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 |
|---|---|
| Fudge scroobius-pip/fudge-mcp Build websites that look designed, not generated. Fudge gives AI real websites to study. | |
| br.com.scrypta/guapissimas scrypta-mcp/scrypta-mcp Catálogo de 328 produtos em 26 categorias — servido via Scrypta. | |
| viberank sculptdotfun/viberank Submit your AI coding usage (Claude Code, Codex, Gemini CLI) to viberank and read the leaderboard. | |
| tgcloud — Telegram serverless bots sdamarketing/tgcloud_mcp MCP server for Telegram serverless bots: lifecycle, deploys, migrations, webhooks via tgcloud CLI | |
| io.github.sdeanesh-png/agentpay sdeanesh-png/agentpay Spending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail. | |
| io.github.seahawk2986-hue/apex-ghost-family seahawk2986-hue/apex-ghost-family Read-only window into an open self-evolving agent family: fleet health, court verdicts, receipts. | |
| GrabFood MCP (via SEA MCP) seamcp/grabfood-mcp Search GrabFood restaurants, full menus and dish prices by city, neighbourhood or radius. | |
| IDX MCP - Indonesia Stock Exchange Trading Data seamcp/idx-mcp Indonesia Stock Exchange data: listed companies, shareholders, boards and daily trading. | |
| Shopee MCP (via SEA MCP) seamcp/shopee-mcp Search Shopee shops, listings and categories across markets: sellers, prices, sales and ratings. | |
| Seamgrin seamgrin/dubdubdub Find alterations, free tailor training, and paid work opportunities for experienced tailors. | |
| Korea Nationwide Data sean-park-funda/korea-data-mcp Nationwide Korea: bus stops in 138 cities, 30-year climate normals, tourism (KR/EN). | |
| Korea Ocean Leisure sean-park-funda/korea-ocean-mcp Korea tide times (42 stations) plus fishing, mudflat, beach, surf and scuba forecasts. | |
| Builderforce Memory seanhogg/builderforce-memory Token-saving persistent memory for AI agents: recall durable facts instead of re-reading files. | |
| Builderforce seanhogg/builderforce.ai Run tickets, boards, OKRs and cloud coding agents in your Builderforce workspace | |
| io.filechanger/filechanger seanparsons/monorepo Convert documents between text formats (markdown, html, and more) via the FileChanger API. | |
| io.searchapi/mcp searchapi/searchapi-mcp Give AI assistants access to real-time search data through SearchApi. | |
| Searcher OS searcher-os/searcher-os-mcp AI agent access to your Searcher OS deal feed, pipeline, buy boxes, CIM analysis, and broker CRM. | |
| Search Fragments searchfragments/search-fragments-mcp Pieces together films, shows, songs, books, quotes, places and studies from remembered fragments. | |
| SearchPipe searchpipe/searchpipe-mcp Web search API and MCP server for developers building AI agents. | |
| io.github.SebastianBO/financial-data sebastianbo/quant-platform Stock prices, financials, insider trades, institutional holdings for 141K+ companies | |
| NC Wedding Guide sebastianrtj/nc-wedding-dreamscape Find NC wedding venues and vendors, plan costs, and prepare vendor inquiries. | |
| Corral sebastienrousseau/corral Search code and symbols across every clone in your Corral workspace. Zero network calls. | |
| run.cityheart/heart-routes secupunk/scenic-pathfinder-ai Heart-shaped GPS running routes in 200+ cities — charity, gift, memorial, anniversary. | |
| one.secureai/redaction secureaione-jpg/secure-ai-web Takes the people out of text before a model sees it, and puts them back in the reply. | |
| Securealy securealy/securealy Grade a URL as an attacker and a customer would see it; scan a repo; check Supabase, Stripe, Vercel. | |
| SecureLend Underwriting securelend/mcp-underwriting Open a credit file, chase gaps, screen sanctions, draft a cited memo. Person decides. | |
| SecureNow securenow-ai/securenow-npm Production security for Node.js apps: investigate live attacks, block IPs, tune detections. | |
| io.github.SecurityRonin/alaya-mcp securityronin/alaya Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall | |
| io.github.securityscan-api/securityscan securityscan-api/securitystack-mcp Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout. | |
| AgentFeed on Mezo seekdaseek/agentfeed-mezo Crypto data, MUSD peg and Mezo trove health, paid per call in MUSD on Base or Mezo. No gas. | |
| Impri sekera-radim/impri Impri MCP server — human-in-the-loop approval inbox for AI agents | |
| five46 sekharsdet/five46 BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success. | |
| Kemory sekondbrainailabs/kemory-cli Persistent memory for AI agents: connects MCP clients to your Kemory memory vault | |
| Sekura sekuraai/sekura-plugins Scan a GitHub repository for vulnerabilities, with proof for every finding, from your coding agent. | |
| Selda selda-ai/selda-mcp-docs Find customers, research each one and draft the outreach. Nothing sends without approval. | |
| io.github.seldonframe/seldonframe-mcp seldonframe/seldonframe Open-source GoHighLevel alternative for agencies. White-label CRM, booking, intake, chatbot via MCP. | |
| Akashi Notari self-reality/verifier Proof of existence for files: anchor a SHA-256 hash on Base, look up proofs. Paid with x402. | |
| io.github.selfagency/beans-mcp selfagency/beans-mcp Interact with the Beans CLI issue tracker agentically | |
| io.github.selfagency/git-mcp selfagency/git-mcp A Git MCP server that doesn't suck | |
| Base Intel MCP selflabbs/base-intel-mcp Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status. | |
| Domain & Company Intel MCP selflabbs/domain-intel-mcp Domain intel for AI agents: RDAP registration, DNS, email deliverability, tech stack. | |
| Economy Intel MCP selflabbs/economy-intel-mcp Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys. | |
| Filings Intel MCP selflabbs/filings-intel-mcp SEC EDGAR filings for AI agents: company lookup, filings, financials, insider trades. No keys. | |
| Market Intel MCP selflabbs/market-intel-mcp Live & historical FX rates and currency conversion for AI agents. No API keys. | |
| Package Intel MCP selflabbs/package-intel-mcp Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys. | |
| Regulatory Intel MCP selflabbs/regulatory-intel-mcp US Federal Register for AI agents: rules, notices, executive orders, agency lookup. No keys. | |
| Security Intel MCP selflabbs/security-intel-mcp CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys. | |
| Weather & Geo Intel MCP selflabbs/weather-intel-mcp US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys. | |
| ConnectWise PSA selic/mcp-connectwise-psa ConnectWise PSA (Manage) MCP server — tickets, time entries, companies, configurations, BYOK | |
| Microsoft Planner selic/mcp-planner Microsoft Planner MCP server — plans, buckets, tasks via Microsoft Graph, ETags handled |
48,601–48,650 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.