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 |
|---|---|
| GenParkEmbodiedSpatial3DOccupancyGridSolver alpha-park/genpark-embodied-spatial-3d-occupancy-grid-solver-skill Enables real-time 3D spatial occupancy mapping, Bayesian log-odds occupancy updates, Bresenham raycasting, trajectory generation, and sphere collision solving for autonomous robotic systems through MCP tools. | |
| GenParkEmbodiedTactileSlipForceFeedbackController alpha-park/genpark-embodied-tactile-slip-force-feedback-controller-skill Exposes a zero-dependency MCP server that ingests depth-sensor, joint-encoder, and tactile-array telemetry to deliver real-time spatial intelligence, trajectory generation, and safety-guarded control vectors for autonomous robots. It tracks | |
| GenParkEmbodiedTrajectoryQuinticSplineSmoother alpha-park/genpark-embodied-trajectory-quintic-spline-smoother-skill Enables autonomous robotic systems to generate real-time smoothed trajectories with continuous boundary position, velocity, and acceleration constraints and analytic jerk minimization via MCP. | |
| Enterprise Compliance Data Retention GDPR Erasure Sentinel alpha-park/genpark-enterprise-compliance-data-retention-gdpr-erasure-sentinel-skill Enables users to audit relational databases, vector embeddings, and activity logs for GDPR/CCPA erasure requests, apply legal-hold exemptions, perform cascading pseudo-anonymization, and generate cryptographic HMAC-SHA256 proof-of-erasure c | |
| genpark-enterprise-compliance-pii-redaction-sentinel-skill alpha-park/genpark-enterprise-compliance-pii-redaction-sentinel-skill Enables detection and deterministic masking of personally identifiable information, financial account numbers, JWT tokens, and cryptographic keys so sensitive data can be sanitized before further processing. Runs as a zero-dependency Python | |
| genpark-enterprise-context-permission-boundary-auditor-skill alpha-park/genpark-enterprise-context-permission-boundary-auditor-skill Enables enterprise context governance by auditing ingested content, classifying security clearance tiers, sanitizing cross-department prompts, and preventing data leaks through role-based permission boundaries. | |
| genpark-enterprise-executive-briefing-doc-synthesizer-skill alpha-park/genpark-enterprise-executive-briefing-doc-synthesizer-skill Enables transformation of raw multi-source enterprise findings into comprehensive, structured executive briefings with auto-generated executive summaries, risk registers, decision matrices, and appendix citations. It runs as a native MCP se | |
| genpark-enterprise-identity-token-exchange-bridge-skill alpha-park/genpark-enterprise-identity-token-exchange-bridge-skill Enables agents and services to perform on-behalf-of token exchange across enterprise systems, with scoped permission delegation, automatic token lifetime refresh, and zero-leakage ephemeral credentials. It runs as a zero-dependency MCP serv | |
| genpark-enterprise-knowledge-graph-provenance-tracer-skill alpha-park/genpark-enterprise-knowledge-graph-provenance-tracer-skill Enables agents to ground claims in enterprise knowledge by hashing source chunks, tracing claims back to their origins, validating clearance boundaries, and maintaining audit trails to support anti-hallucination workflows. | |
| genpark-enterprise-meeting-action-item-extractor-skill alpha-park/genpark-enterprise-meeting-action-item-extractor-skill Enables analysis of multi-speaker meeting transcripts from Tencent Meeting, Zoom, and Teams to extract explicit commitments, dates, and assignees. It prioritizes tasks with an Eisenhower urgency-importance matrix and formats collaborative t | |
| genpark-enterprise-merkle-audit-proof-anchor-skill alpha-park/genpark-enterprise-merkle-audit-proof-anchor-skill Enables agents and audit systems to hash execution logs into tamper-proof Merkle trees, compute cryptographic inclusion proofs, and verify audit-trail integrity on demand. It runs as a zero-dependency Python MCP server (stdio JSON-RPC) or a | |
| Enterprise Agentic RBAC/ABAC Least-Privilege Policy Synthesizer & Blast-Radius Auditor alpha-park/genpark-enterprise-rbac-least-privilege-policy-synthesizer-skill Enables synthesizing tight JSON authorization policies from historical agent tool-call audit logs, flagging over-permissioned wildcard grants and quantifying how much the attack surface shrinks. It also validates individual actions against | |
