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-maximum-flow-edmonds-karp-network-skill alpha-park/genpark-maximum-flow-edmonds-karp-network-skill Enables agents to compute shortest paths, topological orderings, maximum flow and minimum cut bottlenecks, minimum spanning trees, and centrality rankings for graph-based multi-agent routing. It runs as a zero-dependency MCP server using st | |
| genpark-merkle-tree-state-proof-verifier-skill alpha-park/genpark-merkle-tree-state-proof-verifier-skill Enables agents to construct SHA-256 Merkle trees, generate and verify state inclusion proofs, validate JWT HMAC signatures, perform Schnorr zero-knowledge proofs, and enforce nonce replay protection for immutable state attestation. | |
| genpark-meta-muse-episodic-memory-graph-mcp alpha-park/genpark-meta-muse-episodic-memory-graph-mcp Enables personal AI agents to fuse ambient multimodal perception with continuous episodic memory streams, routing routine reflexive actions at low latency while reserving heavier reasoning for ambiguous plans. Memory records apply Ebbinghau | |
| genpark-meta-muse-multimodal-episodic-resonance-mcp alpha-park/genpark-meta-muse-multimodal-episodic-resonance-mcp Enables personal AI agents to integrate multimodal Meta Ray-Ban audio and vision grounding with long-term episodic life memory graphs and empathetic emotional resonance. Supports proactive, context-aware assistance through sensory inputs, a | |
| genpark-milwaukee-onekey-smart-tool-inventory-skill alpha-park/genpark-milwaukee-onekey-smart-tool-inventory-skill Enables AI agents to locate and track smart cordless tools, program torque and speed profiles, fetch telematics, and remotely lock or unlock tools based on jobsite geofences. | |
| genpark-minimum-spanning-tree-kruskal-prim-skill alpha-park/genpark-minimum-spanning-tree-kruskal-prim-skill Enables agents to compute optimal multi-agent communication backbones and other graph operations such as shortest paths, topological sorting, maximum flow, and centrality ranking via the Model Context Protocol. | |
| genpark-monorepo-dependency-cycle-detector-skill alpha-park/genpark-monorepo-dependency-cycle-detector-skill Enables coding agents to analyze Python source with AST-based static analysis, detect circular dependencies across monorepo packages via Tarjan SCC, and produce a topological build order with Kahn's algorithm along with refactoring plans an | |
| genpark-monte-carlo-geometric-brownian-motion-skill alpha-park/genpark-monte-carlo-geometric-brownian-motion-skill Enables quantitative finance and risk analysis through MCP, including geometric Brownian motion Monte Carlo simulations, Black-Scholes Greeks, VaR/CVaR, bond duration/convexity, and Nelson-Siegel yield curve interpolation. | |
| genpark-multi-agent-debate-consensus-synthesizer-skill alpha-park/genpark-multi-agent-debate-consensus-synthesizer-skill Enables users to coordinate multiple specialized personas to debate high-stakes decisions and aggregate their input into an explainable consensus with dissenting minority logs. | |
| genpark-multi-agent-debate-consensus-verifier-skill alpha-park/genpark-multi-agent-debate-consensus-verifier-skill Enables multi-agent debate cross-examination and consensus arbitration through a deterministic, zero-dependency MCP server, providing structured outputs and telemetry for autonomous AI workflows. | |
| genpark-multi-agent-speculative-execution-coordinator-skill alpha-park/genpark-multi-agent-speculative-execution-coordinator-skill Enables coordinating multiple speculative agent execution paths by tracking milestone validation scores and canceling inferior branches early to reduce inference overhead. | |
| genpark-multi-agent-token-bucket-gossip-protocol-skill alpha-park/genpark-multi-agent-token-bucket-gossip-protocol-skill Enables autonomous agent swarms to coordinate and reach deterministic convergence through epidemic dissemination, causal vector clocks, CRDT reconciliation, quorum-based leader election, and atomic two-phase commit over MCP. It also support | |
| genpark-multi-model-cost-latency-router-skill alpha-park/genpark-multi-model-cost-latency-router-skill Enables dynamic, intent- and budget-aware routing of queries across 70+ LLMs by balancing cost and latency through Pareto-optimal model selection. Integrates with MCP clients like Claude Desktop and Cursor for automated multi-model executio | |
