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 |
|---|---|
| genpark-monte-carlo-geometric-brownian-motion-skill alphaparkinc/genpark-monte-carlo-geometric-brownian-motion-skill Provides native MCP tools for quantitative-finance and risk-modeling workflows, enabling computation of option Greeks, simulation of geometric Brownian motion asset-price paths, historical/parametric VaR and CVaR estimates, bond duration/co | |
| genpark-multi-agent-debate-consensus-synthesizer-skill alphaparkinc/genpark-multi-agent-debate-consensus-synthesizer-skill Enables AI agents to run structured multi-persona debates over high-stakes decisions and merge their positions into an explainable consensus, complete with logged dissenting minority opinions. It runs as a zero-dependency Python MCP server | |
| genpark-multi-agent-debate-consensus-verifier-skill alphaparkinc/genpark-multi-agent-debate-consensus-verifier-skill Enables deterministic multi-agent debate cross-examination and consensus arbitration through the Model Context Protocol, with structured JSON output and zero external dependencies. | |
| Multi-Agent Speculative Execution & Early Cancellation Coordinator alphaparkinc/genpark-multi-agent-speculative-execution-coordinator-skill Spawns multiple candidate reasoning paths concurrently, scores their progress against milestones, and halts underperforming branches early to cut inference costs. | |
| genpark-multi-agent-token-bucket-gossip-protocol-skill alphaparkinc/genpark-multi-agent-token-bucket-gossip-protocol-skill Enables MCP clients to run bounded epidemic dissemination, causal ordering, conflict-free state merging, and quorum-based transaction coordination across autonomous agent swarms. | |
| genpark-multi-file-git-workspace-dependency-diff-synthesizer-skill alphaparkinc/genpark-multi-file-git-workspace-dependency-diff-synthesizer-skill Enables analysis of multi-file git workspaces to synthesize dependency diffs and refactor sequences. | |
| genpark-multi-modal-chart-graph-data-extractor-skill alphaparkinc/genpark-multi-modal-chart-graph-data-extractor-skill Enables AI agents and MCP-compliant clients to extract visual data from charts and graphs into structured markdown tables using deterministic, zero-dependency Python. | |
| genpark-multi-model-cost-latency-router-skill alphaparkinc/genpark-multi-model-cost-latency-router-skill Enables AI agents and MCP clients to dispatch queries to the most suitable model among 70+ LLMs by scoring intent, budget, cost, and latency, returning structured routing decisions with execution telemetry. It runs as a zero-dependency Pyth | |
| genpark-multi-model-prompt-regression-benchmark-evaluator-skill alphaparkinc/genpark-multi-model-prompt-regression-benchmark-evaluator-skill Enables running deterministic multi-model prompt regression and golden dataset benchmark suites, exposing structured results and telemetry through the Model Context Protocol for integration with MCP-compliant clients. | |
| genpark-multi-tenant-agent-isolation-sandbox-skill alphaparkinc/genpark-multi-tenant-agent-isolation-sandbox-skill Enables developers and AI agents to enforce per-tenant security isolation for autonomous agents by compartmentalizing memory boundaries and managing sandboxed tenant execution. It exposes this deterministic, dependency-free guard through a | |
| genpark-multihop-research-query-decomposer-skill alphaparkinc/genpark-multihop-research-query-decomposer-skill Enables decomposition of complex research queries into multi-hop sub-queries and synthesis DAGs, with scientific consensus analysis, citation credibility verification, and deterministic JSON outputs for MCP-compliant clients. | |
| genpark-multimodal-aspect-ratio-smart-reframe-skill alphaparkinc/genpark-multimodal-aspect-ratio-smart-reframe-skill Enables autonomous shortform video editing by tracking speakers and dynamically reframing 16:9 footage into 9:16, with smart bounding box coordination for CapCut and MCP-compatible agent workflows. | |
| genpark-multimodal-audio-emotion-valence-detector-skill alphaparkinc/genpark-multimodal-audio-emotion-valence-detector-skill Enables acoustic vocal emotion, prosodic valence, and customer frustration analysis on audio queries via the Model Context Protocol, letting MCP-compliant clients obtain structured emotional telemetry and deterministic results. | |