| genpark-enterprise-slack-wecom-knowledge-base-auto-curator alpha-park/genpark-enterprise-slack-wecom-knowledge-base-auto-curator-skill Enables parsing of messy multi-turn Slack and WeChat Work troubleshooting threads into validated Q&A resolution pairs, stripping duplicate organizational knowledge and synthesizing structured Markdown SOP runbooks. Exposes this curation cap | |
| genpark-enterprise-slide-deck-narrative-compiler-skill alpha-park/genpark-enterprise-slide-deck-narrative-compiler-skill Enables transforming raw enterprise documents, meeting transcripts, and KPI metrics into structured executive slide decks with layout templates, card callouts, speaker notes, and timing budgets through MCP-compatible workflows. | |
| genpark-enterprise-spreadsheet-formula-dag-synthesizer-skill alpha-park/genpark-enterprise-spreadsheet-formula-dag-synthesizer-skill Enables synthesis of multi-tab financial models with circular-reference detection, formula dependency DAG compilation (SUMIFS, XLOOKUP, CAGR, NPV), and deterministic preview cell matrix evaluation through MCP. | |
| genpark-episodic-memory-consolidation-decay-skill alpha-park/genpark-episodic-memory-consolidation-decay-skill Enables agents to decay stale transient interactions and consolidate frequent episodic events into enduring semantic user persona traits using sleep-cycle and forgetting-curve inspired memory processing. | |
| genpark-evm-flashloan-arbitrage-slippage-guard-skill alpha-park/genpark-evm-flashloan-arbitrage-slippage-guard-skill Enables automated EVM flash loan arbitrage risk assessment and MEV sandwich attack protection for Aave and Uniswap v3, offering deterministic slippage and vulnerability analysis through the Model Context Protocol. | |
| genpark-fintech-transaction-velocity-fraud-sentinel-skill alpha-park/genpark-fintech-transaction-velocity-fraud-sentinel-skill Enables autonomous financial agents and payment systems to analyze transaction streams in real time, detect velocity-based fraud patterns such as card testing, volume spikes, and account takeovers, and produce balanced ledger records with a | |
| genpark-fintech-webhook-idempotent-replay-guard-skill alpha-park/genpark-fintech-webhook-idempotent-replay-guard-skill Enables secure ingestion and validation of payment webhooks using HMAC-SHA256 signatures, replay tolerance, and atomic idempotency locking to prevent duplicate financial transactions. It provides deterministic ledger integrity and risk audi | |
| genpark-flaky-test-timing-non-determinism-detector-skill alpha-park/genpark-flaky-test-timing-non-determinism-detector-skill Enables automated analysis of test suite traces to identify timing races and state pollution, helping developers mitigate flaky tests through MCP-compliant clients. | |
| genpark-generative-image-spatial-upscale-tiler-skill alpha-park/genpark-generative-image-spatial-upscale-tiler-skill Enables high-resolution image canvas processing by slicing images into spatial grid tiles and blending seams for seamless generative upscaling, compatible with Magnific AI / Krea AI workflows. | |
| genpark-graph-dijkstra-astar-pathfinder-skill alpha-park/genpark-graph-dijkstra-astar-pathfinder-skill Enables graph pathfinding and network analysis through MCP, including Dijkstra/A* shortest paths, topological dependency resolution, maximum flow, minimum spanning trees, and PageRank centrality for agent planning. | |
| genpark-html-dom-semantic-tree-pruner-skill alpha-park/genpark-html-dom-semantic-tree-pruner-skill Enables autonomous web agents to prune raw HTML into accessibility-friendly semantic trees with 80%+ token reduction, auto-map form input schemas, convert HTML/Markdown tables into type-inferred JSON records, and score agent execution traje | |
| genpark-hubx-ai-apps-orchestration-skill alpha-park/genpark-hubx-ai-apps-orchestration-skill Enables agents to orchestrate and call tools across HubX's mobile AI app portfolio for multi-model chat, plant/vision diagnostics, generative image and design, nutrition tracking, audio note summarization, language tutoring, and wellness wo | |
