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 |
|---|---|
| GenParkQuantTriangularArbitrageBellmanFordDetector alpha-park/genpark-quant-triangular-arbitrage-bellman-ford-detector-skill Enables MCP clients to detect negative-cycle triangular arbitrage, compute cross-currency rate discrepancies and net arbitrage ROI, and run quantitative microstructure and portfolio optimization analyses. | |
| genpark-quantum-gate-hadamard-pauli-cnot-engine-skill alpha-park/genpark-quantum-gate-hadamard-pauli-cnot-engine-skill Enables zero-dependency quantum circuit simulation with qubit state-vector evolution, Hadamard/Pauli/CNOT gates, Born-rule measurement, Bell state generation, and Grover amplitude amplification via MCP. | |
| genpark-quantum-grover-search-oracle-amplifier-skill alpha-park/genpark-quantum-grover-search-oracle-amplifier-skill Enables zero-dependency quantum circuit simulation, qubit state evolution, Born-rule measurement, and Grover amplitude amplification through MCP for unstructured search benchmarking. | |
| genpark-quantum-measurement-born-rule-sampler-skill alpha-park/genpark-quantum-measurement-born-rule-sampler-skill Enables users to simulate quantum circuits and sample projective qubit measurements via Born's rule, including unitary gates, entanglement, EPR Bell states, and Grover amplitude amplification with Monte Carlo shot histograms. | |
| genpark-quantum-qubit-state-vector-simulator-skill alpha-park/genpark-quantum-qubit-state-vector-simulator-skill Enables users to simulate multi-qubit quantum circuits through an MCP interface, including unitary gates, entanglement, Born-rule measurement sampling, fidelity/probability calculations, and Grover amplitude amplification. Integrates with C | |
| genpark-quantum-teleportation-entanglement-circuit-skill alpha-park/genpark-quantum-teleportation-entanglement-circuit-skill Enables zero-dependency quantum circuit simulation with state-vector evolution, Hadamard/CNOT entanglement, Born-rule measurement, EPR Bell pair generation, and Grover amplitude amplification, exposed natively over MCP for Claude Desktop, C | |
| genpark-raft-leader-election-consensus-kernel-skill alpha-park/genpark-raft-leader-election-consensus-kernel-skill Enables MCP clients to run distributed Raft leader election, quorum voting, vector-clock causality tracking, LWW CRDT reconciliation, epidemic gossip, and two-phase commit coordination using only Python standard library. It supports local b | |
| genpark-raycast-script-command-palette-router-skill alpha-park/genpark-raycast-script-command-palette-router-skill Enables parsing command palette arguments and dispatching deep-link shortcuts for Raycast and Alfred workflows, with deterministic execution and structured telemetry via MCP. | |
| genpark-realtime-voice-agent-latency-telemetry-skill alpha-park/genpark-realtime-voice-agent-latency-telemetry-skill Enables end-to-end profiling of conversational voice agent latency, tracking VAD, STT, LLM-TTFT, TTS-TTFB, and playout bottlenecks to identify pipeline delays. | |
| genpark-realtime-voice-noise-suppression-gate-skill alpha-park/genpark-realtime-voice-noise-suppression-gate-skill An MCP server that estimates acoustic noise floors and applies spectral gating to suppress ambient reverberation in real-time voice audio. It enables developers and AI agents to run deterministic, zero-dependency noise suppression through a | |
| genpark-realtime-voice-turn-taking-orchestrator-skill alpha-park/genpark-realtime-voice-turn-taking-orchestrator-skill Enables sub-100ms conversational turn-taking and barge-in handling for voice agents, integrating with Cartesia Sonic and ElevenLabs, and can be used by MCP-compliant clients like Claude Desktop and Cursor. | |
| genpark-reasoning-backtracking-counterfactual-auditor-skill alpha-park/genpark-reasoning-backtracking-counterfactual-auditor-skill Enables MCP-compatible agents to audit reasoning trajectories for loops, deadlocks, and logical contradictions and to perform non-destructive checkpoint rollbacks. | |
