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 |
|---|---|
| Slide Layout Auto-Rebalancer MCP Server alpha-park/genpark-agent-slide-layout-auto-rebalancer-skill Enables autonomous agents to optimize presentation canvas ASTs by repositioning overlapping elements, preventing clipping, and harmonizing padding and vertical rhythm. | |
| Slide Theme & Palette Harmonizer alpha-park/genpark-agent-slide-theme-palette-harmonizer-skill This MCP server generates accessible, harmonized presentation design tokens — primary, background, surface, text, and border colors — from a single brand color while computing exact WCAG AA/AAA contrast ratios and typography pairings. It le | |
| genpark-agent-speculative-decoding-orchestrator-skill alpha-park/genpark-agent-speculative-decoding-orchestrator-skill Enables MCP-compatible clients to run speculative decoding draft-model verification, calculating acceptance probabilities and returning structured execution telemetry with zero external dependencies. | |
| genpark-agent-synthetic-data-differential-privacy-guard-skill alpha-park/genpark-agent-synthetic-data-differential-privacy-guard-skill Enables agents to apply differential privacy epsilon-noise generation and quasi-identifier redaction to tabular data releases, helping prevent re-identification during data sharing and synthetic data workflows. | |
| genpark-agent-synthetic-trajectory-evaluator-skill alpha-park/genpark-agent-synthetic-trajectory-evaluator-skill Enables autonomous web agents to prune DOM trees, canonicalize URLs, auto-map form inputs, and convert HTML/Markdown tables into typed JSON, then score execution trajectories with action-level precision, recall, and Levenshtein edit distanc | |
| genpark-agent-tool-call-self-healing-retry-guard-skill alpha-park/genpark-agent-tool-call-self-healing-retry-guard-skill Enables deterministic repair of malformed tool-call schemas and guards parameter projections for AI agents, ensuring reliable JSON-RPC interactions via MCP. | |
| genpark-agent-tool-dag-speculative-prefetcher-skill alpha-park/genpark-agent-tool-dag-speculative-prefetcher-skill Enables agents and MCP-compliant clients to resolve tool execution graphs as topological dependency DAGs, batching independent calls in parallel and speculatively prefetching arguments to cut latency and token burn. Runs deterministically a | |
| genpark-agent-tool-retry-exponential-backoff-jitter-skill alpha-park/genpark-agent-tool-retry-exponential-backoff-jitter-skill Enables fault-tolerant agent tool execution with adaptive exponential backoff, full jitter, rate-limit 429 backpressure handling, and circuit breaker patterns to make AI agent calls resilient to transient failures. Plugs directly into MCP-c | |
| genpark-agent-web-stealth-scraper-distiller-skill alpha-park/genpark-agent-web-stealth-scraper-distiller-skill Enables AI agents and MCP clients to fetch web pages and distill them into clean, token-efficient markdown by stripping cookie banners, navigation bars, and ads. Runs with zero external dependencies over JSON-RPC stdio, delivering determini | |
| genpark-agentic-cache-semantic-deduplicator-skill alpha-park/genpark-agentic-cache-semantic-deduplicator-skill Enables agents to deduplicate semantic prompt cache entries by calculating Jaccard token overlap, reducing redundant LLM calls and cost. | |
| AgenticCartAbandonmentRecoveryOrchestrator alpha-park/genpark-agentic-cart-abandonment-recovery-orchestrator-skill Enables monitoring abandoned checkout sessions, diagnosing friction causes, crafting margin-preserving incentive vouchers, and generating multi-channel win-back messages through MCP. | |
| Agentic Cold Email Outreach Spam Score & Deliverability Guard alpha-park/genpark-agentic-cold-email-outreach-spam-score-guard-skill Enables users to evaluate cold email copy for spam heuristics, formatting ratios, unsubscribe compliance, and readability, returning a composite spam score, deliverability tier, flags, and recommendations to improve primary inbox placement. | |
| genpark-agentic-commerce-a2m-bargaining-negotiator-skill alpha-park/genpark-agentic-commerce-a2m-bargaining-negotiator-skill Enables AI agents to run automated Rubinstein alternating-offers bargaining and multi-item bundle negotiations with merchant gateways, resolving catalog availability and settling through tokenized, spend-bounded payment rails under the Univ | |
