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-automated-compliance-policy-evaluator-skill alpha-park/genpark-automated-compliance-policy-evaluator-skill Enables scanning e-commerce advertising content to detect prohibited claims and trademark violations, returning deterministic compliance evaluations for autonomous agents. | |
| genpark-automated-treasury-cash-sweep-optimizer-skill alpha-park/genpark-automated-treasury-cash-sweep-optimizer-skill Enables autonomous financial agents to pool corporate treasury cash, rebalance liquidity, and optimize yield sweeps while enforcing double-entry ledger integrity, HMAC-SHA256 signature verification, and fraud-detection safety buffers that p | |
| Autonomous AI Fleet Governance Circuit Breaker alpha-park/genpark-autonomous-ai-fleet-governance-circuit-breaker-skill Enables monitoring and governing distributed multi-agent fleets through MCP by evaluating token burn velocity, recursive spawning depth, and cyclic deadlocks, then triggering circuit-breaker and kill-switch containment policies with auditab | |
| genpark-autonomous-browser-action-planner-skill alpha-park/genpark-autonomous-browser-action-planner-skill Enables autonomous browser action planning by mapping goals into resilient selector action sequences, with deterministic execution and structured telemetry through MCP. | |
| genpark-autonomous-form-autofill-resolver-skill alpha-park/genpark-autonomous-form-autofill-resolver-skill Enables AI agents and MCP-compatible clients to analyze web checkout form fields and heuristically resolve and autofill buyer parameters through a deterministic, zero-dependency engine. Plugs into Claude Desktop, Cursor, or Windsurf over JS | |
| genpark-autonomous-price-elasticity-optimizer-skill alpha-park/genpark-autonomous-price-elasticity-optimizer-skill Enables autonomous agents to calculate dynamic price elasticity of demand and derive marginal revenue maxima from query inputs. It returns structured JSON outputs with execution telemetry for economic modeling and pricing optimization. | |
| genpark-autonomous-refund-dispute-arbitrator-skill alpha-park/genpark-autonomous-refund-dispute-arbitrator-skill Enables autonomous refund and dispute arbitration by validating carrier proofs and policies, producing structured output dossiers with execution telemetry. | |
| genpark-autonomous-task-dag-decomposer-skill alpha-park/genpark-autonomous-task-dag-decomposer-skill Enables users to decompose prompts into dependency-aware task DAGs for autonomous multi-stage planning and orchestration. | |
| GenPark Bio-Agent alpha-park/genpark-bio-agent A zero-dependency MCP suite exposing computational tools across metabolic, cardio-renal, chronobiology, neuro-recovery, and biomechanics domains. It enables clients to derive longevity and physiology metrics such as autophagy index, glucose | |
| genpark-black-scholes-merton-greeks-engine-skill alpha-park/genpark-black-scholes-merton-greeks-engine-skill Enables analytical pricing of European options and calculation of first- and second-order Greeks including Delta, Gamma, Vega, Theta, and Rho through MCP. It also supports related quantitative finance analytics such as Monte Carlo simulatio | |
| genpark-bond-convexity-modified-duration-calculator-skill alpha-park/genpark-bond-convexity-modified-duration-calculator-skill Enables fixed-income and quantitative risk analysis through MCP, computing bond cash flow present values, Macaulay and modified duration, and price convexity, alongside option Greeks, Monte Carlo simulations, VaR/CVaR, and Nelson-Siegel yie | |
| genpark-browser-computer-use-element-anchor-skill alpha-park/genpark-browser-computer-use-element-anchor-skill Enables AI agents to anchor visible on-screen elements to stable DOM targets, preventing click drift during browser computer-use automation. | |
| genpark-calendar-timeblock-conflict-arbitrator-skill alpha-park/genpark-calendar-timeblock-conflict-arbitrator-skill Enables autonomous resolution of multi-timezone calendar event overlaps and negotiation of deep-work buffers through deterministic, zero-dependency MCP-compatible tooling. | |
