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-creator-content-deliverable-calendar-scheduler-skill alphaparkinc/genpark-creator-content-deliverable-calendar-scheduler-skill Enables autonomous scheduling of creator content deliverable calendars and embargo wave campaigns through natural language, integrating with MCP-compliant clients for deterministic, zero-dependency execution. | |
| genpark-creator-msa-contract-deliverable-escrow-skill alphaparkinc/genpark-creator-msa-contract-deliverable-escrow-skill Enables AI agents to broker creator MSA contracts and escrow deliverable milestones through Impact.com, with deterministic, zero-dependency execution and native MCP integration. | |
| genpark-creator-paid-amplification-roi-synthesizer-skill alphaparkinc/genpark-creator-paid-amplification-roi-synthesizer-skill Enables modeling and synthesis of creator paid amplification ROI, spark ads performance, and whitelisted return on ad spend (ROAS) for influencer marketing campaigns. It provides deterministic, zero-dependency calculations through MCP for u | |
| genpark-creator-product-seeding-parcel-dispatcher-skill alphaparkinc/genpark-creator-product-seeding-parcel-dispatcher-skill Enables autonomous creator operations and influencer marketing automation by dispatching product seeding kits and coordinating unboxing workflows through MCP-compliant clients. | |
| genpark-creator-short-video-hook-retention-scorer-skill alphaparkinc/genpark-creator-short-video-hook-retention-scorer-skill Enables AI agents and MCP clients to deterministically score creator short-video hooks for 3-second retention and scroll-stop effectiveness, returning structured JSON telemetry. It runs as a zero-dependency Python MCP server for seamless in | |
| genpark-cross-chain-bridge-invariant-anomaly-detector-skill alphaparkinc/genpark-cross-chain-bridge-invariant-anomaly-detector-skill Enables auditing cross-chain bridge token reserve invariants and monitoring outflow spikes for LayerZero and Wormhole bridges, helping detect reserve anomalies and potential vulnerabilities. | |
| genpark-cross-lingual-semantic-intent-router-skill alphaparkinc/genpark-cross-lingual-semantic-intent-router-skill Enables cross-lingual semantic intent routing and multilingual agent dispatch through a deterministic, zero-dependency MCP server, allowing AI agents to parse and route user queries across languages and delegate to appropriate agents with s | |
| genpark-cross-platform-commerce-inventory-arbitrage-skill alphaparkinc/genpark-cross-platform-commerce-inventory-arbitrage-skill Enables real-time multi-merchant price comparison, coupon stacking, delivery-speed trade-offs, stock volatility tracking, and optimal purchase routing for cross-platform commerce inventory arbitrage. | |
| genpark-cross-surface-frictionless-checkout-auditor-skill alphaparkinc/genpark-cross-surface-frictionless-checkout-auditor-skill Enables users to audit and optimize zero-hop conversion journeys across lock screens, smart TVs, and ambient screens, including cross-surface attribution and instant checkout analysis. | |
| genpark-ctrip-destination-crowd-density-router-skill alphaparkinc/genpark-ctrip-destination-crowd-density-router-skill Enables agents to optimize real-time attraction visitor dispersion and queueing wait times using queuing-theory models and dynamic heatmap routing. | |
| genpark-ctrip-flight-fare-volatility-forecaster-skill alphaparkinc/genpark-ctrip-flight-fare-volatility-forecaster-skill Enables agents to forecast dynamic airline ticket fare volatility and produce optimal buy-now versus wait-and-freeze recommendations through a zero-dependency MCP STDIO interface. | |
| GenPark Ctrip Hotel Corporate Policy Compliance Auditor alphaparkinc/genpark-ctrip-hotel-corporate-policy-compliance-auditor-skill Enables agents to validate enterprise travel policies, audit hotel rate parity, and check carbon ESG compliance through a zero-dependency MCP server. It exposes policy and expense-auditing tools over STDIO JSON-RPC for use in Claude Desktop | |
