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-quantum-grover-search-oracle-amplifier-skill alphaparkinc/genpark-quantum-grover-search-oracle-amplifier-skill Enables simulation of quantum circuits, including state-vector evolution, entanglement, measurement, and Grover amplitude amplification for unstructured search tasks through MCP-compatible AI assistants. | |
| genpark-quantum-measurement-born-rule-sampler-skill alphaparkinc/genpark-quantum-measurement-born-rule-sampler-skill Enables users to simulate quantum circuits, evolve qubit state vectors, apply gates such as Hadamard and CNOT, perform Born-rule projective measurements with Monte Carlo shot histograms, and run Grover amplitude amplification through MCP-co | |
| genpark-quantum-qubit-state-vector-simulator-skill alphaparkinc/genpark-quantum-qubit-state-vector-simulator-skill Enables simulation of multi-qubit quantum circuits using complex state vectors, including unitary gates, entanglement, Born-rule measurement sampling, state fidelity, and probability distributions via MCP. | |
| genpark-quantum-teleportation-entanglement-circuit-skill alphaparkinc/genpark-quantum-teleportation-entanglement-circuit-skill Enables users to simulate quantum circuits, evolve qubit state vectors, generate EPR Bell pairs, perform Born-rule measurement, and run Grover amplitude amplification through a zero-dependency MCP interface. | |
| genpark-raft-leader-election-consensus-kernel-skill alphaparkinc/genpark-raft-leader-election-consensus-kernel-skill Enables agents to run distributed consensus and coordination primitives over MCP, including Raft leader election with terms and quorum validation, LWW CRDT state reconciliation, vector-clock causal stamping, token-bucket gossip disseminatio | |
| genpark-rag-retrieval-faithfulness-hallucination-auditor-skill alphaparkinc/genpark-rag-retrieval-faithfulness-hallucination-auditor-skill Enables deterministic auditing of RAG retrieval faithfulness and hallucination scores, providing structured JSON output for AI agents and MCP-compliant clients. | |
| genpark-raycast-script-command-palette-router-skill alphaparkinc/genpark-raycast-script-command-palette-router-skill Enables command palette argument parsing and deep-link shortcut dispatch for Raycast/Alfred, allowing developers to route command invocations and execute keyboard-first productivity workflows through MCP. | |
| genpark-realtime-voice-noise-suppression-gate-skill alphaparkinc/genpark-realtime-voice-noise-suppression-gate-skill Enables real-time acoustic noise floor estimation and spectral gating to suppress ambient reverberation in voice audio through an MCP-compatible interface. | |
| genpark-realtime-voice-turn-taking-orchestrator-skill alphaparkinc/genpark-realtime-voice-turn-taking-orchestrator-skill Enables low-latency conversational turn-taking and barge-in handling for real-time voice AI interactions, orchestrating speech flow with sub-100ms responsiveness. | |
| genpark-realtime-websocket-heartbeat-reconnector-skill alphaparkinc/genpark-realtime-websocket-heartbeat-reconnector-skill Enables resilient real-time WebSocket streams with automatic heartbeat monitoring, reconnection, and state resynchronization for AI agents and MCP-compliant clients. | |
| genpark-reasoning-backtracking-counterfactual-auditor-skill alphaparkinc/genpark-reasoning-backtracking-counterfactual-auditor-skill Enables agents to audit their own reasoning trajectories for loops, deadlocks, and logical contradictions, then perform non-destructive checkpoint rollbacks to a sound prior step. It combines step-level reward evaluation, MCTS search, symbo | |
| genpark-reasoning-budget-test-time-compute-allocator-skill alphaparkinc/genpark-reasoning-budget-test-time-compute-allocator-skill Enables agents to dynamically schedule thinking-token budgets, reflection passes, and temperature annealing while performing MCTS/process-reward verification, proof checking, and consensus voting through a standard-library STDIO MCP interfa | |