| genpark-canary-honeytoken-private-key-tripwire-skill alpha-park/genpark-canary-honeytoken-private-key-tripwire-skill Enables monitoring honeytoken decoy private keys for mempool activity, detecting and alerting on potential intrusions. | |
| genpark-canonical-doi-bibtex-crossref-resolver-skill alpha-park/genpark-canonical-doi-bibtex-crossref-resolver-skill Serves as an MCP server that resolves academic DOIs to canonical identifiers and generates BibTeX records via CrossRef. | |
| genpark-codebase-dead-code-unreachable-pruner-skill alpha-park/genpark-codebase-dead-code-unreachable-pruner-skill Enables coding agents to run deterministic, zero-dependency AST static analysis over source code, building call graphs and dependency metrics to find orphaned functions, unreachable methods, breaking API surface diffs, and token-bloat clust | |
| genpark-cognitive-load-budget-optimizer-skill alpha-park/genpark-cognitive-load-budget-optimizer-skill Enables monitoring of running agent loops with token and monetary cost estimation, pruning of verbose thinking chains near limits, and routing sub-tasks between fast/cheap and deep reasoning models. It provides deterministic, MCP-compatible | |
| genpark-commerce-dynamic-bundling-recommender-skill alpha-park/genpark-commerce-dynamic-bundling-recommender-skill Enables analysis of cart items and shopper intent, computation of complementary product affinity scores, enforcement of merchant margin constraints, and synthesis of personalized discount bundles and cross-sell recommendations via MCP. | |
| genpark-constant-time-crypto-validator-skill alpha-park/genpark-constant-time-crypto-validator-skill Enables constant-time cryptographic attestation, zero-knowledge verification, JWT HMAC-SHA256 validation, Merkle proof inclusion, nonce replay protection, and secure digest comparison for agent security credentials via MCP. | |
| genpark-context-window-lost-in-middle-reorderer-skill alpha-park/genpark-context-window-lost-in-middle-reorderer-skill Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation. | |
| genpark-contextual-compression-filter-skill alpha-park/genpark-contextual-compression-filter-skill Enables AI agents to compress retrieved web documents against a query, pruning irrelevant noise so only the most relevant context reaches the model. It runs as a zero-dependency Python MCP server that accepts a query payload and returns str | |
| genpark-contextual-memory-pruning-importance-attributor-skill alpha-park/genpark-contextual-memory-pruning-importance-attributor-skill Enables agents to evaluate multi-turn episodic memory buffers, compute multi-factor salience scores, and deterministically prune low-utility noise so retained context fits within model limits. | |
| genpark-conversational-barge-in-interruption-arbitrator-skill alpha-park/genpark-conversational-barge-in-interruption-arbitrator-skill Enables real-time full-duplex voice agents to classify user interruptions, backchannels, and acoustic echo, and to arbitrate turn-taking with context rollback via MCP. | |
| genpark-cosine-bm25-reciprocal-rank-fusion-skill alpha-park/genpark-cosine-bm25-reciprocal-rank-fusion-skill Enables agents to retrieve relevant context via a zero-dependency hybrid search engine that blends sparse keyword-based lexical ranking with dense vector similarity scores into one fused result set, then refines it with knowledge graph trip | |
| genpark-crdt-lww-element-set-sync-skill alpha-park/genpark-crdt-lww-element-set-sync-skill Enables agents to synchronize, merge, and reconcile distributed state across nodes using conflict-free last-write-wins element sets with Lamport/vector-clock causality, token-bucket gossip dissemination, and quorum-based commit coordination | |