| genpark-multi-tenant-agent-isolation-sandbox-skill alpha-park/genpark-multi-tenant-agent-isolation-sandbox-skill Enables enforcing memory boundary compartmentalization and multi-tenant security isolation for autonomous agents via a deterministic, zero-dependency Python skill. Seamlessly integrates with Claude Desktop, Cursor, and other MCP-compliant c | |
| genpark-multihop-research-query-decomposer-skill alpha-park/genpark-multihop-research-query-decomposer-skill Enables decomposition of complex, multi-faceted research prompts into executable query plans and synthesis DAGs, with support for scientific evidence analysis and consensus calculation. | |
| genpark-multimodal-aspect-ratio-smart-reframe-skill alpha-park/genpark-multimodal-aspect-ratio-smart-reframe-skill Enables autonomous shortform video editing by converting 16:9 footage to 9:16 with dynamic speaker tracking, smart reframing bounding boxes, audio silence pacing, and precise cut-list generation through MCP-compatible clients. | |
| genpark-multimodal-audio-emotion-valence-detector-skill alpha-park/genpark-multimodal-audio-emotion-valence-detector-skill Enables analysis of acoustic vocal emotion, prosodic valence, and customer frustration from audio inputs through a zero-dependency MCP server. | |
| genpark-multimodal-chart-data-point-extractor-skill alpha-park/genpark-multimodal-chart-data-point-extractor-skill Enables users to calibrate multimodal chart coordinates and recover tabular datasets from visual bar, line, and scatter charts as structured numbers. | |
| MultimodalPDFContractClauseRiskAuditor alpha-park/genpark-multimodal-pdf-contract-clause-risk-auditor-skill Enables users to scan enterprise MSAs, NDAs, and Vendor SOWs in Tencent Docs for high-risk clauses such as unlimited indemnity, one-sided IP assignment, perpetual non-compete, and evergreen auto-renewal traps; calculates composite risk scor | |
| genpark-multimodal-spatial-audio-visual-grounding-skill alpha-park/genpark-multimodal-spatial-audio-visual-grounding-skill Enables AI agents to fuse 2D/3D visual bounding boxes, user head-pose gaze vectors, and acoustic beamforming azimuth angles into cross-modal focal salience scores. It also resolves deictic spatial references in real time, running as a zero- | |
| genpark-multimodal-vision-table-structural-extractor-skill alpha-park/genpark-multimodal-vision-table-structural-extractor-skill Provides multimodal OCR table grid and merged-cell reconstruction into Markdown, and integrates with MCP-compliant clients like Claude Desktop and Cursor. | |
| genpark-multimodal-voice-prosody-sentiment-analyzer-skill alpha-park/genpark-multimodal-voice-prosody-sentiment-analyzer-skill Enables agents to analyze speech prosody and vocal sentiment, including speech rate, pitch variance, and cognitive fatigue, to dynamically calibrate response pacing. | |
| genpark-nonce-replay-attack-guard-skill alpha-park/genpark-nonce-replay-attack-guard-skill Enables agent API request security by detecting and invalidating duplicated requests with sliding-window nonce replay protection, constant-time secret checks, JWT HMAC-SHA256 validation, Merkle inclusion proofs, and Schnorr zero-knowledge v | |
| genpark-page-rank-power-iteration-centrality-skill alpha-park/genpark-page-rank-power-iteration-centrality-skill Enables graph analysis and network-flow computations through the Model Context Protocol, including shortest-path search, topological dependency resolution, maximum flow, minimum spanning trees, and PageRank centrality scoring for interconne | |
| genpark-sparkpage-synthesis-engine-skill alpha-park/genpark-page-synthesis-engine-skill Enables AI agents to perform deterministic search synthesis and compile Sparkpage layouts into comparison matrices and ready-to-render HTML interfaces through a zero-dependency Python MCP server. Plugs into Claude Desktop, Cursor, and other | |
| Acoustic MOC Efferent Contralateral Suppression Skill alpha-park/genpark-personal-agent-acoustic-efferent-contralateral-suppression-skill Enables deterministic evaluation and classification of contralateral suppression from otoacoustic emission amplitudes, along with speech-in-noise gating and auditory protective resilience scoring through JSON-RPC tools for LLMs and autonomo | |
