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 |
|---|---|
| Image Editing Edit images with AI inpainting, outpainting, background removal, upscaling, and restoration tools. | |
| AI Image Generation Create AI images with GPT Image, Gemini Nano Banana, FLUX, Imagen, and top providers using prompt engineering, style control, and smart editing. | |
| IMAP Read, search, and sync IMAP mailboxes with UID-safe fetches, precise filters, and attachment-aware workflows. | |
| In-App Purchases Implement in-app purchases and subscriptions across iOS, Android, and Flutter with RevenueCat, paywalls, receipt validation, and subscription analytics. | |
| Deep Research Conduct exhaustive multi-source investigation with methodology tracking, source evaluation, and iterative depth. | |
| Inbox Master any inbox with triage frameworks, cognitive load reduction, and multi-channel prioritization. | |
| India Plan India trips with specific neighborhoods, regional food calls, route choices, and grounded advice that avoids common travel mistakes. | |
| Indie Hacker Build profitable products as a solo founder with validation-first approach, time protection, and brutal honesty. | |
| Indonesia Plan Indonesia trips with island-routing logic, verified entry guidance, weather-aware logistics, and practical local execution. | |
| Indonesian Write Indonesian that sounds human. Not formal, not robotic, not AI-generated. | |
| Influencer Create, manage, and scale AI-generated virtual influencers with consistent characters, multi-platform content, and monetization workflows. | |
| InfluxDB Store and query time-series data with proper schema design and retention. | |
| Infrastructure Design, provision, and connect cloud resources across servers, networks, and services. | |
| Inspiration Find design and AI art inspiration from curated galleries, screenshot libraries, and creative showcases. | |
| Instacart Build Instacart recipe pages, shopping lists, and retailer lookups with MCP, REST, secure auth, and launch-ready integration rules. | |
| Interior Design Coordinate interior design projects with space verification, supplier localization, and staged decision-making. | |
| Internet Manage internet connectivity, compare providers, diagnose issues, optimize performance, and handle mobile data when away from home. | |
| Intuition Make rapid pattern-based judgments without explicit reasoning, using Recognition-Primed Decision techniques and System 1 response patterns. | |
| Inventory Build a personal inventory system for home items, valuables, and equipment tracking. | |
| Invest Start investing with account selection, portfolio building, and long-term wealth strategies. | |
| Investor Evaluate opportunities, conduct due diligence, and manage portfolios with sound investment principles. | |
| Invoice Create and send professional invoices with automatic numbering, tax calculation, templates, and payment tracking. | |
| Invoices Files, checks, and audits the invoices you receive: OCR and e-invoice XML, duplicate and fraud checks, VAT deduction, and a searchable archive. Use when an invoice, bill, or receipt arrives as a PDF, photo, email attachment, or portal downl | |
| iOS Builds, ships, and debugs native iOS apps: lifecycle, permissions, entitlements, push, widgets, StoreKit, and App Store review. Use when a submission is rejected or a guideline blocks a release; when a permission prompt never appears, or a | |
| IoT Assist with IoT device setup, protocols, security hardening, and home automation integration. | |
| iPhone Run iPhone mission playbooks for battery, storage, privacy, connectivity, and daily automation with live operator-style guidance. | |
| Ireland Discover Ireland like a local with concrete pubs, coastal routes, city guides, and practical trip-planning tips. | |
| Irish Write Irish that sounds human. Not formal, not robotic, not AI-generated. | |
| Italian Write Italian that sounds human. Not formal, not robotic, not AI-generated. | |
| Italy Discover Italy beyond the clichés with specific restaurants, hidden gems, and insights that only locals know. | |
| Japan Discover Japan like a local with concrete city tips, regional route planning, food context, and practical travel logistics. | |
| Japanese Writes and edits Japanese that reads as if a native wrote it — casual, 敬体, or full keigo. Use when composing anything in Japanese (LINE or Slack message, business email, 履歴書, 退職願, 議事録, note or X post, speech, 年賀状, contract clause, manga or | |
| Jarvis Run the agent like an executive operator with calm briefings, sharp prioritization, context recovery, and proactive follow-through. | |
| Java Writes, debugs, and tunes Java and the JVM: nulls, equality, collections, generics, concurrency, streams, memory, builds, and upgrades. Use when Java throws NullPointerException, ClassCastException, ConcurrentModificationException, NoClassD | |
| JavaScript Writes, debugs, and reviews JavaScript: async and the event loop, coercion, closures, dates, Unicode, regex, and modern ES2023+ APIs. Use when JS throws TypeError or "undefined is not a function", a promise never settles or a rejection goes | |
| JEE Prepare for India's Joint Entrance Examination with progress tracking, weak area analysis, mock test strategy, and IIT/NIT targeting. | |
| Job Search Navigate job hunting with application tracking, company research, and interview preparation. | |
| Journal Runs a personal journaling practice: capturing entries, prompts for a blank page, weekly and yearly reviews, and patterns across years of writing. Use when the user wants to write, vent, dictate, or get something out of their head; when the | |
| JSON Parses, validates, transforms, and designs JSON payloads that survive real parsers, real clients, and real data sizes. Use when a parse fails at a byte offset or on a trailing comma, an id or an amount loses precision, accents and emoji com | |
| JWT Implement secure JWT authentication with proper validation and token handling. | |
| Kubernetes Debugs Kubernetes workloads and reviews manifests: pods, probes, resources, rollouts, Services, storage, RBAC. Use when a pod is Pending, CrashLoopBackOff, ImagePullBackOff, OOMKilled or stuck Terminating, when a Service or Ingress serves n | |
| Kanban Build multi-project Kanban systems with deterministic board discovery, consistent task processing, and persistent routing memory across sessions. | |
| Keras Build, train, and debug deep learning models with Keras patterns, layer recipes, and training diagnostics. | |
| Kernel Avoid common Linux kernel mistakes — atomic context violations, allocation failures, and locking traps. | |
| Keys Secure API key management with broker. Keys never exposed to agent context. | |
| Kimi Build and debug Kimi API workflows for chat, coding, reasoning, and tool-calling with live model checks, retries, and safe routing. | |
| Korean Write Korean that sounds human. Not formal, not robotic, not AI-generated. | |
| Kotlin Writes, debugs, and reviews Kotlin: coroutines and flows, null safety, collections, Java interop, and Compose state. Use when an NPE hits a non-null type, `!!` or a Java platform type blows up, a coroutine leaks, never cancels, or swallows | |
| Landing Page Build high-converting landing pages with proven structure, persuasive copy, and conversion optimization. | |
| LangChain Builds and debugs LangChain apps in Python: LCEL chains, agents, tools, retrievers, streaming, and structured output. Use when writing or reviewing a chain, agent, tool, retriever, or prompt template; when a prompt raises KeyError or "missi |
39,251–39,300 of 108,824
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.