| genpark-reasoning-budget-test-time-compute-allocator-skill alpha-park/genpark-reasoning-budget-test-time-compute-allocator-skill Enables agents to dynamically allocate test-time compute, including entropy-driven thinking token budgets, temperature annealing, and reflection passes, while verifying reasoning via MCTS search with process reward modeling, counterfactual | |
| genpark-reasoning-formal-symbolic-proof-checker-skill alpha-park/genpark-reasoning-formal-symbolic-proof-checker-skill Enables agents to check propositional logic assertions and validate formal symbolic deductions through MCP, supporting rigorous step-level reasoning verification. | |
| genpark-reasoning-majority-voting-consensus-engine-skill alpha-park/genpark-reasoning-majority-voting-consensus-engine-skill Enables MCP-connected agents to resample reasoning at varied temperatures, deduplicate semantically equivalent outputs, and select a confidence-weighted majority-vote answer. | |
| genpark-reasoning-mcts-step-verity-evaluator-skill alpha-park/genpark-reasoning-mcts-step-verity-evaluator-skill Enables agents to verify complex math, code, and logic reasoning through MCTS step-level process reward modeling, counterfactual backtracking, symbolic proof checking, and majority-vote consensus so hallucinated branches get pruned. It also | |
| genpark-schnorr-zero-knowledge-prover-skill alpha-park/genpark-schnorr-zero-knowledge-prover-skill Enables AI agents to prove knowledge of a private key through a three-pass commitment, challenge, and response exchange, paired with SHA-256 Merkle inclusion proofs, JWT HMAC-SHA256 claim validation, constant-time secret comparison, and sli | |
| genpark-scientific-consensus-ratio-mapper-skill alpha-park/genpark-scientific-consensus-ratio-mapper-skill Enables autonomous multi-study scientific paper analysis, consensus ratio calculation, citation credibility verification, and multi-hop research queries through the Model Context Protocol. | |
| GenPark Screen Zero Ambient Intent Scorer alpha-park/genpark-screen-zero-ambient-intent-scorer-skill An MCP server that scores lock-screen micro-moments from gaze, dwell, and ambient context signals to estimate impulse-shopping propensity and return personalized shopping actions. It exposes this inference over standard STDIO JSON-RPC so ag | |
| genpark-semantic-entropy-hallucination-estimator-skill alpha-park/genpark-semantic-entropy-hallucination-estimator-skill Enables detecting LLM hallucinations and confabulations by clustering sampled responses into semantic equivalence classes and computing semantic entropy. | |
| genpark-semver-breaking-change-auditor-skill alpha-park/genpark-semver-breaking-change-auditor-skill Enables coding agents and developers to detect SemVer 2.0 breaking changes by statically diffing Python AST public API surfaces, catching removed exports, parameter reordering, and other incompatible signature shifts. It returns determinist | |
| genpark-shortform-hook-retention-scorer-skill alpha-park/genpark-shortform-hook-retention-scorer-skill Enables MCP clients to score the retention quality of the first three seconds of shortform video hooks using audio/video telemetry and transcript input, returning deterministic JSON results for viral hook optimization. | |
| genpark-smart-citation-credibility-scorer-skill alpha-park/genpark-smart-citation-credibility-scorer-skill Enables users to audit academic citation contexts, calculate scientific consensus ratios, and generate credibility badge indexes for verified citations through MCP-compliant tools. | |
| genpark-smart-contract-reentrancy-callgraph-auditor-skill alpha-park/genpark-smart-contract-reentrancy-callgraph-auditor-skill Enables automated Solidity smart contract auditing by analyzing callgraphs and control flow to detect reentrancy vulnerabilities. Integrates with MCP-compatible clients to provide deterministic, zero-dependency security assessments. | |
| genpark-smart-dunning-churn-prevention-strategist-skill alpha-park/genpark-smart-dunning-churn-prevention-strategist-skill Enables autonomous financial agents to optimize payment recovery by analyzing decline-code retry windows and mitigating involuntary churn, while enforcing balanced double-entry ledger records, HMAC-SHA256 signature verification, and sliding | |