| MOC Efferent Acoustic Reflex MCP Server alpha-park/genpark-personal-agent-acoustic-efferent-olivocochlear-reflex-moc-skill Enables calculation of contralateral OAE suppression delta and linear voltage damping from baseline and CAS measurements, with threshold classification for cochlear efferent protection and checks for stapedial reflex artifact contamination. | |
| Acoustic Frequency Following Response (FFR) Skill alpha-park/genpark-personal-agent-acoustic-frequency-following-response-ffr-skill Enables LLMs and autonomous agents to compute phase-locking value, signal-to-noise ratio, and subcortical temporal envelope encoding fidelity through JSON-RPC tool integration. | |
| DPOAE Skill alpha-park/genpark-personal-agent-acoustic-otoacoustic-emissions-dpoae-skill Enables deterministic, zero-dependency audiological analysis of distortion-product emissions, SNR/clinical pass criteria, and outer hair cell fatigue scoring so agents can assess cochlear health and headphone noise overexposure. | |
| Acoustic Startle Prepulse Inhibition (PPI) MCP Server alpha-park/genpark-personal-agent-acoustic-startle-prepulse-inhibition-skill Enables deterministic calculation and classification of prepulse inhibition (%PPI) from startle reflex amplitudes and lead intervals, supporting sensorimotor gating and sensory overload vulnerability assessment through JSON-RPC tools. | |
| Personal Agent Adaptive Deep Work & Focus Guardian alpha-park/genpark-personal-agent-adaptive-deep-work-focus-guardian-skill Enables users to schedule 90-minute ultradian focus blocks, triage incoming interruptions using contact priority and urgency thresholds, and capture execution checkpoints for instant task resumption. | |
| alveolar-capillary-diffusion alpha-park/genpark-personal-agent-alveolar-capillary-diffusion-dlco-skill Enables evaluation of pulmonary gas diffusion by calculating hemoglobin-adjusted DLCO, percent predicted DLCO, transfer coefficient (KCO), and a pulmonary diffusion resilience score from clinical inputs. | |
| Personal Agent Auditory Acoustic Decibel Dosimeter Skill alpha-park/genpark-personal-agent-auditory-acoustic-decibel-dosimeter-skill Enables calculation of NIOSH/OSHA cumulative noise dose, equivalent continuous sound level (Leq), 8-hour time-weighted average, and Ward-model temporary threshold shift recovery from acoustic exposure inputs. | |
| Auditory Binaural Masking Level Difference (BMLD) MCP Server alpha-park/genpark-personal-agent-auditory-binaural-masking-level-difference-skill Enables deterministic psychoacoustic modeling of dichotic hearing thresholds, interaural phase differences, brainstem processing scores, and cocktail-party speech-in-noise intelligibility through JSON-RPC tools. | |
| Personal Agent Biometric Sleep & Readiness Workload Allocator alpha-park/genpark-personal-agent-biometric-sleep-readiness-workload-allocator-skill Enables users to evaluate biometric sleep and HRV recovery data, calculate a cognitive readiness score, and automatically reallocate demanding work blocks based on current capacity. | |
| Personal Agent Caffeine Adenosine Pharmacokinetics Skill alpha-park/genpark-personal-agent-caffeine-adenosine-pharmacokinetics-skill Enables users to model two-compartment caffeine elimination, estimate adenosine A1/A2A receptor occupancy and slow-wave sleep suppression, and schedule intake windows and cutoffs from wake and bedtime. | |
| Cardiac Baroreflex Sensitivity (BRS) Sequence Skill alpha-park/genpark-personal-agent-cardiac-baroreflex-sensitivity-sequence-skill Enables deterministic, non-invasive evaluation of spontaneous baroreflex sensitivity from beat-to-beat systolic blood pressure and ECG RR-interval streams via sequence analysis, reporting mean BRS, cardiovagal tone, and autonomic resilience | |
| Dual-Sensor Pulse Arrival Time (PAT / PTT) MCP Server alpha-park/genpark-personal-agent-cardiac-pulse-arrival-time-pat-pwt-skill Enables LLMs and autonomous agents to calculate pulse arrival time, pulse transit time, pulse wave velocity, and arterial vascular compliance from dual-sensor timestamps through deterministic JSON-RPC tools. Supports continuous cuffless car | |