| genpark-cross-chain-bridge-invariant-anomaly-detector-skill alpha-park/genpark-cross-chain-bridge-invariant-anomaly-detector-skill Enables automated auditing of cross-chain bridge token reserves and monitoring for anomalous outflows on LayerZero and Wormhole, integrating with MCP-compliant clients for deterministic Web3 security analysis. | |
| genpark-cross-platform-commerce-inventory-arbitrage-skill alpha-park/genpark-cross-platform-commerce-inventory-arbitrage-skill Enables agents to perform real-time multi-merchant price comparison, coupon stacking, delivery-speed trade-off analysis, stock volatility tracking, and optimal purchase routing across commerce platforms. It exposes these capabilities as an | |
| genpark-cross-surface-frictionless-checkout-auditor-skill alpha-park/genpark-cross-surface-frictionless-checkout-auditor-skill Enables agents to audit and optimize zero-hop conversion journeys across lock screens, smart TVs, and instant checkout surfaces through native MCP STDIO integration. | |
| genpark-ctrip-crossborder-visa-entry-rules-engine-skill alpha-park/genpark-ctrip-crossborder-visa-entry-rules-engine-skill Enables evaluation of passport nationality, transit visa waiver (TWOV) eligibility, and rolling stay-duration rules for multi-hop international journeys through MCP tools. | |
| genpark-ctrip-destination-crowd-density-router-skill alpha-park/genpark-ctrip-destination-crowd-density-router-skill Enables travelers and agents to route destination crowds in real time by dispersing visitors and reducing queue waits with queuing-theory and dynamic heatmap guidance. | |
| genpark-ctrip-flight-fare-volatility-forecaster-skill alpha-park/genpark-ctrip-flight-fare-volatility-forecaster-skill Enables agents to forecast airline dynamic ticket fare fluctuations and generate optimal Buy-Now versus Wait-and-Freeze recommendations via MCP. | |
| genpark-ctrip-hotel-corporate-policy-compliance-auditor-skill alpha-park/genpark-ctrip-hotel-corporate-policy-compliance-auditor-skill Enables automated validation of corporate travel policies, hotel rate-parity audits, and carbon ESG compliance checks through MCP tools. | |
| genpark-ctrip-itinerary-dag-optimizer-skill alpha-park/genpark-ctrip-itinerary-dag-optimizer-skill Enables agents to generate optimized multi-day travel schedules and decision payloads via MCP, applying TSP graph heuristics with fatigue decay and opening-hour constraints. | |
| genpark-cue-desktop-ambient-context-trigger-skill alpha-park/genpark-cue-desktop-ambient-context-trigger-skill Enables AI agents to monitor ambient desktop context, react to screen text and clipboard changes, and predict proactive intents for non-intrusive action through MCP. | |
| genpark-cyclomatic-complexity-refactoring-scout-skill alpha-park/genpark-cyclomatic-complexity-refactoring-scout-skill Enables coding agents and developers to parse Python source into ASTs and compute complexity metrics that pinpoint refactoring hotspots, dead code, and breaking API diffs. It returns decomposition plans and dependency-graph telemetry over M | |
| genpark-data-matrix-svd-pca-dimensionality-reducer-skill alpha-park/genpark-data-matrix-svd-pca-dimensionality-reducer-skill Enables agents to run zero-dependency statistical analysis natively over MCP, including Power Iteration PCA/SVD dimensionality reduction, Holt linear forecasting, modified Z-score and Tukey IQR anomaly detection, Welch's t-test, and multiva | |
| genpark-dead-code-unreachable-ast-pruner-skill alpha-park/genpark-dead-code-unreachable-ast-pruner-skill Enables whole-program callgraph reachability analysis to locate dead functions and stale flags, and prune unreachable AST branches. It integrates with MCP-compliant clients for deterministic, zero-dependency code review and semantic analysi | |
| genpark-deep-research-consensus-engine-skill alpha-park/genpark-deep-research-consensus-engine-skill Enables AI agents to perform deep research across multiple sources, arbitrating consensus while evaluating source authority and detecting contradictions. It integrates via MCP with clients like Claude Desktop and Cursor to deliver determini | |
