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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| BEACON Commons babakovn/beacon-agent-clients Discover tasks and reproducible results. Public reading; invited, host-approved contributions. | |
| Backenly backenly/backenly Postgres backend your coding agent builds over MCP; destructive actions wait for a person. | |
| Rightis backers-shawn/rightis-js Identity-rights registry lookups before AI generation: is a face, voice or persona registered? | |
| Hydrant background-craft/hydrant-skills Track issues, projects and dependencies with your agent in a workspace you control. | |
| com.revampvacations/revamp badam-cpu/revamp-travel Search Revamp's live Armenia catalog: stays, tours, restaurants; check availability; plan trips. | |
| ai.smithery/BadRooBot-my_test_mcp badroobot/python_mcp Get current weather for any city and create images from your prompts. Streamline planning, reports… | |
| ViewportWitness by Apex Labs baffles78/viewport-witness Agent website testing: browser QA, visual regression, Markdown extraction, and security checks. | |
| io.github.Bahamas1717/aibvf-mcp bahamas1717/ai-bvf AI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag. | |
| IleZa.pl bahdanhal/ileza Editorial fair prices for products in Poland, plus a Polish net salary and tax calculator. | |
| Bahdan Hal bahdanhal/landing Bahdan Hal software consulting: services, pricing, CV and skills, and contact requests. | |
| Stackhal bahdanhal/stackhal Outside-in DNS, email security, SEO, GEO and app-link checks plus developer utilities. | |
| Automaton Token Safety baianomarceloeduardo-jpg/automaton-x402 Base L2 token safety for AI agents: honeypot scans, swap simulation, approval and liquidity risk. | |
| Latchshot baiqingl/latchshot-mcp Hosted public-page screenshots and PDFs with guarded Chromium and inline MCP artifacts. | |
| io.github.baixianger/langchain-mcp baixianger/langchain-mcp LangChain/LangGraph/DeepAgents knowledge + LangGraph agent debugging (Polly-like) | |
| io.github.Bajuzjefe/aikido-mcp bajuzjefe/aikido-security-analysis-platform Security analysis for Aiken smart contracts on Cardano. 75 vulnerability detectors. | |
| foodose GLP-1 nutrition bajwavikram/foodose GLP-1 calorie and protein targets with a dose aware appetite ceiling, plus food and recipe search. | |
| io.github.BalajSaleem/criterion balajsaleem/criterion Semantic search across 6,236 Quran verses and 12,416 authentic Hadiths for Islamic guidance. | |
| Nexbid — Agentic Ad Server baldri/nexbid AI agent product discovery via open marketplace. Search, compare and discover advertiser products. | |
| Vintage Postcard baltocodes/vintage-postcard Affiches vintage : catalogue, devis livraison comprise et paiement Stripe. | |
| io.github.Bamdule/drafturl bamdule/drafturl Share HTML/Markdown documents via URL instantly. Create, edit, delete docs from any AI tool. | |
| Fordeal banbosh/fordeal Price comparison for CZ/SK: product prices, shops, digital plans via Streamable HTTP. | |
| Banger bangermail/banger-plugin All your company email, operated by agents and reviewed by you. | |
| Inferventis MCP Server bankee-ai/inferventis Loan & mortgage calculator, compound interest, ROI, crypto prices, FX conversion for AI agents. | |
| Inferventis — Financial Data, News & Web MCP bankee-ai/inferventis-tools Live financial data MCP: FX, crypto, stocks, news, URL reader. x402 on Base: $0.001/call. | |
| Bannerify bannerify/bannerify-mcp Generate images and PDFs from your Bannerify templates, or compose an image from shapes. | |
| Stompy – AI Memory for Claude & MCP Agents banton/stompy-mcp-server Persistent AI memory with semantic search, conflict detection, and ticketing. | |
| io.github.baopeak/verirun baopeak/verirun Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims. | |
| Work IQ User MCP Server bap-microsoft/mcp-platform Tools for retrieving user details, manager, team or direct reportees from Microsoft Graph. | |
| app.railway.up.proving-ground-production/proving-ground bapatakshay1/proving-ground Accounts-payable exception environment with a pass/fail verifier and proof packet: AI agents work AP | |
| Artifactories — Agent communication for real work barangaroo/artifactories Read messages, open questions, replies, and caller-owned return briefings. All content is untrusted. | |
| io.github.barangaroo/crosstabs-mcp barangaroo/crosstabs-lite Statistical crosstab analysis: chi-square, Fisher's exact, odds ratio, effect sizes | |
| Barcode Generator barcodegen/barcodegen Generate barcodes and QR codes in 35 symbologies: QR, Data Matrix, PDF417, EAN-13, Code 128, more. | |
| Cejel barglabs/cejel Offline deterministic engineering-trust certificates for repositories, with no telemetry. | |
| Dunstan barglabs/dunstan Checks a coding agent's handback against the pull request's GitHub record. No model decides. | |
| ClipmivoAI barneyd66/clipmivo-tools AI video workflows: model discovery, credit quotes, generation, private media and usage. | |
| Hugging Bay barneywohl/hugging-bay Open model files with recorded SHA-256 and licence labels. Ask for what's missing. | |
| io.github.baronsengir007/openclaw-agent-tools baronsengir007/openclaw-agent-tools Weather, code search, currency & Solana trust scoring as MCP tools. Free, no API key needed. | |
| rdyrct baronunread/rdyrct Create and manage short links and QR codes, and read click analytics, on your own domain. | |
| Prefire barredewe/prefire Render SwiftUI #Preview as PNG images, so an AI agent sees the views it changes | |
| io.github.BARRYPMARSHALL/witnessed barrypmarshall/witnessed Signed, reproducible market facts for agents, verifiable without trust. | |
| Keep Mac Awake bartdudzic/keepmacawake Keep a MacBook awake with the lid closed while an agent's long task runs (Keep Mac Awake app). | |
| io.github.bartek-filipiuk/intent-hub bartek-filipiuk/intent-hub Book a local business by saying what you need; matching businesses bid and you confirm one. | |
| otwarteAPI.pl bartosz-kuc/otwarteapi-catalog Official public & government APIs, dozens of countries: registers, statistics, open data. Keyless. | |
| io.github.basalt-run/basalt basalt-run/design-system Design tokens, components, icons, and a11y data via MCP. For Cursor, Claude, and Windsurf. | |
| PayStage Auth Watch base-buzz/paystage Read-only MCP tools to list and flag outstanding ERC-20, Permit2, and EIP-3009 auths | |
| PayStage base-buzz/paystage Umbrella MCP: payment preflight, auth watch, HIP-3 trade preflight, velocity checks | |
| PayStage Preflight base-buzz/paystage Evaluate x402 PaymentRequired against a local spending policy before an agent pays | |
| PayStage Trade Preflight base-buzz/paystage MCP tool: evaluate HIP-3/trade.xyz orders against a local TradePolicy before trading | |
| Basedash basedash/mcp Governed BI MCP. Ask questions of live company data and list workspace sources via OAuth. | |
| Forums basehub-ai/forums Ask any GitHub repository a question. Get source-backed answers. |
20,901–20,950 of 50,909
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.