| genpark-reasoning-formal-symbolic-proof-checker-skill alphaparkinc/genpark-reasoning-formal-symbolic-proof-checker-skill Enables agents to validate propositional logic assertions and formal symbolic deductions through a zero-dependency MCP STDIO server, supporting proof checking and reasoning verification. | |
| genpark-reasoning-majority-voting-consensus-engine-skill alphaparkinc/genpark-reasoning-majority-voting-consensus-engine-skill Enables agents to resample reasoning paths, semantically deduplicate candidate answers, and confidence-weight votes to produce a consensus result. It also exposes verification and proof-checking tools over MCP STDIO JSON-RPC. | |
| genpark-reasoning-mcts-step-verity-evaluator-skill alphaparkinc/genpark-reasoning-mcts-step-verity-evaluator-skill Enables MCP clients to perform step-level process reward evaluation, MCTS-guided reasoning search, hallucination branch pruning, and formal verification for complex math, code, and logic problems. | |
| genpark-schnorr-zero-knowledge-prover-skill alphaparkinc/genpark-schnorr-zero-knowledge-prover-skill Enables agents to perform Schnorr zero-knowledge identification and cryptographic attestation through a native MCP interface, including commitment-challenge-response proofs, JWT validation, Merkle inclusion checks, and replay protection. | |
| genpark-scientific-consensus-ratio-mapper-skill alphaparkinc/genpark-scientific-consensus-ratio-mapper-skill Enables multi-study scientific assertion analysis and consensus ratio calculation, integrating with Consensus.app and Elicit to verify citations and execute research queries. | |
| genpark-semantic-entropy-hallucination-estimator-skill alphaparkinc/genpark-semantic-entropy-hallucination-estimator-skill Enables estimating LLM hallucination and confabulation by clustering sampled responses into semantic equivalence classes and computing semantic entropy. It provides a plug-and-play validation filter for agent pipelines using the MCP protoco | |
| genpark-semver-breaking-change-auditor-skill alphaparkinc/genpark-semver-breaking-change-auditor-skill Enables autonomous coding agents to audit source-code changes for SemVer 2.0 breaking changes by inspecting AST public API surface diffs, parameter reordering, and removed exports. Produces deterministic refactoring plans and dependency met | |
| genpark-shortform-hook-retention-scorer-skill alphaparkinc/genpark-shortform-hook-retention-scorer-skill Enables MCP-compatible clients to score the retention quality of the first three seconds of shortform video hooks using deterministic, zero-dependency Python tooling. | |
| genpark-smart-citation-credibility-scorer-skill alphaparkinc/genpark-smart-citation-credibility-scorer-skill Enables automated scientific paper analysis, citation credibility verification, consensus ratio calculation, and multi-hop research queries through the Model Context Protocol, integrating with MCP-compliant clients. | |
| genpark-smart-contract-reentrancy-callgraph-auditor-skill alphaparkinc/genpark-smart-contract-reentrancy-callgraph-auditor-skill Enables Solidity callgraph and control-flow analysis to detect reentrancy vulnerabilities in smart contracts, with MCP integration for automated security auditing and DeFi vulnerability triage. | |
| genpark-smart-dunning-churn-prevention-strategist-skill alphaparkinc/genpark-smart-dunning-churn-prevention-strategist-skill Enables autonomous agents to optimize payment recovery by applying decline-code-specific retry windows and reducing involuntary churn through MCP-accessible ledger and fraud-checking workflows. | |
| genpark-spatial-obstacle-pointcloud-voxel-slicer-skill alphaparkinc/genpark-spatial-obstacle-pointcloud-voxel-slicer-skill Enables edge LiDAR/depth point cloud processing into 2.5D occupancy grids for robotics safety and control, with native MCP integration for telemetry and actuator supervision. | |
| genpark-speculative-decoding-verifier-skill alphaparkinc/genpark-speculative-decoding-verifier-skill Deliversdependency-free slash unavailable: | |
