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 |
|---|---|
| Electron Build Electron desktop apps with secure architecture and common pitfall avoidance. | |
| Email Management Triage inbox email, draft clear replies, and manage follow-ups with priority routing, commitment tracking, and reusable templates. | |
| Email Marketing Email deliverability, list management, sequences, segmentation, and campaign optimization. | |
| Embeddings Generate, store, and search vector embeddings with provider selection, chunking strategies, and similarity search optimization. | |
| Empathy Respond to emotional content with genuine-feeling empathy using Chain of Empathy reasoning, reflection-before-response, and calibrated validation. | |
| Employee Create and manage virtual AI employees with persistent memory, defined roles, and graduated autonomy. Hire, train, and delegate tasks to specialized workers. | |
| Encryption Encrypt files, secure passwords, manage keys, and audit code for cryptographic best practices. | |
| Engineer Apply engineering judgment across systems, constraints, trade-offs, failure modes, and verification before acting. | |
| Engineering Support engineering understanding from DIY projects to professional practice and research. | |
| English Writes and corrects English that reads like a native wrote it — any variety, any register. Use when text sounds stiff, robotic, translated, or AI-generated; when a sentence is grammatically fine but "sounds wrong"; when choosing between US, | |
| Enterprise Navigate enterprise software development with legacy integration, compliance requirements, stakeholder management, and architectural decisions at scale. | |
| Escalate Self-learn to decide when to act, when to ask, and which actions should always need approval. | |
| eSIM Implement and troubleshoot eSIM across consumer activation, carrier integration, and RSP development. | |
| ESP32 Avoid common ESP32 mistakes — GPIO conflicts, WiFi+ADC2 trap, deep sleep gotchas, and FreeRTOS pitfalls. | |
| Estonian Write Estonian that sounds human. Not formal, not robotic, not AI-generated. | |
| Ethereum Assist with Ethereum transactions, gas optimization, token approvals, and L2 bridges. | |
| Ethics Navigate moral reasoning from personal dilemmas to academic philosophy. | |
| Etsy Improve Etsy listings with buyer-intent keywords, margin-safe pricing checks, and structured experiments that raise qualified traffic and conversion. | |
| Europe Navigate Europe for travel, relocation, study, remote work, and cross-border life with bloc logic, country fit, rights, timing, and practical execution. | |
| Events Build a personal event system for tracking concerts, conferences, parties, appointments, and everything in between. | |
| Exam Generate practice tests, flashcards, study schedules, and timed simulations from any study material. | |
| Excel / XLSX Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation... | |
| Expat Companion Plan and track international moves with visa timelines, document checklists, and country-specific guides. | |
| Expedia Search Expedia stays, packages, cars, and activities, compare real trip costs, and run partner-safe booking workflows with web and API modes. | |
| Expenses Logs, splits, categorizes and reports spending — daily expenses, shared costs, reimbursements, receipts, project and trip budgets. Use when the user paid for something and wants it recorded, when a bill has to be split and someone told what | |
| Explain Learns how to explain things to your human. Adapts format, depth, and style by topic. | |
| Extract PDF Text Extract text from PDF files using PyMuPDF. Parse tables, forms, and complex layouts. Supports OCR for scanned documents. | |
| Face Put a human face on your agent with fast avatar shortlists, gender control, transparent options, and reusable profile links. Use when the user wants an avata... | |
| Facebook Marketplace Buy and sell on Facebook Marketplace with pricing discipline, safer messaging, shipping guardrails, scam detection, and account-safe workflows. | |
| Family Coordinate family schedules, household tasks, school logistics, care routines, and private-versus-shared memory with a structured family system | |
| Fashion Style outfits, decode dress codes, and shop smart with body-aware advice, trend intelligence, and practical constraints. | |
| FastAPI Builds, debugs, and hardens FastAPI services: async endpoints, Pydantic models, dependency injection, auth, and deployment. Use when writing or reviewing a FastAPI app, router, or schema; when the API hangs or every route slows because a sy | |
| Fasting Tracker Tracks intermittent fasting and extended fasts: logs start and break times, computes elapsed hours, fasting stages, and eating windows. Use when the user starts, breaks, or checks a fast, plans 16:8, 18:6, OMAD, 5:2, alternate-day, time-res | |
| Fastmail API Drives the Fastmail JMAP API for mail, search, bulk triage, sending, masked email, contacts, and calendars. Use when the user mentions Fastmail, JMAP, api.fastmail.com, or a Fastmail API token; when a JMAP call returns 401, 403, `unknownCap | |
| Feelings Build a personal emotional tracking system for understanding patterns, triggers, and what helps. | |
| FFmpeg Process video and audio with correct codec selection, filtering, and encoding settings. | |
| Figma Builds and debugs Figma files: auto layout, components and variants, variables and modes, libraries, prototypes, and Dev Mode handoff. Use when a frame will not resize, text clips or overflows, a variant set lags, a library update breaks in | |
| Files Safely organize, deduplicate, and analyze files with intelligent bulk operations and full undo support. | |
| Finance Support financial understanding from personal budgeting to professional analysis and research. | |
| Find Locate anything with progressive search expansion, multi-source validation, and iterative refinement until found. | |
| Fine-Tuning Fine-tune LLMs with data preparation, provider selection, cost estimation, evaluation, and compliance checks. | |
| Finland Plan Finland trips with verified entry rules, season-aware routing, rail-and-Lapland logistics, and practical tourist safety. | |
| Finnish Write Finnish that sounds human. Not formal, not robotic, not AI-generated. | |
| Firewall Configure firewalls on servers and cloud providers with security best practices. | |
| First Principles Thinking Break problems to fundamentals, rebuild from truth, eliminate hidden assumptions. | |
| Fishing Track fishing spots, gear, catches, and conditions with personalized recommendations. | |
| Fitness Plans and progresses workout programs — strength, muscle building, cardio, endurance, and general conditioning — with quantified rules. Use when designing a training plan, routine, or split, choosing sets, reps, weights, or heart-rate zones | |
| Fiverr Build and scale a Fiverr freelancing business with gig optimization, buyer communication, and seller level progression. | |
| Flashcards Create effective flashcards with optimal formatting, spaced repetition integration, and memory science principles. | |
| Flask Avoid common Flask mistakes — context errors, circular imports, session configuration, and production gotchas. |
39,101–39,150 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.