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 |
|---|---|
| Glint Meet — every global model for your agent Call every global AI model through one OpenAI-compatible API. One key, all models. | |
| Glint Render — web rendering for AI agents Screenshots, PDFs, OG images, monitoring and evidence for AI agents. Glint Render by Moyu. | |
| memento Team claims Parallel coding agents claim a file before editing, so none overwrites another. | |
| GlobalGov — Government Contracts, Tenders & Procurement Find government contracts, tenders and RFPs you can still bid on, in 193 countries. Free, no key. | |
| GoodSign Send documents for e-signature, track and remind signers, and download signed PDFs. | |
| Govparse Government Data Gateway Pay-per-call US government data: carrier safety, visa sponsors, contracts, employer risk. | |
| GPT Business Read your GPT Business workspace, calculate quotes and invoices, and prepare business drafts. | |
| GrabMail disposable email Disposable email for agents: create an inbox, wait for the message, read the code. No key needed. | |
| GramForge Chat assistants for small businesses on Telegram: use cases, pricing, guides, sign-up links. | |
| Graph Paper Check a plot document and get a link that opens it in Graph Paper. No account, no key. | |
| Griddo AX Docs Official Griddo backoffice docs for content authors: search, read and list pages in ES and EN. | |
| GrowthVector Free SEO, GEO, ads, and email marketing knowledge base: search guides, pages, glossary, and prompts. | |
| GrowthVector Pro GrowthVector knowledge base plus SEO audits and website data extraction. Needs GrowthVector Pro. | |
| io.guapu/guapu CRM AI-native para PYMEs de LATAM: contactos, ventas, cotizaciones, WhatsApp y métricas vía MCP. | |
| Guardr Hosted MCP for website health monitoring. Tools: check_site, list_sites, get_site. | |
| GuestGraph GuestGraph: One guest, not five strangers | |
| GunSpec Read-only firearm specifications: calibers, ammunition, manufacturers and attachment fitment. | |
| Hamla An AI marketing team for any business: draft campaigns, read results, manage contacts. | |
| Hanoo Manage PHP apps on your own Ubuntu servers: deploy, roll back and inspect Laravel and WordPress | |
| Happo Review Happo's visual and accessibility diffs: inspect comparisons, accept or reject, report flakes. | |
| Harmony AI-native ITSM and ESM platform. resolve IT and HR requests inside Slack and Teams. | |
| HashIQ TikTok Shop products starting to sell: Scores, Go/Wait/Skip verdicts, videos, creators, competitors. | |
| Haulista Load Assistant Calculate required trucks or containers, verify shipment fit, and manage Haulista loading plans. | |
| Haystack Auto Apply See your job matches and have Haystack's AI agent apply to the ones you pick. Sign in with Haystack. | |
| Haystack Jobs Search live jobs from employers' own careers sites in the US, UK, Canada, Australia and Europe. | |
| Healthparse Healthcare Data Gateway Pay-per-call US healthcare data: hospital financials, prices, quality, exclusions, wages. | |
| Heartly Deals — Live Flash Sales (Shopify & WooCommerce) Live flash-sale inventory from verified Shopify and WooCommerce merchants worldwide. | |
| Heldly AI-native scheduler that lives in Claude. Describe meetings in plain English; Heldly does the rest. | |
| Helious market intelligence US Treasury auction tails, the live curve regime, scored macro releases, and why rates moved. | |
| io.helloledger/bookkeeping Bookkeeping for owner-operated businesses. Query transactions, invoices, and reports. | |
| HelpCenter.io for agents Without an account, an AI agent can create or migrate a help center and hand its user a claim link. | |
| HelpCenter.io Write, organize, design and migrate a HelpCenter.io help center: articles, categories, template. | |
| HempData Verified hemp & cannabinoid regulatory data for all 50 US states + DC. Free key at hempdata.io. | |
| io.heronapp/heron Signed security scores for what an AI agent runs and reads: skills, MCP servers, prompts, tokens. | |
| HeyReach Automate your HeyReach workspace — manage campaigns, leads, unibox, webhooks, and pull analytics. | |
| Hibira Create and manage Hibira realtime apps (Pusher protocol compatible) from your AI agent. | |
| Hirelabs Find and message top native iGaming and web3 talent: AI search, roles and chats. | |
| HokAI AI tool directory MCP server, live since July 2026. Tools, agents, models, companies, services. | |
| Honee – cruise · honeefy Find bookable sea and river cruises; ports, ships, cruise lines and an advisor opinion. | |
| Honeycomb Query Honeycomb observability data: traces, events, metrics, SLOs, triggers, and boards. | |
| hovhannes.io Yerevan Product Coffee: table dates, remaining seats, seat requests, and the field notes behind it. | |
| HowToRomania Romanian company data, e-Factura and legislation: CUI lookup, courts, risk, invoices, laws | |
| Howwe Read and update your Howwe strategy: initiatives, MIGs, milestones, activities and teams. | |
| htmlkin.io Publish and manage HTML and static websites via OAuth 2.1 MCP on htmlkin.io. | |
| Hubity Preview the month's billing from approved time, retainers and progress, then draft invoices to send | |
| Huint Create and manage real-world Huint photo verification tasks via hosted streamable HTTP. | |
| Hunter-Seeker The decision layer for AI agents: act, escalate or refuse, and every decision comes back signed. | |
| Huntertech Vendor incidents, public pricing, and plan-gated account tools. OAuth at /mcp/auth. | |
| Hydori Read, write, translate and sync WordPress and Webflow blog articles from Claude. | |
| Parley Message channels between the agents of different people, one-to-one or in groups. |
41,401–41,450 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.