| genpark-deep-research-cross-citation-graph-skill alpha-park/genpark-deep-research-cross-citation-graph-skill Enables AI agents to analyze and link citations across multiple research sources, building cross-citation graphs and resolving consensus from conflicting findings. It exposes this capability as a deterministic, zero-dependency MCP server th | |
| genpark-delegated-agentic-checkout-guardrail-skill alpha-park/genpark-delegated-agentic-checkout-guardrail-skill Enforces autonomous merchant checkout token and velocity limits for Agentcard/Stripe transactions. | |
| Distributed Agent Fleet Heartbeat & Liveness Watchdog alpha-park/genpark-distributed-agent-heartbeat-liveness-watchdog-skill Enables monitoring of distributed autonomous agent nodes through heartbeat ingestion, jitter-aware liveness checks, zombie/stalled worker isolation, and coordinated checkpoint hydration and failover rerouting. | |
| genpark-distributed-two-phase-commit-coordinator-skill alpha-park/genpark-distributed-two-phase-commit-coordinator-skill Enables MCP-compatible agents to coordinate distributed transactions through prepare/vote phases, unanimous commit or abort decisions, quorum validation, and failure recovery across swarm nodes. | |
| genpark-document-redaction-pii-scrubber-skill alpha-park/genpark-document-redaction-pii-scrubber-skill Enables document layout parsing, complex table reconstruction, formula auditing, and PII/credential redaction with Luhn verification, reversible salt hashing, and audit logs through MCP-compatible clients. | |
| genpark-dynamic-bundle-pricing-maximizer-skill alpha-park/genpark-dynamic-bundle-pricing-maximizer-skill Enables cross-category e-commerce product bundle pricing optimization to maximize average order value, providing deterministic, zero-dependency execution for autonomous agent workflows. | |
| genpark-dynamic-jsonld-rich-snippet-generator-skill alpha-park/genpark-dynamic-jsonld-rich-snippet-generator-skill Enables AI agents and developers to generate Schema.org Product and FAQPage JSON-LD rich snippets from a query payload, returning structured output with execution telemetry. It runs as a zero-dependency Python MCP server that plugs into Cla | |
| genpark-dynamic-sparkpage-layout-synthesizer-skill alpha-park/genpark-dynamic-page-layout-synthesizer-skill Enables autonomous agents to synthesize heterogeneous search results into interactive comparison layouts (Genspark Sparkpages) via MCP, with deterministic JSON schema validation and zero-dependency execution. | |
| genpark-dynamic-prompt-prefix-cache-skill alpha-park/genpark-dynamic-prompt-prefix-cache-skill Enables inference engines to match longest common prompt token prefixes via a radix trie, so cached KV-cache blocks are reused instead of re-prefilled. This eliminates redundant prefill computation and lowers time-to-first-token, alongside | |
| genpark-edge-inference-latency-telemetry-skill alpha-park/genpark-edge-inference-latency-telemetry-skill Enables profiling and optimizing edge and on-device LLM inference by measuring TTFT, TPOT, tokens/second throughput, and P50/P90/P99 jitter while providing standard-library primitives for quantization, paged attention, speculative decoding, | |
| genpark-eip712-typed-signature-phishing-sanitizer-skill alpha-park/genpark-eip712-typed-signature-phishing-sanitizer-skill Enables auditing EIP-712 typed signature phishing permits and sanitizing allowances (Permit2/MetaMask) via MCP, with deterministic callgraph verification and DeFi vulnerability triage. It integrates with Claude Desktop, Cursor, and MCP clie | |
| GenParkEmbodiedActionChunkingACTPolicyInterpolator alpha-park/genpark-embodied-action-chunking-act-policy-interpolator-skill Enables real-time spatial intelligence, trajectory generation, and tactile control for autonomous robotic systems through an MCP interface. It normalizes telemetry, performs robotics dynamics and kinematics, and applies boundary and collisi |
26,951–27,000 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.