enables users to compute credential bit entropy and GPU brute-force cracking timelines, audit cross-account password reuse exposure, and perform k-anonymity hash-prefix privacy checks without leaking credentials. | |
| critical-flicker-fusion alphaparkinc/genpark-personal-agent-critical-flicker-fusion-frequency-skill Computes Critical Flicker Fusion Frequency thresholds from ascending and descending psychophysical trial data, capturing hysteresis and comparing results against a baseline to derive a cortical arousal and cognitive fatigue index. It also e | |
| Cutaneous Axon Reflex Flare (Laser Doppler) Skill alphaparkinc/genpark-personal-agent-cutaneous-axon-reflex-flare-laser-skill Enables deterministic calculation of the Cutaneous Axon Reflex Vasodilatory Index, flare radius, and unmyelinated nociceptive C-fiber axonal integrity for small-fiber neuropathy screening through MCP JSON-RPC tool integration. | |
| Cutaneous Cold-Induced Vasodilation (CIVD) Skill alphaparkinc/genpark-personal-agent-cutaneous-cold-induced-vasodilation-civd-skill Enables deterministic calculation of peripheral cold-response metrics—Lewis hunting reaction, rewarming amplitude, hunting index, and cold resilience scores—from local cold immersion measurements via JSON-RPC tools for LLMs and autonomous a | |
| Cutaneous Galvanic Skin Conductance (EDA/GSR) Skill alphaparkinc/genpark-personal-agent-cutaneous-galvanic-skin-conductance-tonic-phasic-skill Enables analysis of raw EDA/GSR series by separating tonic baseline SCL from phasic SCR peaks, screening peaks, and classifying sympathetic arousal and cognitive workload through an MCP JSON-RPC stdio server. | |
| Cutaneous Laser Speckle Contrast Imaging (LSCI) Skill alphaparkinc/genpark-personal-agent-cutaneous-laser-speckle-contrast-imaging-lsci-skill Enables deterministic calculation of laser speckle contrast, blood flow index, and laser speckle perfusion units from local pixel intensity kernels, with exposure-compensated microvascular perfusion guidance via an MCP JSON-RPC stdio server | |
| cutaneous-microcirculation alphaparkinc/genpark-personal-agent-cutaneous-microcirculation-laser-doppler-skill Analyzes cutaneous laser Doppler flux and mean arterial pressure to compute cutaneous vascular conductance, axon-reflex ratios, %CVCmax plateau, and an endothelial microvascular health score with classification and downstream cardiovascular | |
| Cutaneous Microdialysis Perfusion Recovery Skill alphaparkinc/genpark-personal-agent-cutaneous-microdialysis-perfusion-recovery-skill Enables deterministic zero-net-flux analysis of cutaneous microdialysis data to compute in vivo extraction fraction and true interstitial concentrations, with biomarker quantitation and probe delivery guidance. | |
| Cutaneous Microvascular Reactive Hyperemia (PORH) Skill alphaparkinc/genpark-personal-agent-cutaneous-microvascular-post-occlusive-reactive-hyperemia-skill Enables deterministic calculation of cutaneous post-occlusive reactive hyperemia metrics, including PU_peak/PU_base amplification ratio, time to peak, and endothelial nitric oxide reserve, from laser Doppler flowmetry inputs for microvascul | |
| Cutaneous Tactile Sensitivity & Mechanical Allodynia (Von Frey) MCP Server alphaparkinc/genpark-personal-agent-cutaneous-tactile-allodynia-vonfrey-skill Enables deterministic evaluation of cutaneous mechanoreceptive tactile thresholds using Von Frey Semmes-Weinstein monofilament forces, classifying sensory blunting versus mechanical allodynia and exposing results as JSON-RPC tools for LLM a | |
| Cutaneous Vibration Perception Threshold (VPT) Skill alphaparkinc/genpark-personal-agent-cutaneous-tactile-vibration-pallesthesia-skill Enables agents to calculate age-adjusted Rydel-Seiffer tuning fork pallesthesia scores and classify large-fiber sensory neuropathy from clinical readings. | |
| Cutaneous Transepidermal Water Loss (TEWL) Skill alphaparkinc/genpark-personal-agent-cutaneous-transepidermal-water-loss-tewl-skill Enables calculation of vapor flux and stratum corneum barrier integrity from dual surface and ambient temperature/humidity sensor readings, with clinical and cosmetic guidance. | |