| genpark-agentic-commerce-agent-gateway-verifier-skill alpha-park/genpark-agentic-commerce-agent-gateway-verifier-skill Publishes a zero-dependency, standard-library-only STDIO MCP server that exposes agentic commerce capabilities such as multi-merchant catalog resolution, spend-bounded cryptographic payment delegation, and automated alternating-offers barga | |
| genpark-agentic-commerce-ap2-payment-delegation-vault-skill alpha-park/genpark-agentic-commerce-ap2-payment-delegation-vault-skill Enables AI agents to manage Agentic Payment Protocol ephemeral tokens with cryptographic spend mandates, risk scoring, merchant catalog resolution, and automated bargaining through MCP tools. | |
| Agentic Commerce Review Authenticity Sentinel alpha-park/genpark-agentic-commerce-counterfeit-product-review-synthesizer-skill Enables auditing product review streams for review-velocity clustering, sentiment dissonance, repetitive incentivized phrases, and review hijacking, then surfaces authenticity grades and adjusted ratings that estimate true customer sentimen | |
| Agentic Escrow Milestone Payout Arbiter alpha-park/genpark-agentic-commerce-dynamic-escrow-milestone-releaser-skill Enables autonomous evaluation of contractual milestone criteria — such as merged pull requests, unit-test pass rates, and Lighthouse performance thresholds — against submitted telemetry to decide whether funds should be released. It verifie | |
| genpark-agentic-commerce-intent-cart-checkout-skill alpha-park/genpark-agentic-commerce-intent-cart-checkout-skill Enables agents to translate consumer shopping intent into aggregated item discovery, cross-merchant cart consolidation, and structured transaction checkout payloads across multiple merchants. It runs as a zero-dependency Python MCP server o | |
| Agentic Commerce Retroactive Price Drop Refund Claimer alpha-park/genpark-agentic-commerce-price-drop-retroactive-refund-claimer-skill Enables users to scan past order receipts against retailer price-protection policy windows, verify eligibility for retroactive refunds, and synthesize auto-claim filing packets for merchants such as Target, Best Buy, Amazon, and Nordstrom. | |
| genpark-agentic-commerce-recurring-utility-bill-negotiator-skill alpha-park/genpark-agentic-commerce-recurring-utility-bill-negotiator-skill Enables auditing monthly broadband and mobile bills, detecting out-of-contract price creep and hidden junk fees, and synthesizing high-leverage churn-threat retention negotiation scripts through an MCP-compliant JSON-RPC interface. | |
| Agentic Commerce RFQ Multi-Vendor Bidding Arbiter alpha-park/genpark-agentic-commerce-rfq-multi-vendor-bidding-arbiter-skill Enables autonomous evaluation and ranking of wholesale vendor bids for B2B RFQs by weighing unit volume pricing, minimum order quantities, landed tariffs, net payment terms, and historical lead-time reliability to select the best supplier. | |
| genpark-agentic-commerce-sponsored-placement-router-skill alpha-park/genpark-agentic-commerce-sponsored-placement-router-skill Enables AI agents to optimize in-context sponsored product placements and algorithmic slotting yield through MCP-compatible routing capabilities. | |
| genpark-agentic-commerce-ucp-catalog-resolver-skill alpha-park/genpark-agentic-commerce-ucp-catalog-resolver-skill Enables AI agents to resolve multi-merchant Universal Commerce Protocol catalogs with Pareto-optimal pricing and SLA routing, while supporting tokenized payment delegation and automated bargaining through MCP tools. | |
| Agentic Contextual Compression Prompt Packer Skill alpha-park/genpark-agentic-contextual-compression-prompt-packer-skill Enables MCP-compatible clients to shrink oversized long-context prompts through task-relevant slicing, lexical deduplication, and entropy-preserving pruning while honoring token budgets and safeguarding system invariants. | |
| genpark-agentic-cross-carrier-freight-carbon-offset-router-skill alpha-park/genpark-agentic-cross-carrier-freight-carbon-offset-router-skill Enables users to compare air, rail, maritime, and electric ground freight options using GLEC emissions factors, optimize multi-carrier routes, and compute carbon footprints with offset costs. It also generates verified carbon offset credit | |