| genpark-spatial-obstacle-pointcloud-voxel-slicer-skill alpha-park/genpark-spatial-obstacle-pointcloud-voxel-slicer-skill Enables edge robotics to slice LiDAR/depth point clouds into 2.5D occupancy grids, computing spatial obstacles for real-time telemetry and actuator safety supervision. | |
| genpark-speculative-decoding-verifier-skill alpha-park/genpark-speculative-decoding-verifier-skill Enables verification of draft-target speculative decoding with rejection sampling, acceptance-rate telemetry, and dynamic speedup estimation, alongside edge inference primitives such as INT8 quantization, paged KV allocation, and radix pref | |
| genpark-speech-filler-word-remover-cleaner-skill alpha-park/genpark-speech-filler-word-remover-cleaner-skill Enables transcript timestamp-aligned speech filler word removal and cutlist generation for automated video editing, with zero-dependency MCP integration. | |
| genpark-split-inbox-triage-priority-scorer-skill alpha-park/genpark-split-inbox-triage-priority-scorer-skill Enables multi-channel inbox message priority classification and response SLA tracking, integrating with MCP-compatible clients such as Claude Desktop and Cursor. | |
| genpark-sponsored-agent-intent-auction-bid-router-skill alpha-park/genpark-sponsored-agent-intent-auction-bid-router-skill Enables agents to run second-price Vickrey auctions that match consumer query intent against brand bids while keeping organic recommendations neutral. It also provides privacy-preserving ad monetization routing as a zero-dependency MCP serv | |
| genpark-statistical-zscore-iqr-anomaly-detector-skill alpha-park/genpark-statistical-zscore-iqr-anomaly-detector-skill Enables agents to detect outliers in numerical streams using multiple robust statistical strategies and to perform related analytics such as forecasting, regression, hypothesis testing, and dimensionality reduction via MCP. | |
| Stripe Agentic Dynamic Payment Routing Optimizer alpha-park/genpark-stripe-agentic-dynamic-payment-routing-fee-optimizer-skill Enables evaluating transaction geography, card BIN networks, authorization probabilities, and basis-point rail costs to route payments along Pareto-optimal settlement paths and optimize interchange fees across ACH, FedNow, and card rails. | |
| genpark-structured-data-diff-patcher-skill alpha-park/genpark-structured-data-diff-patcher-skill Enables autonomous agents to compute and atomically apply minimal JSON Patch (RFC 6902) operational diffs for structured data state synchronization. Runs as a zero-dependency Python MCP server supporting deterministic patching, caching, and | |
| genpark-structured-extract-schema-validator-skill alpha-park/genpark-structured-extract-schema-validator-skill Enables deterministic extraction and validation of structured JSON data from inputs using a defined schema. It plugs into MCP-compatible clients like Claude Desktop, Cursor, and Windsurf to return standardized, schema-validated results. | |
| genpark-study-methodology-bias-detector-skill alpha-park/genpark-study-methodology-bias-detector-skill Enables auditing scientific papers for methodological biases such as selection bias and p-hacking, and assessing citation credibility and research consensus. | |
| genpark-synthetic-persona-interview-simulator-skill alpha-park/genpark-synthetic-persona-interview-simulator-skill Enables running multi-perspective synthetic consumer focus groups that simulate persona interviews to gauge market sentiment. Delivers deterministic, JSON-schema-validated results over the Model Context Protocol for use in autonomous resear | |
| genpark-terminal-session-semantic-history-search-skill alpha-park/genpark-terminal-session-semantic-history-search-skill Enables semantic search of shell session history, matching natural-language intents to past CLI commands, including Warp sessions, for fast keyboard-first command discovery and reuse. | |