| genpark-ctrip-itinerary-dag-optimizer-skill alphaparkinc/genpark-ctrip-itinerary-dag-optimizer-skill Enables agents to plan multi-day travel schedules by solving itinerary graphs with TSP heuristics, fatigue decay, and opening-hour constraints, exposed over MCP STDIO JSON-RPC for agent runtime integration. | |
| genpark-cue-desktop-ambient-context-trigger-skill alphaparkinc/genpark-cue-desktop-ambient-context-trigger-skill Enables MCP-compliant clients to listen to ambient desktop context, detect screen text and clipboard changes, and proactively predict user intent through a zero-dependency Python server. | |
| genpark-customer-interview-pain-point-clusterer-skill alphaparkinc/genpark-customer-interview-pain-point-clusterer-skill Analyzes customer interview transcripts to surface recurring pain points and synthesize actionable roadmap themes through MCP, with deterministic, dependency-free execution. | |
| genpark-cyclomatic-complexity-refactoring-scout-skill alphaparkinc/genpark-cyclomatic-complexity-refactoring-scout-skill Enables agents to statically analyze Python source via AST traversal, computing McCabe cyclomatic complexity, cognitive nesting depth, and dependency graphs to pinpoint refactoring hotspots. It returns standardized refactoring plans, decomp | |
| genpark-data-matrix-svd-pca-dimensionality-reducer-skill alphaparkinc/genpark-data-matrix-svd-pca-dimensionality-reducer-skill Enables agents to run statistics and data-science computations over numerical streams using only the Python standard library, including Z-score/IQR anomaly detection, Holt linear forecasting, Welch's t-test hypothesis evaluation, gradient-d | |
| genpark-dead-code-unreachable-ast-pruner-skill alphaparkinc/genpark-dead-code-unreachable-ast-pruner-skill Enables whole-program callgraph reachability analysis to locate dead functions and stale flags, and integrates with MCP-compliant clients for automated code review, breaking-change audits, and CI/CD workflow pruning. | |
| genpark-deep-research-consensus-engine-skill alphaparkinc/genpark-deep-research-consensus-engine-skill Enables AI agents and MCP clients to run deterministic deep research consensus arbitration by parsing queries, evaluating source authority and contradictions, and returning structured JSON dossiers and telemetry. | |
| genpark-deep-research-cross-citation-graph-skill alphaparkinc/genpark-deep-research-cross-citation-graph-skill Enables autonomous research workflows to construct and analyze multi-source cross-citation graphs and resolve consensus from structured outputs via MCP. | |
| genpark-deep-research-evidence-synthesis-graph-skill alphaparkinc/genpark-deep-research-evidence-synthesis-graph-skill Enables deep research evidence synthesis and citation verification by generating structured research graphs through the Model Context Protocol. | |
| genpark-delegated-agentic-checkout-guardrail-skill alphaparkinc/genpark-delegated-agentic-checkout-guardrail-skill Provides a deterministic, zero-dependency MCP server that enforces autonomous merchant checkout token and velocity limits for Agentcard/Stripe transactions, outputting structured guardrail telemetry for agent workflows. | |
| genpark-distributed-agent-chaos-latency-fuzzer-skill alphaparkinc/genpark-distributed-agent-chaos-latency-fuzzer-skill Enables distributed multi-agent chaos latency injection and fault fuzzing, allowing MCP-compatible clients to inject network faults and retrieve structured execution telemetry. | |
| Distributed Agent Fleet Heartbeat & Liveness Watchdog alphaparkinc/genpark-distributed-agent-heartbeat-liveness-watchdog-skill Enables monitoring of distributed autonomous agent nodes through MCP tools, dynamically computing jitter-aware failover deadlines and isolating zombie or stalled workers. It also coordinates state checkpoint hydration and failover rerouting | |
| genpark-distributed-two-phase-commit-coordinator-skill alphaparkinc/genpark-distributed-two-phase-commit-coordinator-skill Enables AI agents to coordinate atomic distributed transactions across a swarm through a prepare/vote phase, unanimous commit-or-abort consensus, quorum validation, and failure recovery. It also layers in vector-clock causal stamping, LWW C | |
