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 |
|---|---|
| Porkbun foreverworks/mcps Register domains and manage DNS, hosting and mail at Porkbun, with every purchase confirmed first. | |
| Trademark search foreverworks/mcps Check whether a name is already a registered or pending trademark in the US or the EU. | |
| TypeSafe foreverworks/mcps Get calibrated yes or no answers, choices and scores from TypeSafe's Jev, for one item or 1000 rows. | |
| Forge Treasury forge-treasury/forge-cursor-plugin Non-custodial USDC yield vaults on Base mainnet with 9 MCP tools for AI agent treasury. | |
| OKA Anywhere forgeagents-jp/oka-anywhere Cited answers in Claude or ChatGPT only from your office's procedures; says so when not covered. | |
| io.github.forgemeshlabs/travel-assistant-mcp forgemeshlabs/travel-assistant-mcp No-key travel MCP for Claude Desktop, Codex-style agents, Hermes, and other clients. | |
| io.github.forgemeshlabs/x402-scan-mcp forgemeshlabs/x402-scan-mcp x402 Endpoint Scanner — a free local health probe for x402 paid endpoints as an MCP server. | |
| io.github.forkflux/forkflux-mcp forkflux/forkflux Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams | |
| formbase formbaseso/formbase-mcp Collect verified customer information with one request | |
| addy.io former-stranger/addy-mcp Manage addy.io email aliases, recipients, domains, rules and blocklist. | |
| Formgong formgong/mcp Create contact forms, get HTML/React/Next.js snippets and read recent submissions on Formgong. | |
| Formhaus formhaus-dev/formhaus Validate Formhaus form definitions and simulate multi-step paths against the real engine. | |
| io.form/formio-mcp formio/ai Create and manage Form.io forms, resources, actions, roles, and projects from your AI agent. | |
| FormLM formlm/cli Build AI-powered forms, scored assessments and professional reports on FormLM, by natural language. | |
| Tachyon GPU monitor formray/tachyon Read-only NVIDIA GPU monitor: bottlenecks, VRAM forecast, crash diagnosis, pre-render check, jobs. | |
| Fortrip fortripengineering/fortrip Search hotels worldwide, compare live room rates, and create booking payment links. | |
| io.github.FortuneCasablancas/magicweave-fastmcp fortunecasablancas/magicweave-fastmcp Author, validate, simulate, and one-click-build game economies on the Magicweave platform. | |
| Admaxxer fortuneflick/admaxxercom AI-powered DTC analytics & ads manager for Meta + Google | |
| AgentiSend fortuneflick/agentisend-claude-plugin Email API for apps and AI agents: budgets per key, a kill switch, refusals that name the fix. | |
| PostDashPro fortuneflick/postdashpro-claude-plugin Social post scheduling for AI agents: queue or draft posts to 12 connected networks. | |
| io.github.fortunesayspump/nibgate fortunesayspump/nibgate x402 paid content and Nib Tips with pending holds, refunds, public ledger, pricing, and reputation. | |
| Forward Email forwardemail/mcp-server Privacy-focused email: domains, DNS verification, aliases, SMTP sending, mailboxes and calendars. | |
| com.talktoaleksandra/consultations fotorent/monorepo Published consultation details, live availability and booking handoff for Russian-language sessions. | |
| Slipmark founder-ship-it/slipmark Record AI agent verdicts bound to file hashes; refuse ones whose files or instructions changed. | |
| ContentSweep Supplier Feeds founder-sweep/contentsweep-supplier-feed-examples Map and validate recurring flat supplier catalogs with approved profiles and drift checks. | |
| Data Quality Gate founder-sweep/data-quality-gate-examples Check entire lead, order and inventory CSV/JSONL against approved contracts before writes. | |
| io.github.FoundryNet/foundrynet-inference foundrynet/foundrynet-inference x402 LLM proxy + data-enriched analysis (17 sources) + TimesFM predictive IoT intelligence. | |
| Stock Market Data MCP foundrynet/market-data-mcp Real-time stock quotes, history, options chains, sector performance & screening for agents. | |
| io.github.fouomene/mcp-server-geodata-placefinder fouomene/geodataplacefinder MCP GeoData Placefinder: search places, reverse geocode, and find nearby locations. | |
| com.mspmcp/instinct fox-crow-group-inc/instinct-mcp-extension MSP market intelligence for AI assistants: profiles, tech, maturity scores, and change signals. | |
| Foxit PDF API MCP Server foxitsoftware/foxit-pdf-api-mcp-server MCP server that exposes Foxit PDF API capabilities via stdio. | |
| x402 Tools foxxx009/x402-tools-mcp Pay-per-call research tools for AI agents, paid via x402 USDC. Remote MCP, one free tool. | |
| io.github.fpetitit/mcpcheckup fpetitit/mcpcheck Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP. | |
| CodeY CMS fpointerdev/codey-cms Discover, evaluate, install, and validate generated websites for the self-hosted CodeY CMS. | |
| Agentry.sh Observability fr33dr4g0n/agentry-public Canonical Agentry discovery for coding agents: analytics, errors, deploys, and automation. | |
| Midnight + Next.js MCP fractionestate/midnight-nextjs-mcp Unified MCP server for Midnight blockchain development and Next.js dApps. | |
| France Care, accès aux soins et prévention france-care/claude-plugin-france-care Accès aux soins en France, qui saisir pour une démarche de santé, prévention en entreprise. | |
| Alice — Santé territoriale France Care france-care/france-care-sites Donnees sante territoriale France : acces aux soins, FINESS, RNA — 35 000+ communes | |
| dev.rostro/rostro francis-ros/rostro-mcp-server Turn any LLM multimodal; generate images, voices, videos, 3D models, music, and more. | |
| io.github.francisco-perez-sorrosal/cv francisco-perez-sorrosal/cv An MCP server that provides access to Francisco Perez-Sorrosal's CV | |
| STEMPA francoisheunis88-beep/stempa-mcp STEMPA seals one brief every AI reads the same way, with a signed receipt. | |
| io.github.frangelbarrera/osint-agent-skills frangelbarrera/osint-agent-skills OSINT MCP server — 23 tools: DNS, WHOIS, Shodan, breaches, GEOINT, crypto. Works with Claude Code. | |
| ShowMeOnMap frankaiuser/showmeonmap Ask in plain English, get a rendered, shareable map from live public data. 24 geospatial tools. | |
| Disc Golf England (EDGA) frankbongo/discgolfengland EDGA Tour results, policies, club templates, course search and course-development guidance. | |
| Golf With Discs DiscFinder MCP frankbongo/golfwithdiscs-code Search current disc golf retailer inventory across 50+ shops by mould, plastic, price, and country. | |
| io.github.frankchu91/mindbase frankchu91/mindbase LLM-maintained personal wiki: cross-references sources, flags contradictions. Local markdown. | |
| com.frankponcelet/profile franknft-labs/portifolio Read-only MCP server for Frank Poncelet: profile, career, projects, speaking, expertise, persona. | |
| AgentPub frankshen18/agentspub Agent-to-agent messaging: directory, public lobby, DMs, channels, search. Stateless MCP + REST. | |
| FreshGate franktherecensor-hash/freshgate Paid MCP tool that checks whether a web page has changed. $0.001 per check via x402 on Base. | |
| Compera fredxhansson-cmyk/compera-mcp Live Swedish price & service comparison (products, broadband, mobile, electricity, loans) |
23,151–23,200 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.