| two-point-discrimination alphaparkinc/genpark-personal-agent-cutaneous-two-point-discrimination-skill Enables assessment of tactile spatial acuity from discriminated distances and response ratios, including static and dynamic threshold classification, acuity scoring, and ergonomic sensory-training guidance. | |
| genpark-personal-agent-dual-cognition-orchestrator-skill alphaparkinc/genpark-personal-agent-dual-cognition-orchestrator-skill Enables personal AI agents to perceive ambient context, retain episodic memory with decay, act proactively, and route routine decisions through fast System-1 reflexes while escalating ambiguous multi-hop plans to frontier LLMs. Includes rev | |
| Personal Agent Dunbar Relationship Cadence alphaparkinc/genpark-personal-agent-dunbar-relationship-cadence-skill Enables users to classify contacts into social closeness layers, estimate relationship warmth decay over time, and schedule intentional reconnections within a bounded weekly cadence. | |
| Personal Agent Autonomous Smart Pantry & Dietary Grocery Replenisher alphaparkinc/genpark-personal-agent-dynamic-grocery-pantry-auto-replenisher-skill Enables autonomous tracking of household food consumption and expiration, applying dietary filters such as organic, gluten-free, and low-sugar to generate optimized grocery replenishment baskets within a specified budget. | |
| dynamic-postural-stability alphaparkinc/genpark-personal-agent-dynamic-postural-stability-index-skill Enables analysis of triaxial force plate data to compute directional and composite stability indices, impact load multipliers, and time to stabilization for jump-landing assessments. | |
| genpark-personal-agent-dynamic-wardrobe-capsule-packer-skill alphaparkinc/genpark-personal-agent-dynamic-wardrobe-capsule-packer-skill Enables users to generate weather- and itinerary-adaptive capsule wardrobe packing lists that respect destination dress codes and airline carry-on limits. | |
| Electroretinogram Photopic Negative Response (PhNR) Skill alphaparkinc/genpark-personal-agent-electroretinogram-photopic-negative-erg-skill Enables deterministic, non-invasive PhNR analysis from electroretinogram amplitudes and latency, calculating the PhNR/b-wave ratio and stratifying retinal ganglion cell strain for LLM and autonomous-agent use. | |
| Personal Agent Financial Runway Monte Carlo alphaparkinc/genpark-personal-agent-financial-runway-monte-carlo-skill This MCP server enables users to model personal cash runway under stochastic income shocks, quantify ruin probability and liquidity resilience, and calculate safe discretionary daily and monthly spending caps. | |
| Personal Agent Flight Layover Micro-Itinerary Synthesizer alphaparkinc/genpark-personal-agent-flight-layover-micro-itinerary-synthesizer-skill Enables agents to evaluate layover time budgets and generate timed sightseeing or culinary micro-tours that account for immigration buffers, round-trip metro/taxi latencies, and connection safety. | |
| Personal Agent Focus Recovery Binaural Beats Skill alphaparkinc/genpark-personal-agent-focus-recovery-binaural-beats-skill Enables calculation of Auditory Steady-State Response binaural beat frequencies and scheduling of phased cognitive entrainment protocols for focus, recovery, and sleep-related soundscapes. | |
| Personal Agent Gift Curator & Social Graph Occasion Recommender alphaparkinc/genpark-personal-agent-gift-curator-social-graph-recommender-skill Enables users to ingest relationship tiers, recipient interests, milestone urgency, and budget constraints, then synthesize personalized gift recommendations with bespoke card copy through MCP. | |
| Personal Agent Glycemic Load Macro Balancer alphaparkinc/genpark-personal-agent-glycemic-load-macro-balancer-skill Enables users to aggregate meal glycemic index/load, model protein and fat buffering, forecast post-prandial cognitive crash risk and focus hours, and receive macronutrient stabilization recommendations. | |
| Personal Agent Habit Elasticity Tracker MCP Server alphaparkinc/genpark-personal-agent-habit-elasticity-tracker-skill Enables users to forecast when habits become automatic, quantify how friction changes completion rates, and adapt routines into minimum viable micro-habits during low-energy days. | |