| MultimodalPDFContractClauseRiskAuditor alphaparkinc/genpark-multimodal-pdf-contract-clause-risk-auditor-skill Enables scanning of enterprise MSAs, NDAs, and vendor SOWs to detect high-risk clauses such as unlimited indemnity, one-sided IP assignment, perpetual non-compete, and evergreen auto-renewal traps. Computes composite risk scores with an ove | |
| genpark-multimodal-spatial-audio-visual-grounding-skill alphaparkinc/genpark-multimodal-spatial-audio-visual-grounding-skill Enables real-time fusion of 2D/3D visual bounding boxes, head-pose gaze vectors, and acoustic beamforming azimuth angles into cross-modal focal salience scores to resolve deictic spatial references for multimodal agents. | |
| genpark-multimodal-vision-table-structural-extractor-skill alphaparkinc/genpark-multimodal-vision-table-structural-extractor-skill Enables multimodal OCR-based extraction of table grids and merged cells into Markdown with deterministic, zero-dependency execution through MCP for AI agents. | |
| genpark-multimodal-voice-prosody-sentiment-analyzer-skill alphaparkinc/genpark-multimodal-voice-prosody-sentiment-analyzer-skill Enables MCP-compliant agents to analyze speech prosody and vocal sentiment from audio-derived input, measuring speech rate, pitch variance, and user cognitive fatigue. Exposes these deterministic results over JSON-RPC so clients can dynamic | |
| Genpark-multivariate-ad-creative-fatigue-auditor alphaparkinc/genpark-multivariate-ad-creative-fatigue-auditor-skill Genpark-multivariate-ad-creative-fatigue-auditor | |
| genpark-nonce-replay-attack-guard-skill alphaparkinc/genpark-nonce-replay-attack-guard-skill Enables MCP clients to guard agent API requests against nonce replay attacks using a sliding-window ledger, constant-time digest checks, JWT claim validation, Merkle inclusion proofs, and Schnorr zero-knowledge verification. | |
| genpark-page-rank-power-iteration-centrality-skill alphaparkinc/genpark-page-rank-power-iteration-centrality-skill Enables graph analysis over interconnected agent networks by computing centrality and authority scores, shortest paths, dependency orderings, maximum flows, and minimum spanning trees through MCP tools. | |
| genpark-sparkpage-synthesis-engine-skill alphaparkinc/genpark-page-synthesis-engine-skill Enables AI agents to perform dynamic search synthesis and compile Sparkpage layouts into comparison matrices and HTML interfaces, running deterministically with zero external dependencies over the Model Context Protocol. | |
| genpark-paged-attention-kv-cache-budget-calculator-skill alphaparkinc/genpark-paged-attention-kv-cache-budget-calculator-skill Enables calculating PagedAttention KV cache allocation and GPU memory budgets for vLLM-style chunked prefill workloads via MCP. | |
| Medial Olivocochlear (MOC) Efferent Acoustic Reflex Skill alphaparkinc/genpark-personal-agent-acoustic-efferent-olivocochlear-reflex-moc-skill Enables deterministic calculation of contralateral OAE suppression deltas and linear voltage damping to assess cochlear efferent protection and flag stapedial reflex contamination. | |
| Acoustic Frequency Following Response (FFR) Skill alphaparkinc/genpark-personal-agent-acoustic-frequency-following-response-ffr-skill Enables agents to compute deterministic phase-locking value, signal-to-noise ratio, and subcortical temporal envelope encoding fidelity through JSON-RPC tool calls. | |
| Distortion Product Otoacoustic Emissions (DPOAE) Skill alphaparkinc/genpark-personal-agent-acoustic-otoacoustic-emissions-dpoae-skill Enables deterministic audiological evaluation of cochlear outer hair cell function, clinical pass criteria, and early noise-overexposure indicators through JSON-RPC tools for LLM and autonomous agent workflows. | |
| Acoustic Stapedial Reflex Threshold (ART) Skill alphaparkinc/genpark-personal-agent-acoustic-stapedial-reflex-threshold-skill Enables deterministic calculation of ipsilateral and contralateral acoustic reflex thresholds, sensation level, 10-second reflex decay, and middle-ear protective resilience through JSON-RPC tools for LLM and autonomous-agent integration. | |