| genpark-document-redaction-pii-scrubber-skill alphaparkinc/genpark-document-redaction-pii-scrubber-skill Enables redaction and sanitization of document PII and credentials through MCP, including Luhn credit-card verification, reversible salt hashing, and audit logging. | |
| genpark-dynamic-bundle-pricing-maximizer-skill alphaparkinc/genpark-dynamic-bundle-pricing-maximizer-skill Enables autonomous agents and MCP-compliant clients to optimize cross-category e-commerce product bundle pricing for maximum average order value (AOV) using deterministic, zero-dependency Python execution. | |
| GenPark Dynamic Context Pruning Needle Retriever alphaparkinc/genpark-dynamic-context-pruning-needle-retriever-skill GenPark MCP server for selecting relevant context under token and latency constraints. | |
| genpark-dynamic-jsonld-rich-snippet-generator-skill alphaparkinc/genpark-dynamic-jsonld-rich-snippet-generator-skill Enables AI agents and developers to generate deterministic Schema.org Product and FAQPage JSON-LD rich snippets from query payloads. Integrates via MCP with Claude Desktop, Cursor, and other compliant clients. | |
| genpark-dynamic-sparkpage-layout-synthesizer-skill alphaparkinc/genpark-dynamic-page-layout-synthesizer-skill Enables AI agents to synthesize heterogeneous search results into interactive comparison layouts (Genspark Sparkpages) through the Model Context Protocol, with deterministic, zero-dependency execution. | |
| genpark-dynamic-prompt-prefix-cache-skill alphaparkinc/genpark-dynamic-prompt-prefix-cache-skill Enables clients to optimize prompt prefix caching by matching longest common token prefixes with a radix trie, eliminating redundant prefill computation and reducing time-to-first-token. | |
| genpark-edge-geo-distributed-request-routing-governor-skill alphaparkinc/genpark-edge-geo-distributed-request-routing-governor-skill Enables low-latency geo-distributed request routing for AI agents, providing deterministic, zero-dependency edge request governance with sub-millisecond execution overhead. | |
| genpark-edge-inference-latency-telemetry-skill alphaparkinc/genpark-edge-inference-latency-telemetry-skill Provides an MCP-compatible profiler for measuring edge and on-device LLM inference latency, including TTFT, TPOT, tokens-per-second throughput, and P50/P90/P99 jitter distributions. It enables agents and developers to run these telemetry be | |
| genpark-eip712-typed-signature-phishing-sanitizer-skill alphaparkinc/genpark-eip712-typed-signature-phishing-sanitizer-skill Enables autonomous auditing and sanitization of EIP-712 typed signature phishing attempts and permit/allowance risks, including Permit2 and MetaMask scenarios, through deterministic callgraph and invariant analysis with vulnerability triage | |
| GenParkEmbodiedGripper6DoFGraspStabilityEvaluator alphaparkinc/genpark-embodied-gripper-6dof-grasp-stability-evaluator-skill Enables real-time spatial intelligence, trajectory generation, and tactile control for autonomous robotic systems via MCP, including Coulomb friction cone checking, contact normal alignment, and grasp wrench quality evaluation. | |
| GenParkEmbodiedSpatial3DOccupancyGridSolver alphaparkinc/genpark-embodied-spatial-3d-occupancy-grid-solver-skill Enables autonomous robotic systems to perform real-time 3D occupancy voxel mapping, raycast-based Bayesian occupancy updates, and sphere collision checking through standard MCP tools. | |
| genpark-embodied-tactile-slip-force-feedback-controller-skill alphaparkinc/genpark-embodied-tactile-slip-force-feedback-controller-skill Enables real-time robotic manipulation safety through shear-to-normal ratio tracking, micro-vibration onset detection, and dynamic grasp force adaptation over MCP. | |
| GenParkEmbodiedTrajectoryQuinticSplineSmoother MCP Server alphaparkinc/genpark-embodied-trajectory-quintic-spline-smoother-skill Enables autonomous robotic systems to generate and smooth trajectories with continuous position, velocity, and acceleration boundary constraints, analytic jerk minimization, spatial intelligence, and tactile control through MCP tools. | |