| Personal Agent Hydration Osmolality Electrolyte MCP Server alphaparkinc/genpark-personal-agent-hydration-osmolality-electrolyte-skill Enables estimation of sweat rate and sodium loss, modeling of subclinical dehydration cognitive deficits, and generation of personalized hourly fluid and electrolyte replenishment schedules. | |
| Personal Agent Indoor CO2 Cognitive Ventilation MCP Server alphaparkinc/genpark-personal-agent-indoor-co2-cognitive-ventilation-skill Enables users to model indoor CO2 accumulation using mass-balance differential equations, estimate cognitive performance impairment from CO2 levels, and schedule timed fresh-air purges to restore healthy ventilation. | |
| genpark-personal-agent-information-diet-entropy-pruner-skill alphaparkinc/genpark-personal-agent-information-diet-entropy-pruner-skill Enables users to audit personal reading streams by quantifying category diversity with Shannon entropy, detecting lexical redundancy and echo chambers via Jaccard similarity, and ranking content sources by decibel signal-to-noise ratio for | |
| Personal Agent Mitochondrial Biogenesis MET Flux Skill alphaparkinc/genpark-personal-agent-mitochondrial-biogenesis-met-flux-skill Enables modeling PGC-1alpha transcriptional induction, partitioning CaMK versus AMPK pathway signaling, and optimizing 80/20 polarized training for mitochondrial density. | |
| muscle-oxygenation alphaparkinc/genpark-personal-agent-muscle-oxygenation-nirs-smo2-skill Enables evaluation of NIRS SmO2 desaturation profiles, muscle oxygen extraction, and hyperemic reperfusion recovery kinetics, with pacing recommendations. | |
| Ocular Accommodative Microfluctuations (AMF) Skill alphaparkinc/genpark-personal-agent-ocular-accommodative-microfluctuations-amf-skill Enables analysis of continuous diopter time series through Hann-windowed discrete Fourier spectral decomposition to compute LFC/HFC power, AMF ratio, and ciliary fatigue index for objective ergonomic classification. | |
| Ocular Cone Contrast Test (CCT) Skill alphaparkinc/genpark-personal-agent-ocular-cone-contrast-test-color-vision-cct-skill Enables calculation of isolated L-, M-, and S-cone contrast thresholds and mapping them to calibrated 0–100 diagnostic scores for assessing photoreceptor integrity and selective color-vision defects. | |
| Visual Contrast Sensitivity (Pelli-Robson) Skill alphaparkinc/genpark-personal-agent-ocular-contrast-sensitivity-pelli-robson-skill Enables deterministic calculation of Pelli-Robson contrast sensitivity scores, Weber contrast thresholds, visual functional acuity, and photopic glare recovery through JSON-RPC tools for agent workflows. | |
| Ocular Dark Adaptation Rod Intercept Time (RIT) Skill alphaparkinc/genpark-personal-agent-ocular-dark-adaptation-rod-intercept-time-rit-skill Enables deterministic calculation of dark-adaptation kinetics and photoreceptor recovery metrics from post-bleach luminance sensitivity curves, supporting early nyctalopia and macular screening. | |
| Ocular Microsaccade Rate & Fixational Fatigue Skill alphaparkinc/genpark-personal-agent-ocular-microsaccade-rate-fatigue-skill Enables agents to evaluate fixational eye-movement kinematics—microsaccade rate, main-sequence velocity, and involuntary drift—and derive deterministic alertness and fatigue classifications from fixation metrics. | |
| Ocular Photopic Negative Response (PhNR) Skill alphaparkinc/genpark-personal-agent-ocular-photopic-negative-response-phnr-glaucoma-skill Enables deterministic analysis of photopic flash ERG signals to compute negative-response amplitude, b-wave ratio, and retinal ganglion cell health indicators through an MCP stdio interface. | |
| ocular-tear-film alphaparkinc/genpark-personal-agent-ocular-tear-film-breakup-ergonomics-skill Enables agents to compute Ocular Protection Index and tear film breakup dynamics from NIBUT, blink rate, and incomplete blink data, producing digital asthenopia risk scores and ergonomic microbreak and blink-coaching guidance for extended s | |
| Ocular Optokinetic Nystagmus (OKN) MCP Server alphaparkinc/genpark-personal-agent-ocular-torsional-optokinetic-nystagmus-skill Enables deterministic calculation of OKN slow-phase tracking gain, retinal slip velocity, directional symmetry ratios, and visual-vestibular motion stabilization scores from supplied stimulus and eye-movement values. | |