| Acoustic Startle Prepulse Inhibition (PPI) Skill alphaparkinc/genpark-personal-agent-acoustic-startle-prepulse-inhibition-skill Enables deterministic evaluation of prepulse inhibition percentages, sensorimotor gating integrity, and cognitive distractibility from acoustic startle reflex measurements through MCP JSON-RPC tools. | |
| Personal Agent Adaptive Deep Work & Focus Guardian alphaparkinc/genpark-personal-agent-adaptive-deep-work-focus-guardian-skill Enables users to schedule 90-minute ultradian focus blocks, triage incoming interruptions against contact priority thresholds, and capture execution checkpoints for instant resumption. | |
| Personal Agent Allostatic Load Index Biomarker Skill alphaparkinc/genpark-personal-agent-allostatic-load-index-biomarker-skill Enables users to calculate a normalized allostatic load index from biomarker panels, identify the primary vulnerable physiological subsystem, and project 12-week homeostatic recovery trajectories. | |
| alveolar-capillary-diffusion alphaparkinc/genpark-personal-agent-alveolar-capillary-diffusion-dlco-skill Enables computational pulmonary physiology assessment of DLCO, hemoglobin-normalized diffusion, KCO, and a pulmonary diffusion resilience score for altitude and cardiorespiratory guidance. | |
| Personal Agent Ambient Noise Auditory Focus Masker Skill alphaparkinc/genpark-personal-agent-ambient-noise-auditory-focus-masker-skill Enables auditing speech intelligibility and acoustical distraction risk, modeling working-memory throughput penalties, and synthesizing pink or brown noise masking profiles for focused work. | |
| Personal Agent Attention Residue Context Switch alphaparkinc/genpark-personal-agent-attention-residue-context-switch-skill Enables quantifying attention residue from unfinished task transitions, scoring application fragmentation entropy, and optimizing context batching schedules to recover deep work hours. | |
| Auditory Binaural Masking Level Difference (BMLD) MCP Server alphaparkinc/genpark-personal-agent-auditory-binaural-masking-level-difference-skill Enables deterministic psychoacoustic modeling for dichotic hearing tests, including interaural phase extraction, decibel advantage scoring, brainstem processing, and speech-in-noise intelligibility through JSON-RPC tools for LLMs and autono | |
| Personal Agent Biometric Sleep & Readiness Workload Allocator alphaparkinc/genpark-personal-agent-biometric-sleep-readiness-workload-allocator-skill Enables agents to ingest sleep debt, REM/deep sleep ratios, and HRV recovery metrics to compute an objective cognitive readiness index and dynamically reschedule high-intensity deep work blocks. | |
| Cardiac Baroreflex Sensitivity (BRS) Sequence Skill alphaparkinc/genpark-personal-agent-cardiac-baroreflex-sensitivity-sequence-skill Enables deterministic calculation of spontaneous cardiac baroreflex sensitivity from beat-to-beat systolic blood pressure and RR-interval sequences, including mean BRS in ms/mmHg, cardiovagal tone, and autonomic resilience scoring through J | |
| Cardiac Central Aortic Augmentation Index (AIx) & Pulse Wave Analysis (PWA) Skill alphaparkinc/genpark-personal-agent-cardiac-central-aortic-augmentation-index-pwa-skill Enables evaluation of central aortic pulse wave reflections and ventricular afterload from applanation tonometry inputs, computing augmentation pressure, AIx, AIx@75, reflection time, and SEVR for personal vascular aging monitoring. | |
| Cardiac Coronary Flow Velocity Reserve (CFVR) Personal Agent Skill alphaparkinc/genpark-personal-agent-cardiac-coronary-flow-velocity-reserve-cfvr-skill Enables deterministic calculation of a Doppler-derived microvascular reserve ratio and rate-pressure product, classifying microvascular dysfunction and supporting angina risk stratification. | |
| Dual-Sensor Pulse Arrival Time (PAT / PTT) Skill alphaparkinc/genpark-personal-agent-cardiac-pulse-arrival-time-pat-pwt-skill Enables deterministic calculation of PAT, PTT, pulse wave velocity, and arterial vascular compliance from dual-sensor timestamps for continuous cuffless cardiovascular monitoring via MCP JSON-RPC tools. | |