| genpark-time-series-exponential-smoothing-forecaster-skill alpha-park/genpark-time-series-exponential-smoothing-forecaster-skill Enables statistical forecasting and anomaly detection over numerical time-series data using Holt linear smoothing, multi-step projections, and variance-based confidence bands. | |
| genpark-today-ai-proactive-daily-agenda-synthesizer-skill alpha-park/genpark-today-ai-proactive-daily-agenda-synthesizer-skill Enables personal AI agents to synthesize proactive daily agendas and cognitive briefings, orchestrating circadian energy focus blocks, asynchronous task triage, and meeting preparation. It runs as a zero-dependency MCP server exposing these | |
| genpark-topological-sorter-tarjan-scc-skill alpha-park/genpark-topological-sorter-tarjan-scc-skill Enables agents to resolve dependencies and analyze directed graphs through topological sorting, strongly connected components, shortest paths, maximum flow, minimum spanning trees, and centrality ranking via MCP. | |
| genpark-url-canonicalization-anti-crawler-trap-skill alpha-park/genpark-url-canonicalization-anti-crawler-trap-skill Enables autonomous web agents to canonicalize URLs, detect anti-crawler traps such as circular paths and infinite pagination, prune DOM tokens, auto-map forms, transform tables into JSON, and evaluate action trajectories through MCP. | |
| genpark-value-at-risk-cvar-expected-shortfall-skill alpha-park/genpark-value-at-risk-cvar-expected-shortfall-skill Enables quantitative risk analysis by calculating portfolio Value-at-Risk and Conditional VaR/Expected Shortfall across parametric and historical loss distributions, along with related option Greeks, Monte Carlo simulations, and fixed-incom | |
| genpark-vector-clock-causal-ordering-skill alpha-park/genpark-vector-clock-causal-ordering-skill Enables agents to stamp events with vector clocks, resolve state via LWW CRDT reconciliation, and coordinate distributed swarms through token-bucket gossip, Raft leader/quorum voting, and two-phase commit. It runs over MCP with zero externa | |
| genpark-video-silence-jumpcut-cadence-analyzer-skill alpha-park/genpark-video-silence-jumpcut-cadence-analyzer-skill Enables audio silence detection and jumpcut cadence/pacing analysis for shortform video editing, producing precise cut-lists and telemetry through the Model Context Protocol. | |
| genpark-visual-diagram-architecture-synthesizer-skill alpha-park/genpark-visual-diagram-architecture-synthesizer-skill Enables translation of geometric bounding boxes, flowchart node connections, and architectural sketches into clean Mermaid graphs, JSON topology matrices, and boilerplate code scaffolds. | |
| genpark-visual-grounding-spec-comparison-skill alpha-park/genpark-visual-grounding-spec-comparison-skill Enables AI agents to compare visual specifications and calculate physical dimensions and degrees of freedom from multimodal inputs. | |
| genpark-voice-turn-taking-endpointing-detector-skill alpha-park/genpark-voice-turn-taking-endpointing-detector-skill Enables real-time voice activity detection, dynamic silence endpointing, and barge-in interruption for conversational voice agents. | |
| Waterfall Enrichment Orchestrator alpha-park/genpark-waterfall-enrichment-orchestrator-skill Enables multi-provider waterfall data enrichment for B2B prospects, firmographics, and verified decision-maker corporate emails via MCP. | |
| genpark-web-form-input-schema-auto-mapper-skill alpha-park/genpark-web-form-input-schema-auto-mapper-skill Enables autonomous web form inspection and schema auto-mapping by matching input attributes, autocomplete hints, and regex validations to agent state, while also pruning DOMs and converting tables into structured JSON for web agents. | |
| genpark-workplace-goal-to-artifact-dag-orchestrator-skill alpha-park/genpark-workplace-goal-to-artifact-dag-orchestrator-skill Enables enterprise work agents to decompose high-level business objectives into topological sub-tasks and directly synthesize final deliverables such as financial spreadsheets, executive presentations, and analytical reports. |
27,201–27,250 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.