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 |
|---|---|
| io.github.uncfreak1255-code/hostaway uncfreak1255-code/hostaway-mcp Read-only MCP server for Hostaway PMS — guest conversations, reservations, and listings | |
| io.github.nedim1511/unclaimed-sol unclaimed-sol/unclaimed-sol-mcp The first Vibe Claiming MCP: AI agents scan and reclaim dormant SOL on Solana. Signs locally. | |
| Lupa — local file search for your Mac under71/lupa-mcp Search your Mac's files by name and by text inside documents. Local index, Korean-aware. | |
| com.undercurrentholdings/aegis undercurrentai/aegis-mcp Local stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline. | |
| KMP underpass-ai/kmp Local-first agent memory that preserves what happened, when and why | |
| MRX Public MCP underwriter-mrx/mrx-mcp Read-only, source-linked mineral-rights education from MineralRightsXchange.com. | |
| C# Class Analyzer MCP undy-mosq/csharpanalysermcp A read-only MCP server that lets an AI assistant browse any C# solution through Roslyn. | |
| io.github.unempyd/revenueos unempyd/revenueos Self-hosted revenue department: find opportunities, execute approved work, measure results. | |
| unerr unerr-ai/unerr-cli Operational memory for AI agents: code graph, session memory & guardrails. No context rot. | |
| ai.membase/membase unibaseio/membase Long-term memory for you and your AIs: search memories, read the profile, add facts and documents. | |
| SlicerBridge unicorngraveyard/slicerbridge A Rosetta Stone for multicolor 3MF files: one project in, a checked file for every printer out. | |
| dep-scout unievolver/dep-scout Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them. | |
| com.unifically/mcp unifically-dev/unifically-mcp One API for 100+ AI video, image, music and speech models. | |
| io.github.UNIPaaS/paas-build-mcp unipaas/paas-build-mcp Your agent opens a real merchant account (go_live) and takes payments the same day. 3.9% flat. | |
| Unipile MCP unipile/unipile-mcp LinkedIn, Sales Navigator, Recruiter, WhatsApp, Instagram, Telegram and email MCP for coding agents. | |
| io.github.UniRate-API/mcp unirate-api/unirate-mcp Currency conversion and exchange rates for AI. 170+ currencies, historical data back to 1999. | |
| ActableSite AI Crawler Monitor unitedideas/actablesite-mcp Check AI crawler robots.txt policy and monitor public-site policy, sitemap, and llms.txt changes. | |
| Medicare Enrollment and Revalidation Data unitedideas/pending-medicare-mcp Free CMS enrollment and revalidation evidence with pay-per-result automation and Roster Watch terms. | |
| io.github.UnityNodes/canton-ccpedia unitynodes/ccpedia Canton Network: CIPs and their on-chain vote outcomes, docs, forum, validator upgrade deadlines. | |
| uniwire uniwire-dev/uniwire Electrical single-line and multi-line diagrams: build, check (NF C 15-100, IEC 60364), draw, PDF. | |
| io.getunleash/unleash-mcp unleash/unleash-mcp MCP server for managing Unleash feature flags | |
| Microsoft Access Database unmateria/mcp-access Read and edit Microsoft Access databases (.accdb/.mdb) - forms, VBA, tables, queries. Windows. | |
| KiCad Schematics unmateria/mcp-kicad Design KiCad schematics by talking to Claude. Places parts, wires nets, runs ERC. Needs KiCad 10. | |
| sigtap Agent Tools unnamedaiagent/sigtap-agent-tools 13 paid x402 tools, USDC/Base. Free check: GET /preview<path>=200 sample. Copy-paste pay: /llms.txt | |
| thing unravel-team/thing-cli Artifacts for any coding agent: a durable link with versions, diffs, and comments on the page. | |
| UnrealUGC unrealugc/mcp Generate and manage AI UGC video ads through eleven typed MCP tools | |
| supercarto unselfisheologism/supercarto Token-budgeted map context: OSM graph, terrain, weather, air, transit | |
| Unshift unshift-ai/unshift-mcp Turn Claude or ChatGPT into a website builder that ships a real site to a live URL you own. | |
| mail-index unsoldgroup/mail-index Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests. | |
| Unstoppable Domains unstoppabledomains/unstoppable-mcp-server Domain search, registration, DNS, marketplace, and checkout with your AI agent. | |
| unulu unulu-ai/unulu AI agent website builder. Create and publish link-in-bio sites via MCP or REST API. | |
| NeoSQL MCP unvus/neosql-mcp Schemas, SQL, ERDs, and codegen for PostgreSQL, MySQL, Oracle, SQLite, and more via NeoSQL Desktop. | |
| io.github.up2itnow0822/clawpay up2itnow0822/agentpay-mcp Non-custodial x402 payment MCP server for AI agents. Wallets, payments, and commerce on 17 chains. | |
| ClawPay MCP — Non-Custodial x402 Payments for AI Agents up2itnow0822/clawpay-mcp Non-custodial x402 payments for AI agents. Sign locally, spend limits, Base network. | |
| upGrowth Growth Toolkit upgrowth-in/upgrowth-growth-toolkit 29 free read-only growth tools: CAC, ROAS, PPC, schema, meta tags, robots.txt and AI crawler checks. | |
| io.github.uponex/gisgp uponex/gisgp-mcp GIS tools for AI agents: 65 free tools + 8 paid (hazard/site-scouting/GeoJSON export) | |
| ai.upriver/upriver upriver-ai/upriver-mcp Know what's gaining traction online: breakout topics in tech, sports & politics, with citations. | |
| Upscrape upscrape/upscrape-mcp Real-time data APIs for 50+ commerce, grocery, social and maps platforms over one OAuth MCP server | |
| Korea Tax Calculator upstageai/korean-tax-calc-mcp Korean tax calculation and tax-audit judgment MCP: 94 tools with statutory citations. | |
| Korea Tax Law upstageai/korean-tax-mcp Korea tax law: NTS rulings, court/tribunal decisions, basic rules, treaties, point-in-time statutes | |
| io.github.upstash/mcp-server upstash/mcp-server No longer maintained. Use the remote Upstash MCP server: https://mcp.upstash.com/mcp | |
| io.github.upstash/redis-mcp upstash/redis-mcp Run Redis commands and look up Upstash Redis Search docs against Upstash Redis over HTTP or TCP. | |
| Upstream.so upstream-so/upstream-mcp Manage 24/7 live streams, media, playback queues, schedules, and multistreaming from AI assistants. | |
| Uptimepage uptimepage/uptimepage Monitor uptime and incidents, run checks, and publish status updates from your Uptimepage org. | |
| io.github.Uptrack-App/uptrack-mcp uptrack-app/uptrack-mcp MCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents. | |
| changelogai ura-tools/changelogai Generate changelogs and suggest semver bumps from git history | |
| Urantia Papers urantia-hub/urantia-dev-api The Urantia Papers in English and Spanish, with cross-references to the Bible and 21 texts. No key. | |
| io.github.urbanmorph/irrational urbanmorph/irrational Adversarial behavioural-bias engine — audits your decisions for cognitive biases via your own AI. | |
| Urlbox urlbox/screenshot-mcp-server Screenshots, PDFs, video, markdown and page data from any website, via Urlbox. | |
| URLpipe urlpipe/mcp Read any page with its JavaScript run: Markdown, screenshots, metadata, console errors, Lighthouse. |
18,501–18,550 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.