| genpark-speech-filler-word-remover-cleaner-skill alphaparkinc/genpark-speech-filler-word-remover-cleaner-skill Enables MCP-compatible clients to detect and remove speech filler words using timestamp-aligned transcripts, and generate precise cut lists for video editing workflows. | |
| genpark-split-inbox-triage-priority-scorer-skill alphaparkinc/genpark-split-inbox-triage-priority-scorer-skill Enables multi-channel inbox message priority classification and response SLA tracking through MCP-compliant clients, providing deterministic priority scoring and structured execution telemetry. | |
| genpark-sponsored-agent-intent-auction-bid-router-skill alphaparkinc/genpark-sponsored-agent-intent-auction-bid-router-skill Enables running second-price Vickrey auctions that match consumer query intent with brand bids while preserving organic recommendation neutrality. It integrates as a zero-dependency MCP server for agentic commerce and privacy-preserving ad | |
| genpark-statistical-zscore-iqr-anomaly-detector-skill alphaparkinc/genpark-statistical-zscore-iqr-anomaly-detector-skill Enables zero-dependency statistical analysis of numerical and time-series streams, flagging outliers via standard Z-score, modified median absolute deviation (MAD), and Tukey IQR fences. Also supports trend forecasting with Holt linear smoo | |
| Stripe Agentic Dynamic Payment Routing & Interchange Fee Optimizer alphaparkinc/genpark-stripe-agentic-dynamic-payment-routing-fee-optimizer-skill Enables evaluation of transaction geography, card BIN networks, authorization probabilities, and basis-point rail costs to select Pareto-optimal settlement paths across ACH, FedNow, and card rails. Returns the chosen rail, processing fee, e | |
| genpark-structured-data-diff-patcher-skill alphaparkinc/genpark-structured-data-diff-patcher-skill Enables AI agents to compute and apply minimal JSON Patch (RFC 6902) operational diffs for atomic state synchronization between structured documents. Runs as a zero-dependency Python MCP server with deterministic outputs and sub-millisecond | |
| genpark-structured-extract-schema-validator-skill alphaparkinc/genpark-structured-extract-schema-validator-skill Enables agents to deterministically extract structured entities from input payloads and validate or coerce them against JSON schemas, returning a standardized response dossier with execution telemetry. It runs as a zero-dependency MCP serve | |
| genpark-study-methodology-bias-detector-skill alphaparkinc/genpark-study-methodology-bias-detector-skill Enables autonomous auditing of scientific papers for methodology flaws, identifying selection bias and p-hacking, while computing consensus ratios and verifying citation credibility through MCP-compliant tooling. | |
| genpark-supply-chain-package-dependency-quarantine-scanner-skill alphaparkinc/genpark-supply-chain-package-dependency-quarantine-scanner-skill Enables AI agents and MCP-compliant clients to audit software bills of materials and quarantine supply-chain malicious package dependencies using Snyk and Socket.dev. | |
| genpark-synthetic-persona-interview-simulator-skill alphaparkinc/genpark-synthetic-persona-interview-simulator-skill Enables AI agents and developers to run deterministic, multi-perspective synthetic consumer focus groups and analyze market sentiment through JSON-RPC/MCP tools. | |
| genpark-terminal-session-semantic-history-search-skill alphaparkinc/genpark-terminal-session-semantic-history-search-skill Enables semantic search of shell session history, matching user intents to relevant CLI commands for keyboard-first developer workflows. | |
| genpark-time-series-exponential-smoothing-forecaster-skill alphaparkinc/genpark-time-series-exponential-smoothing-forecaster-skill Enables agents to forecast numerical trends with zero-dependency Holt linear exponential smoothing, multi-step horizons, variance confidence bands, and supporting statistical anomaly detection, regression, hypothesis testing, and PCA. | |
| genpark-today-ai-proactive-daily-agenda-synthesizer-skill alphaparkinc/genpark-today-ai-proactive-daily-agenda-synthesizer-skill Enables personal AI agents to proactively synthesize daily agendas and cognitive briefings by orchestrating circadian energy focus blocks, asynchronous task triage, and meeting preparation from sensory inputs, task goals, or ambient telemet | |