| genpark-agentic-delegated-escrow-settlement-ledger-skill alpha-park/genpark-agentic-delegated-escrow-settlement-ledger-skill Enables multi-party conditional escrow locking, autonomous proof-of-delivery release triggers, referral fee splits, and dispute freeze protection for agentic commerce and enterprise settlement workflows. | |
| genpark-agentic-hallucination-grounding-checker-skill alpha-park/genpark-agentic-hallucination-grounding-checker-skill Enables sentence-level factual grounding verification and hallucination detection for RAG outputs via a native MCP server, providing deterministic scoring and structured telemetry. | |
| genpark-agentic-inventory-restock-predictive-balancer-skill alpha-park/genpark-agentic-inventory-restock-predictive-balancer-skill Enables forecasting SKU demand with exponential moving averages, computing safety-stock buffers and reorder points, and generating supplier purchase orders through an MCP JSON-RPC 2.0 interface. | |
| Agentic Kubernetes Node Spot Termination Drain Scheduler alpha-park/genpark-agentic-kubernetes-node-spot-termination-drain-scheduler-skill Enables cloud SRE and FinOps teams to respond to spot instance preemption by cordoning nodes and orchestrating prioritized pod evictions so critical workloads can be redistributed without downtime. | |
| genpark-agentic-lead-score-velocity-evaluator-skill alpha-park/genpark-agentic-lead-score-velocity-evaluator-skill Enables scoring of customer leads and evaluation of interaction velocity to predict conversion outcomes. It exposes deterministic, dependency-free analysis through the Model Context Protocol for integration with MCP-compliant clients such a | |
| Agentic Multimodal Invoice & Receipt Reconciler alpha-park/genpark-agentic-multimodal-invoice-receipt-reconciler-skill Enables parsing of structured financial receipts, invoices, and bank statements, tolerance-based three-way reconciliation, detection of tax calculation drift and duplicate claims, and synthesis of double-entry bookkeeping journal entries. | |
| Agentic Contract Redline Diff Sentinel alpha-park/genpark-agentic-multimodal-pdf-contract-redline-diff-skill Enables comparing baseline and counter-party contract drafts to flag high-risk clause shifts and synthesize legal redline summaries. | |
| genpark-agentic-multimodal-product-return-fraud-detector-skill alpha-park/genpark-agentic-multimodal-product-return-fraud-detector-skill Enables MCP clients to evaluate e-commerce return requests by correlating return velocity, carrier scan discrepancies, product tag tampering indicators, and customer lifetime return ratios. It computes a composite fraud risk score and recom | |
| genpark-agentic-negotiation-counter-offer-strategist-skill alpha-park/genpark-agentic-negotiation-counter-offer-strategist-skill Enables autonomous multi-turn negotiation and counter-offer strategy by calculating ZOPA, concession decay curves, reservation price thresholds, and structured bargaining offers. | |
| genpark-agentic-payment-tokenized-authorization-sentinel-skill alpha-park/genpark-agentic-payment-tokenized-authorization-sentinel-skill Enables agents to issue and validate cryptographic delegated payment mandates for tokenized checkout, enforcing spend limits, velocity thresholds, and merchant whitelists. Generates ephemeral single-use authorization tokens so commerce and | |
| genpark-agentic-post-purchase-dispute-arbiter-skill alpha-park/genpark-agentic-post-purchase-dispute-arbiter-skill Enables users to ingest carrier webhook events, detect transit anomalies such as stalled or failed deliveries, calculate compensation eligibility, and generate structured merchant claim payloads. | |
| genpark-agentic-price-drop-refund-arbiter-skill alpha-park/genpark-agentic-price-drop-refund-arbiter-skill Enables users to register post-purchase receipts, monitor retailer price drops within price-match guarantee windows, verify eligibility, and synthesize automated refund claims. | |