| vor-gain alphaparkinc/genpark-personal-agent-ocular-vestibulo-ocular-reflex-vor-gain-skill Enables computational neuro-otology assessment from head-impulse kinematics, including VOR gain, bilateral canal asymmetry, corrective catch-up saccades, and a vestibulo-ocular stability index for gaze-stabilization planning. | |
| Oculomotor Saccadic Main Sequence Skill alphaparkinc/genpark-personal-agent-oculomotor-saccadic-main-sequence-velocity-skill This MCP server enables deterministic, zero-dependency evaluation of eye-movement kinetics, including peak-velocity saturation, reaction latency, antisaccade directional errors, and executive inhibitory control for personal-agent focus gati | |
| Oculomotor Smooth Pursuit Tracking Skill alphaparkinc/genpark-personal-agent-oculomotor-smooth-pursuit-velocity-gain-skill Enables agents to evaluate smooth pursuit velocity gain, retinal velocity error, and saccadic substitution kinetics through deterministic JSON-RPC tools. It supports visual fatigue and attention biomarker analysis using standard-library Pyt | |
| Oculomotor Binocular Vergence Dynamics Skill alphaparkinc/genpark-personal-agent-oculomotor-vergence-peak-velocity-dynamics-skill Provides deterministic calculations of peak convergence and divergence velocities, latency, and convergence-insufficiency asthenopia scores through JSON-RPC tools for LLM and autonomous agents. | |
| physiological-tremor alphaparkinc/genpark-personal-agent-physiological-tremor-stability-skill Enables deterministic analysis of accelerometer and gyroscope timeseries for 8–12 Hz microtremor spectral bands, postural stability, and central motor fatigue, returning stability scores and fatigue categorization for agent guidance. | |
| Post-Exercise EPOC alphaparkinc/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 post-workout fuel partitioning to generate hydration and refueling guidance. Supports workout parameter | |
| postural-sway alphaparkinc/genpark-personal-agent-postural-sway-center-of-pressure-skill Enables analysis of 2D center-of-pressure statokinesigram trajectories, computing 95% confidence ellipse area, sway velocity, postural stability index, fall-risk tier, and Romberg Quotient for sensory re-weighting comparisons. | |
| Cervical VEMP MCP Server alphaparkinc/genpark-personal-agent-postural-vestibular-cervical-vemp-skill Enables deterministic calculation of p13–n23 peak latencies, interaural asymmetry ratio, and saccular otolith integrity from vestibular electrophysiology inputs through JSON-RPC tools for LLM and agent workflows. | |
| vHIT Vestibular Gain MCP Server alphaparkinc/genpark-personal-agent-postural-vestibular-head-impulse-vhit-skill Enables deterministic evaluation of high-frequency angular VOR gain, overt/covert corrective saccades, and gaze stability through native JSON-RPC tools for LLMs and autonomous agents. | |
| genpark-personal-agent-pulmonary-alveolar-dead-space-bohr-enghoff-skill alphaparkinc/genpark-personal-agent-pulmonary-alveolar-dead-space-bohr-enghoff-skill This server allows for the calculation of the Bohr-Enghoff Alveolar Dead Space Fraction (V_D/V_T) and the Alveolar-Arterial oxygen gradient. It uses standard physiological equations to evaluate ventilation-perfusion matching based on gas ex | |
| SBN2 Closing Volume MCP Server alphaparkinc/genpark-personal-agent-pulmonary-closing-volume-nitrogen-washout-skill Enables agents to compute single-breath nitrogen washout results — closing volume (CV/VC %), closing capacity (CC/TLC %), Phase III alveolar slope, and a peripheral small airway patency score — from vital capacity, residual volume, and age | |
| Pulmonary Dynamic Airway Closing Pressure Skill alphaparkinc/genpark-personal-agent-pulmonary-dynamic-airway-closing-pressure-pel-skill Enables deterministic physiological analysis of expiratory flow limitation, equal pressure points, airway collapse risk, and gas trapping via Mead's model. Exposes the calculations through a Model Context Protocol JSON-RPC 2.0 stdio server. |
27,551–27,600 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.