| genpark-topological-sorter-tarjan-scc-skill alphaparkinc/genpark-topological-sorter-tarjan-scc-skill Enables MCP clients to run zero-dependency graph algorithms—including topological sorting, strongly connected component detection, shortest paths, maximum flow, minimum spanning trees, and PageRank—for agent dependency resolution and execut | |
| genpark-ugc-creator-brief-auction-matchmaker-skill alphaparkinc/genpark-ugc-creator-brief-auction-matchmaker-skill Enables autonomous matching of UGC creators to brand briefs via a deterministic programmatic auction and video matchmaking workflow. It integrates as an MCP server so AI agents can run creator brief auctions and produce structured results w | |
| genpark-universal-mcp-tool-protocol-gateway-skill alphaparkinc/genpark-universal-mcp-tool-protocol-gateway-skill A lightweight, zero-dependency MCP gateway adapter that enables Claude/Cursor agents to process structured JSON payloads and integrate with GenPark AI agent pipelines. | |
| genpark-url-canonicalization-anti-crawler-trap-skill alphaparkinc/genpark-url-canonicalization-anti-crawler-trap-skill Enables autonomous web browsing and extraction by canonicalizing URLs, detecting anti-crawler traps such as circular paths and infinite pagination, pruning DOM content, mapping forms, converting tables to JSON, and evaluating agent trajecto | |
| genpark-value-at-risk-cvar-expected-shortfall-skill alphaparkinc/genpark-value-at-risk-cvar-expected-shortfall-skill Enables quantitative portfolio tail-risk analysis, option Greeks, Monte Carlo stochastic simulations, fixed-income duration/convexity, and Nelson-Siegel yield-curve interpolation through MCP tools. | |
| genpark-vector-clock-causal-ordering-skill alphaparkinc/genpark-vector-clock-causal-ordering-skill Enables agents to track causal relationships, reconcile concurrent state changes, and coordinate consensus across distributed networks using vector clocks, CRDTs, gossip, and quorum-based protocols. | |
| genpark-video-silence-jumpcut-cadence-analyzer-skill alphaparkinc/genpark-video-silence-jumpcut-cadence-analyzer-skill Enables analyzing audio silence in videos to calculate jumpcut cadences and pacing, returning precise cut-lists and telemetry for shortform video editing. | |
| genpark-visual-diagram-architecture-synthesizer-skill alphaparkinc/genpark-visual-diagram-architecture-synthesizer-skill Enables users to translate geometric bounding boxes, flowchart node connections, and architectural sketches into clean Mermaid graphs, JSON topology matrices, and boilerplate code scaffolds through MCP. | |
| genpark-visual-grounding-spec-comparison-skill alphaparkinc/genpark-visual-grounding-spec-comparison-skill Enables agents to ground and compare visual specifications by calculating physical dimensions and degrees of freedom from multimodal inputs. | |
| Waterfall Enrichment Orchestrator alphaparkinc/genpark-waterfall-enrichment-orchestrator-skill Enables multi-provider waterfall enrichment of B2B prospect data, combining firmographic details and verified decision-maker emails with automated fallback and deliverability filtering. | |
| genpark-web-form-input-schema-auto-mapper-skill alphaparkinc/genpark-web-form-input-schema-auto-mapper-skill Enables autonomous agents to inspect live web pages, prune noisy DOM content down to semantic essentials, and bind each form field to agent state by matching input attributes, autocomplete hints, and regex validations. It also converts HTML | |
| genpark-workplace-goal-to-artifact-dag-orchestrator-skill alphaparkinc/genpark-workplace-goal-to-artifact-dag-orchestrator-skill Enables agents to break high-level business objectives into dependency-ordered sub-task graphs and then directly generate the finished deliverables, such as financial spreadsheets, executive presentations, and analytical reports. It runs as |
27,651–27,700 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.