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 |
|---|---|
| Pipecore Deploy and operate apps with AI agents · Деплой и поддержка приложений через AI | |
| Planable Plan, approve, publish, and analyze social content | |
| PocketCaddie Golf drills, ball-flight fixes and range or home practice plans from the PocketCaddie library. | |
| Polyblog Multilingual Blog Write, translate and publish blog articles, plan topic ideas and check each blog's languages. | |
| PoolParty Main Stage Airtime Inspectable public airtime for agents routing demo media, launch videos, and proof assets. | |
| PostFinder post offices and parcel points Nearest post offices, parcel lockers and post boxes in AU, NZ, US, UK and Canada. Free, no key. | |
| postmoderno Schedule and publish social posts to Bluesky, Mastodon and X / Twitter by asking your AI agent. | |
| io.postnext/postnext Schedule, publish and track posts on X, Instagram, LinkedIn, TikTok, YouTube, Threads and Bluesky. | |
| Postclick by PPC.io: Landing Page CRO Landing-page CRO: audit pages, rewrite copy, answer buyer objections, design and build via MCP. | |
| Presify Microsoft Teams presence history: who's online, when, how long, and flagged patterns. Read-only. | |
| PreVibe Validate your SaaS idea with market research before you build it. | |
| Printdash Online printing for Australia: products, exact prices, quotes, artwork checks and orders. | |
| PrintPal 3D printing: printable models, calculators, troubleshooting wiki, build guides, AI 3D + CAD design. | |
| Prisma Postgres and Prisma Compute Manage Prisma Postgres and existing Prisma Compute apps. Requires sign-in; does not upload code. | |
| ProfessionalHeadshot.io LinkedIn, Slack and GitHub profile photo specs, headshot style guides and a free headshot audit. | |
| Prompt Anything Turn a rough request into a specialized prompt using your saved profile and business context. | |
| PropWalk Real estate social media manager: address in, a week of posts out, booked to IG, FB and TikTok. | |
| ProseMap Sentence-by-sentence analysis of a prose draft: a score for every sentence and every handoff. | |
| ProSide Golf Permission-scoped Play Now, live scoring, and organization event operations for ProSide Golf users. | |
| Prospectar Read a B2B commercial team's catalog and funnel stages on Prospectar. | |
| ProteinIQ Run protein folding, docking, design and sequence analysis tools, and read their results. | |
| ProtoNote Share prototypes for team review: publish HTML, reviewers pin notes, pull feedback back to apply. | |
| Protoperfect Labs Search and read Protoperfect Labs research, documentation and glossary. Read-only. | |
| PtData Point-in-time US equity fundamentals for quants and AI agents. Free tier, no API key needed. | |
| Pubble Real-time audience engagement for newsrooms and events: live Q&A, polls, liveblogs, chat. | |
| PublicAPIs.io Search 1,500+ public APIs with docs, code and auth/free-tier filters; list or sponsor your API. | |
| Pugi AI product team: builds and publishes websites from a brief, logos, security checks. | |
| Pulldata Discover and run Pulldata scrapers, track jobs, and retrieve results from your AI client. | |
| Puzzle Startup accounting: cash, burn, runway, financial statements, transactions, bills and invoices. | |
| PXL8 verified fight records Verified fight records for AI assistants: look up a fighter or fight card, cite the pxl8.io page. | |
| Pylon SEO Audit, rank-track and analyze SEO for sites via an authenticated MCP server. | |
| io.q9ive/olcum Checks e-commerce ad measurement (pixels, GTM, GA4, consent, UTM) and diagnoses exported ad reports. | |
| qrcode.io QR codes Free static QR codes (PNG or SVG) that never expire, for URLs, WiFi, vCards and text. No account. | |
| Qt Documentation Qt 5 and Qt 6 framework and product docs: Qt Creator, MCUs, Squish, Coco and more. | |
| Quick Lotto lottery results Winning numbers for 30+ world lotteries, minutes after each draw. Free, no key, CC BY 4.0. | |
| Qulture Studio Make AI videos and images in Qulture Studio from ChatGPT, Claude, Cursor or any MCP client. | |
| Railagent Inbox for AI agents: one address per agent to message and share files. | |
| Raute Account Your own Raute delivery day from the assistant: stops, drivers and routes, after you sign in. | |
| Raute Route Planner Plans delivery routes for up to 25 US addresses and 5 drivers, with the stop order and a map. | |
| RDAP API Normalized JSON for any domain across 1,200+ TLDs, reading WHOIS where no RDAP server exists. | |
| Re:Vault Find B2B buyers with a live reason to talk, write first messages, send from your own LinkedIn. | |
| io.reachium/linkedin LinkedIn campaigns, content, leads and inbox from your AI client. Scoped, revocable keys. | |
| RealUptime RealUptime monitors, incidents, status pages, Errors issues, and free third-party outage checks. | |
| RecordX Read-only access to your RecordX meetings: search transcripts, summaries, action items. | |
| ReelDrop Schedule Instagram reels, manage comment-to-DM automations, and read analytics | |
| Reelhouse Marketing videos for your business: 150+ searchable viral templates, scripts, AI characters. | |
| ReelMint Studio Script, animate, narrate and publish vertical Shorts — every step stays an editable screen. | |
| Real Estate Analyzer Free real-estate underwriting, no key or account. 6 strategies, stress tests, max offer. | |
| Rendry Deterministic image rendering for agents: JSON template in, on-brand PNG out. | |
| Resilis Deploy local apps, add managed Postgres, and inspect logs from your AI coding agent. |
41,601–41,650 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.