| genpark-agentic-prompt-compression-token-sieve-skill alpha-park/genpark-agentic-prompt-compression-token-sieve-skill Enables agents to deterministically shrink multi-turn conversation history and prompts by stripping verbose boilerplate and filler tokens while preserving critical tool parameters and named entities. This lets users cut inference costs by r | |
| Agentic RAG HyDE Query Expander alpha-park/genpark-agentic-rag-hyde-hypothetical-document-generator-skill Enables MCP clients to generate diverse hypothetical answer passages from sparse user queries, improving vector search recall by bridging lexical and semantic gaps. | |
| genpark-agentic-recurrent-subscription-autopilot-skill alpha-park/genpark-agentic-recurrent-subscription-autopilot-skill Enables agents to monitor transaction streams, detect recurring charges and price creeping, flag zombie subscriptions, and generate automated cancellation workflows. | |
| AgenticShipmentDeliveryRescheduler alpha-park/genpark-agentic-shipment-delivery-rescheduler-skill Enables ingesting FedEx, UPS, DHL, and SF Express carrier tracking webhooks to detect failed delivery attempts and customs delays, then compute and dispatch recovery options. Supports autonomous negotiation of delivery windows, parcel locke | |
| Agentic Smart Contract Vulnerability Static Sentinel alpha-park/genpark-agentic-smart-contract-vulnerability-static-sentinel-skill Enables static auditing of EVM Solidity smart contracts to detect critical vulnerabilities such as reentrancy state changes, unhandled external calls, unchecked delegatecall, and tx.origin authentication flaws, producing risk audit reports. | |
| Agentic Supply Chain Bullwhip Dampener alpha-park/genpark-agentic-supply-chain-bullwhip-dampener-skill Enables users to smooth order surges, filter lead-time demand volatility, and calculate replenishment quantities using safety stock PID control. It reduces inventory whipsawing across multi-tier supplier networks through MCP tools. | |
| genpark-agentic-travel-multi-leg-itinerary-synthesizer-skill alpha-park/genpark-agentic-travel-multi-leg-itinerary-synthesizer-skill Enables turning natural-language vacation or business travel goals into multi-leg flight segments, lodging choices, layover buffers, baggage fee optimization, and consolidated reservation manifests via MCP. | |
| genpark-agentic-webhook-signature-verifier-skill alpha-park/genpark-agentic-webhook-signature-verifier-skill An MCP server that authenticates incoming webhooks from multiple providers such as Shopify, Stripe, GitHub, Slack, and PayPal using HMAC-SHA256 constant-time verification and timestamp replay-window validation. It lets agents validate and m | |
| genpark-agentic-workflow-state-checkpoint-skill alpha-park/genpark-agentic-workflow-state-checkpoint-skill Enables AI agents to capture and commit stateful workflow checkpoints during autonomous execution, computing deterministic state hashes and rollback points. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Curs | |
| genpark-agentic-zero-knowledge-pii-token-vault-masker-skill alpha-park/genpark-agentic-zero-knowledge-pii-token-vault-masker-skill Enables reversible anonymization of SSNs, credit cards, passport numbers, emails, and phone numbers in prompts before sending them to external LLMs, and restores original tokens from completions using local HMAC isolation. | |
| genpark-ast-import-dependency-rewriter-skill alpha-park/genpark-ast-import-dependency-rewriter-skill Enables developers and coding agents to refactor Python codebases by re-aliasing imports and migrating dependencies, safely rewriting module paths and callsites through deterministic AST analysis instead of error-prone regex. It also surfac | |
| genpark-ast-taint-source-sink-flow-tracer-skill alpha-park/genpark-ast-taint-source-sink-flow-tracer-skill Enables static AST-based taint flow tracing from untrusted sources to sensitive sinks, supporting AI code review and security analysis via MCP. | |
| genpark-async-unhandled-promise-rejection-triager-skill alpha-park/genpark-async-unhandled-promise-rejection-triager-skill Enables AI-powered code review and analysis of asynchronous JavaScript/TypeScript control flow, identifying unawaited promises and race conditions through AST taint-flow tracing and ESLint-style audits within MCP-compliant clients. |
26,901–26,950 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.