| Enterprise Compliance Data Retention GDPR Erasure Sentinel alphaparkinc/genpark-enterprise-compliance-data-retention-gdpr-erasure-sentinel-skill Enables agents to process GDPR right-to-be-forgotten and CCPA erasure requests by auditing distributed data stores such as relational databases, vector embeddings, and activity logs, checking legal hold exemptions, executing cascading pseud | |
| genpark-enterprise-compliance-pii-redaction-sentinel-skill alphaparkinc/genpark-enterprise-compliance-pii-redaction-sentinel-skill Enables agents and applications to scan text streams for personally identifiable information, financial account numbers, JWT tokens, and cryptographic keys, returning sanitized output with deterministic zero-leakage masking. It runs as a ze | |
| genpark-enterprise-context-permission-boundary-auditor-skill alphaparkinc/genpark-enterprise-context-permission-boundary-auditor-skill Enables inspection and governance of enterprise ingested context by classifying security clearance tiers, sanitizing cross-department prompts, and enforcing role-based access boundaries to prevent data leaks. It runs as a zero-dependency MC | |
| genpark-enterprise-executive-briefing-doc-synthesizer-skill alphaparkinc/genpark-enterprise-executive-briefing-doc-synthesizer-skill Enables users to transform raw multi-source enterprise findings into complete, structured strategic documents, auto-generating executive summaries, risk registers, decision matrices, and appendix citations. It runs as a zero-dependency Pyth | |
| genpark-enterprise-identity-token-exchange-bridge-skill alphaparkinc/genpark-enterprise-identity-token-exchange-bridge-skill Enables secure cross-system identity and token exchange for autonomous agents, including on-behalf-of token exchange, scoped permission delegation, token lifetime refresh, and zero-leakage ephemeral credentials. It integrates with MCP-compa | |
| genpark-enterprise-knowledge-graph-provenance-tracer-skill alphaparkinc/genpark-enterprise-knowledge-graph-provenance-tracer-skill Enables cryptographic chunk hashing, reverse claim-to-source attribution, clearance boundary validation, and provenance audit trails for enterprise knowledge graphs to combat hallucinations. | |
| genpark-enterprise-llm-pii-masking-redline-gateway-skill alphaparkinc/genpark-enterprise-llm-pii-masking-redline-gateway-skill Enables MCP-compliant clients to sanitize prompt payloads by deterministically masking and reversibly redacting PII before they reach LLMs, returning structured output and telemetry. | |
| EnterpriseMeetingActionItemExtractor alphaparkinc/genpark-enterprise-meeting-action-item-extractor-skill Enables users to analyze multi-speaker meeting transcripts from Tencent Meeting, Zoom, and Teams, extract explicit commitments, deadlines, and assignees, prioritize them using an Eisenhower urgency-importance matrix, and generate WeChat Wor | |
| genpark-enterprise-merkle-audit-proof-anchor-skill alphaparkinc/genpark-enterprise-merkle-audit-proof-anchor-skill Enables agents to hash execution logs into tamper-proof Merkle trees, compute cryptographic inclusion proofs, and verify audit integrity through MCP tools. | |
| EnterpriseRBACLeastPrivilegePolicySynthesizer alphaparkinc/genpark-enterprise-rbac-least-privilege-policy-synthesizer-skill Enables analysis of historical agent tool-call audit logs to detect over-permissioned wildcards, synthesize strict least-privilege JSON security boundary policies, and quantify attack surface and blast-radius reduction. | |
| genpark-enterprise-slack-wecom-knowledge-base-auto-curator-skill alphaparkinc/genpark-enterprise-slack-wecom-knowledge-base-auto-curator-skill Enables parsing multi-turn Slack and WeChat Work troubleshooting threads to extract validated Q&A resolution pairs, deduplicate organizational knowledge, and synthesize structured Markdown SOP runbooks via MCP. | |
| genpark-enterprise-slide-deck-narrative-compiler-skill alphaparkinc/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. Integrates through MCP to support determinist |
27,401–27,450 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.