| genpark-hubx-multimodal-mobile-agent-mcp alpha-park/genpark-hubx-multimodal-mobile-agent-mcp Enables autonomous agents to orchestrate HubX mobile AI tools for plant and nutrition vision diagnostics, voice transcription and summarization, photo-realistic portrait and art generation, and interior/exterior spatial design through struc | |
| Hume AI Empathic Voice Prosody & Expression Analyzer alpha-park/genpark-hume-ai-empathic-voice-prosody-expression-analyzer-skill Exposes an MCP tool that fuses acoustic prosody measurements (F0, speaking rate, jitter, pause ratio) with semantic sentiment to infer high-dimensional emotional states from speech. Returns tone, speaking-rate multiplier, and pitch-shift di | |
| genpark-hybrid-bounding-box-ocr-table-reconstructor-skill alpha-park/genpark-hybrid-bounding-box-ocr-table-reconstructor-skill Enables deterministic reconstruction of complex tables from OCR bounding boxes, including multi-column layouts, merged headers, grid hierarchies, formula auditing, and PII redaction through MCP. | |
| genpark-hybrid-rerank-fusion-retriever-skill alpha-park/genpark-hybrid-rerank-fusion-retriever-skill Enables AI agents and MCP clients to combine and rerank results from multiple search or retrieval sources using Reciprocal Rank Fusion and hybrid rank fusion scoring. It exposes deterministic fusion and reranking execution over MCP with str | |
| genpark-hypothesis-welch-t-test-statistical-evaluator-skill alpha-park/genpark-hypothesis-welch-t-test-statistical-evaluator-skill Enables statistical A/B testing by computing Welch's two-sample t-test, Satterthwaite degrees of freedom, and two-tailed p-values, alongside time-series forecasting, anomaly detection, regression, and PCA through MCP tools. | |
| genpark-immutable-double-entry-ledger-kernel-skill alpha-park/genpark-immutable-double-entry-ledger-kernel-skill Enables MCP clients and autonomous financial agents to submit payment webhook events, journal entries, or transaction streams and receive cryptographically verified, balanced double-entry ledger records with HMAC signatures and hash-chained | |
| InstacartCartSubstitutionAffinityResolver alpha-park/genpark-instacart-cart-substitution-affinity-resolver-skill This MCP server enables agents to handle real-time out-of-stock grocery items by scoring candidate replacements against dietary constraints (vegan, gluten-free, organic), unit price delta ceilings, and brand affinity. It returns a determini | |
| genpark-instinct-proactive-intent-reflex-skill alpha-park/genpark-instinct-proactive-intent-reflex-skill Enables personal AI agents to detect user attention cues, compute intent probabilities, and execute guarded dry-run actions through MCP, with low-latency reflex routing, episodic memory, and safety guardrails. | |
| genpark-int8-symmetric-per-tensor-quantizer-skill alpha-park/genpark-int8-symmetric-per-tensor-quantizer-skill Enables agents to perform symmetric INT8 per-tensor and per-channel quantization of LLM weights and activations, returning SNR and MSE reconstruction metrics for edge inference optimization. | |
| genpark-inverse-kinematics-joint-limit-solver-skill alpha-park/genpark-inverse-kinematics-joint-limit-solver-skill Enables solving inverse kinematics for 6-DOF robotic manipulators (UR5 / Franka Emika) by converting pose to joint angles, with native MCP support. | |
| genpark-jev-system1-subconscious-decision-skill alpha-park/genpark-jev-system1-subconscious-decision-skill Enables agents to resolve routine typed routing, loop-stall arbitration, and tool safety checks locally instead of invoking a frontier LLM, returning schema-enforced decision outputs and telemetry at sub-millisecond latency. Also provides r | |
| genpark-jev-typed-state-action-router-mcp alpha-park/genpark-jev-typed-state-action-router-mcp Enables AI agents to arbitrate typed state-action schemas and dispatch deterministic actions locally, so routine or reflexive decisions are resolved in sub-millisecond fashion instead of incurring expensive frontier-LLM calls. It also appli | |
| genpark-just-in-time-mcp-tool-compiler-skill alpha-park/genpark-just-in-time-mcp-tool-compiler-skill Enables agents to dynamically generate typed MCP tool schemas, validate Python execution ASTs against unsafe imports, and hot-plug sandboxed callable handlers into an active runtime. This allows new tools to be synthesized and safely execut | |