| Cardiac Total Peripheral Resistance Index (TPRI) Skill alphaparkinc/genpark-personal-agent-cardiac-total-peripheral-resistance-tpri-skill Enables deterministic cardiovascular hemodynamic calculations for SVR and indexed TPRI using blood pressure, central venous pressure, cardiac output, height, and weight with Mosteller body surface area adjustment. | |
| Cardiac Ventricular Effective Arterial Elastance (Ea) Skill alphaparkinc/genpark-personal-agent-cardiac-ventricular-effective-arterial-elastance-ea-skill Enables deterministic calculation of effective arterial elastance, end-systolic elastance, and ventriculo-arterial coupling from single-beat pressure-volume metrics, returning mechanical stroke work efficiency and afterload guidance via an | |
| Cardiac Ventricular Late Potentials (SAECG) MCP Server alphaparkinc/genpark-personal-agent-cardiac-ventricular-late-potentials-saecg-skill Enables agents to compute Simson-criteria metrics (filtered QRS duration, RMS40, LAS40) and screen for arrhythmogenic substrate from signal-averaged ECG inputs via JSON-RPC. | |
| Cardiac Ventricular Myocardial Work Index (GWI) Skill alphaparkinc/genpark-personal-agent-cardiac-ventricular-myocardial-work-index-gwi-skill Enables non-invasive calculation of left ventricular myocardial work indices, constructive and wasted work, and global work efficiency from echocardiographic pressure-strain loop inputs through an MCP JSON-RPC stdio interface. | |
| Cerebrovascular Critical Closing Pressure (CrCP) MCP Server alphaparkinc/genpark-personal-agent-cerebral-critical-closing-pressure-crpc-skill Enables agents and LLMs to compute zero-flow pressure intercepts, effective perfusion driving pressure, precapillary wall tension, and hypoperfusion safety classifications through native JSON-RPC tool calls. | |
| Transcranial Doppler Gosling Pulsatility Index (PI) Skill alphaparkinc/genpark-personal-agent-cerebral-pulsatility-gosling-index-skill Enables deterministic calculation of cerebral blood-flow pulsatility and resistive indices from peak systolic and end-diastolic velocities, with classification of microvascular resistance for agent workflows. | |
| Cerebral Tissue Oxygenation NIRS rSO2 MCP Server alphaparkinc/genpark-personal-agent-cerebral-tissue-oxygenation-nirs-rso2-skill Enables LLMs and autonomous agents to calculate and monitor frontal cerebral regional oxygen saturation, fractional tissue oxygen extraction, and cognitive endurance through native JSON-RPC tool integration. | |
| Cerebrovascular Hypocapnic Hyperventilation Reactivity MCP Server alphaparkinc/genpark-personal-agent-cerebral-vasomotor-hyperventilation-reactivity-skill Enables deterministic Transcranial Doppler hypocapnic vasomotor reactivity calculations, including CVR_hypo in %/mmHg, flow-velocity drop, and respiratory alkalosis buffering for agent-guided assessment. | |
| cerebrovascular-reactivity alphaparkinc/genpark-personal-agent-cerebrovascular-co2-reactivity-cvr-skill Enables agents to compute cerebrovascular CO2 reactivity from transcranial Doppler baseline and hypercapnic peak flow velocities plus apnea duration, yielding percentage velocity surge, Breath-Holding Index, and a 0-100 reserve index. Retur | |
| Personal Agent Circadian Chronotype MCTQ Phase Skill alphaparkinc/genpark-personal-agent-circadian-chronotype-mctq-phase-skill Enables computing MCTQ mid-sleep chronotype and social jetlag from workday and free-day sleep schedules, then projecting circadian biological phase windows such as CAR peak, focus periods, caffeine cutoff, DLMO, and sleep gate from a target | |
| Personal Agent Circadian Lux Melatonin Onset alphaparkinc/genpark-personal-agent-circadian-lux-melatonin-onset-skill This MCP server enables users to model ocular light exposure and circadian melatonin onset, forecast screen-induced DLMO delays, and generate timed digital sunset schedules for light hygiene and sleep readiness. | |
| circadian-phase-angle alphaparkinc/genpark-personal-agent-circadian-phase-angle-entrainment-skill Enables calculation of phase angles of entrainment from DLMO, sleep onset, and wake times, along with internal circadian desynchrony scoring and photic PRC adjustment guidance. |
27,501–27,550 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.