| Cardiac Systolic Time Intervals (PEP/LVET) & Inotropy Skill alpha-park/genpark-personal-agent-cardiac-systolic-time-intervals-pep-lvet-skill Enables deterministic, non-invasive calculation of pre-ejection period and left ventricular ejection time, with rate-corrected indices and inotropic performance classification exposed as JSON-RPC tools for LLM and agent workflows. | |
| Cardiac Total Peripheral Resistance Index (TPRI) Skill alpha-park/genpark-personal-agent-cardiac-total-peripheral-resistance-tpri-skill Enables deterministic hemodynamic calculations for left-ventricular afterload and peripheral vascular compliance from blood pressure, cardiac output, height, and weight via an MCP stdio interface. | |
| Cardiac Ventricular Effective Arterial Elastance (Ea) Skill alpha-park/genpark-personal-agent-cardiac-ventricular-effective-arterial-elastance-ea-skill Enables calculation of Effective Arterial Elastance, End-Systolic Elastance, and ventriculo-arterial coupling from pressure-volume loop parameters through an MCP stdio server. It also supports estimating mechanical stroke work efficiency an | |
| Cardiac Ventricular Late Potentials (SAECG) Skill alpha-park/genpark-personal-agent-cardiac-ventricular-late-potentials-saecg-skill This server enables deterministic calculations to evaluate Signal-Averaged ECG (SAECG) Ventricular Late Potentials (VLPs) and RMS40. It provides highly sensitive detection of slow, fragmented conduction for arrhythmogenic substrate screenin | |
| Cardiac Ventricular Myocardial Work Index (GWI) Skill alpha-park/genpark-personal-agent-cardiac-ventricular-myocardial-work-index-gwi-skill Enables non-invasive estimation of left ventricular pressure-strain loop metrics from blood pressure and strain data, including constructive and wasted work plus efficiency, with dyssynchrony and afterload guidance. | |
| Personal Agent Cardiorespiratory VO2Max Velocity Skill alpha-park/genpark-personal-agent-cardiorespiratory-vo2max-velocity-skill Enables users to estimate VO2max from heart-rate ratios or Cooper 12-minute run distances, benchmark results against ACSM age and sex medians, and derive cardiorespiratory fitness biological age and all-cause mortality hazard ratios. | |
| Cerebral Autoregulation & Transient Hyperemic Response Ratio (THRR) MCP Server alpha-park/genpark-personal-agent-cerebral-autoregulation-hyperemic-thrr-skill Enables deterministic evaluation of flow-velocity responses to transient carotid compression and the resulting arteriolar vasodilatory reserve for autonomous neurovascular screening. | |
| Cerebrovascular Critical Closing Pressure (CrCP) MCP Server alpha-park/genpark-personal-agent-cerebral-critical-closing-pressure-crpc-skill Enables deterministic calculation of cerebrovascular critical closing pressure, effective cerebral perfusion pressure, and precapillary arteriolar wall tension from blood pressure and transcranial Doppler flow velocities, with hypoperfusion | |
| Transcranial Doppler Gosling Pulsatility Index (PI) Skill alpha-park/genpark-personal-agent-cerebral-pulsatility-gosling-index-skill Enables deterministic calculation of cerebrovascular pulsatility and resistance metrics from peak systolic and end-diastolic velocities, along with microvascular compliance classification, through MCP JSON-RPC tools. | |
| Frontal Cerebral Regional Tissue Oxygenation (NIRS rSO2) Skill alpha-park/genpark-personal-agent-cerebral-tissue-oxygenation-nirs-rso2-skill Enables deterministic calculation and monitoring of frontal cerebral regional tissue oxygenation, fractional tissue oxygen extraction, and cognitive endurance kinetics through MCP tools. | |
| Cerebrovascular Hypocapnic Hyperventilation Reactivity Skill alpha-park/genpark-personal-agent-cerebral-vasomotor-hyperventilation-reactivity-skill Enables deterministic evaluation of TCD hypocapnic vasomotor reactivity, flow velocity drop, and respiratory alkalosis buffering from baseline and hyperventilation EtCO2 and MCA velocity data. | |
| cerebrovascular-reactivity alpha-park/genpark-personal-agent-cerebrovascular-co2-reactivity-cvr-skill Enables calculation of cerebrovascular CO2 reactivity, Breath-Holding Index, and cerebral microvascular reserve from transcranial Doppler baseline and hypercapnic peak CBFv plus apnea duration, returning classifications and guidance. |
27,051–27,100 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.