| genpark-jwt-hmac-sha256-token-attestation-skill alpha-park/genpark-jwt-hmac-sha256-token-attestation-skill Enables agents to cryptographically attest and verify identity and execution state through RFC 7519 JWT HMAC-SHA256 signature checks, claims and expiration validation, constant-time secret comparison, SHA-256 Merkle inclusion proofs, Schnor | |
| genpark-knowledge-graph-entity-relation-triplet-extractor-skill alpha-park/genpark-knowledge-graph-entity-relation-triplet-extractor-skill Enables agents to build and query structured semantic graphs, extracting, traversing and multi-hop reasoning over entity-relation-object triples while producing Cypher and JSON-LD graph output. It also combines BM25 lexical and dense vector | |
| genpark-kv-cache-paged-attention-allocator-skill alpha-park/genpark-kv-cache-paged-attention-allocator-skill Enables edge AI agents to optimize inference memory and latency by mapping logical blocks to non-contiguous physical pages, tracking fragmentation, and exposing related MCP tools. | |
| genpark-legal-clause-cross-reference-resolver-skill alpha-park/genpark-legal-clause-cross-reference-resolver-skill Enables contract analysis by resolving cross-references between legal clauses and analyzing defined-term graphs to detect circular references, audit formulas, and substitute statutory definitions. | |
| genpark-linear-regression-gradient-descent-engine-skill alpha-park/genpark-linear-regression-gradient-descent-engine-skill Enables users to perform multivariate linear regression with gradient descent, Holt linear forecasting, Welch's t-test evaluation, anomaly detection, and PCA dimensionality reduction through MCP-compatible clients using only Python standard | |
| genpark-linear-sprint-velocity-cycle-forecaster-skill alpha-park/genpark-linear-sprint-velocity-cycle-forecaster-skill Enables agile sprint backlog velocity calculation and milestone completion prediction for Linear, integrating with MCP-compatible clients through a zero-dependency Python server. | |
| genpark-live-artifact-version-diff-tracker-skill alpha-park/genpark-live-artifact-version-diff-tracker-skill Enables AI agents and MCP clients to compute real-time, in-memory unified diffs between versions of live artifacts along with structured change telemetry. It runs as a deterministic, zero-dependency Python MCP server that plugs into Claude | |
| genpark-long-horizon-autonomous-task-resumption-skill alpha-park/genpark-long-horizon-autonomous-task-resumption-skill Enables agents to persist and resume long-horizon tasks using cryptographic event-sourced checkpoints, idempotency deduplication, scheduled heartbeats, pause/resume tokens, and fail-safe recovery. | |
| genpark-low-latency-prosody-sentiment-modulator-skill alpha-park/genpark-low-latency-prosody-sentiment-modulator-skill Enables real-time voice agents to dynamically modulate speech pitch, cadence, and pause inflections via prosody, SSML, and emotion pacing for low-latency conversational audio. | |
| genpark-managed-agent-fleet-lifecycle-supervisor-skill alpha-park/genpark-managed-agent-fleet-lifecycle-supervisor-skill Enables enterprise agent fleets to register workers, dispatch tasks by capability, monitor continuous heartbeat telemetry, trip automated circuit breakers, and recover from checkpointed state through a zero-dependency MCP server. | |
| genpark-manus-autonomous-generalist-sandbox-executor-skill alpha-park/genpark-manus-autonomous-generalist-sandbox-executor-skill Enables MCP-compliant clients to run autonomous task decomposition, multi-modal web and sandbox execution, and self-correcting goal resolution through a zero-dependency Python server. | |
| Manus Autonomous Web Browser DOM Actuator alpha-park/genpark-manus-autonomous-web-browser-dom-actuator-skill Enables autonomous web automation by flattening DOM trees into pruned accessibility trees, synthesizing robust CSS/XPath locators, and compiling goal-driven multi-step action plans with verification. It exposes these capabilities through MC | |
| genpark-markdown-table-to-json-transformer-skill alpha-park/genpark-markdown-table-to-json-transformer-skill Enables agents to transform tabular Markdown content into structured, type-inferred records with normalized formatting through an MCP-compatible interface. |
27,001–27,050 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.