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 |
|---|---|
| io.github.homeofe/supply-chain-guard homeofe/supply-chain-guard Supply-chain malware scanner and MCP server: vet packages in 15 ecosystems before install, offline. | |
| Homespun homespunapps/homespun Deploy a multi-user web app from your agent: hosting, auth, database, and permissions. | |
| citepath homezloco/citepath Citepath public MCP server for LLM readiness audits and public scan results. | |
| CityAlert homezloco/cityalert Free live public-safety incident map: global crime, fire, disaster, weather and news feeds | |
| findefend homezloco/findefend Finds recurring charges in bank statements and flags what to cancel. | |
| LiveGraph homezloco/livegraph Live, editable canvas for AI agents — author graphs via MCP, then watch and reroute runs live. | |
| modelright homezloco/modelright Live registry of AI model specs, context windows, and per-token pricing. | |
| pocketestimator homezloco/pocketestimator Branded job estimates and client approvals for independent contractors. | |
| io.github.honeycrisp-suite/mail honeycrisp-suite/honeycrisp Apple Mail over MCP: fenced reads, draft-only writing, human-gated actions, audited with undo. | |
| FileForge hongfeng328/fileforge File tools for your AI chat: PDF tables to Excel, merge PDFs, images to PDF, fill PDF forms. | |
| EcoCompute Should-I-Quantize Estimator hongping-zh/quant-energy Energy impact of LLM quantization, calibrated to measured GPU data. Every answer states its basis. | |
| Hooklistener hooklistener/mcp Webhook, email, WebSocket and tunnel testing for AI agents: capture, wait, verify, replay. | |
| Hookwarden — Webhook Integrity hookwarden/hookwarden Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +23. Local. Deterministic. | |
| Horosa Skill horace-maxwell/horosa-skill Local-first offline 术数/占星 (Horosa 星阙): 114 technique tools, all computed on your machine. | |
| io.github.horizon-pulse/horizon-pulse horizon-pulse/horizon-pulse 28 agent tools via x402: crypto data, tx checks, web fetch. MCP pays Base USDC; HTTP adds 3 rails. | |
| Horizon Brand Authority MCP horizonmedia/horizon-brand-authority-platform Grounded Horizon Media brand Q&A for AI assistants. Authenticated MCP; brand_authority_query. | |
| IRL Gateway horkos-labs/irl-gateway An AI agent's trading mandate it can't break: checked before every order, reasoning sealed in IRL. | |
| Harie hosshan/harie Annotate screenshots for user guides. Saved as plain JPEG/PNG whose annotations stay editable. | |
| HotelsCasa hotelscasa/hotelscasa-mcp Travel search: 1.3M hotels and apartments, owner homes, tours, flights, taxi, car rental. | |
| Kulturbase houshuang/kulturbase Search and discover currently playable Nordic cultural recordings. | |
| BAMF.ai houstongolden/bamfaiapp LinkedIn and X content, scheduling, analytics and outreach agent for founders, via your BAMF login. | |
| MotiBlog hovernotes/motiblog Agent-first SEO research and publishing: competitors, SERPs, internal links, and Search Console. | |
| com.usefreebox/freebox howdamain/freebox-mcp Find free stuff near any US ZIP, priced for resale. Live listings, resale estimates, alerts. | |
| Agent Surface howells/agentsurface Search and read the Agent Surface guide to making websites, apps, APIs and CLIs work with AI agents. | |
| Howseen howseen-ai/howseen-mcp How ChatGPT, Gemini, Perplexity and Google AI name your brand, cite sources and rank rivals. | |
| gen-system Understand hpdkhoa/gen-system Parser facts about a codebase: architecture, call graphs, control flow, effects, beliefs | |
| io.github.hrandhawa02/squad_up hrandhawa02/squad_up Create events, add invitees, manage potlucks and carpools via natural language. | |
| Kristo Intelligence hristovdimitri2-hub/kristo-intelligence-6 Pay-per-call DeFi intelligence for AI agents on Base — x402, USDC, no keys. | |
| hrva.cc hrvalabs/url-shortener Create, list and check hrva.cc short links and read their click statistics. | |
| com.pantryaide/pantry-aide hsearcy/pantry-aide-mcp AI meal plans that fill your Kroger/Instacart cart - pantry-aware lists, all from chat. | |
| HSM Kit hsm-kit/hsmkit Local-first Base64, Luhn, key-component XOR, and synthetic ISO-0 PIN block tools. | |
| com.htagai/htag-docs htag-analytics/htag-mcp Public HTAG discovery for MCP tools, API endpoints, OpenAPI ops, and agents. | |
| HTML/CSS to Image API htmlcsstoimage/agent-plugins Generate images and PDFs from HTML/CSS, live websites, and reusable templates. | |
| Edgar & Edgarette: SEC Filing Boards huanggoodmanagency/filing-boards SEC filing boards and actuarial checks: companies, portfolios vs insurers, reinsurers, cash records. | |
| China NMPA Medical Device Data huangjunsong404-crypto/agentdata-api Structured China NMPA UDI data for AI agents: devices, registrants, models and registration numbers. | |
| OctoCounts MCP Server huanglizhuo/octocounts Analyze and compare public GitHub repo line counts (SLOC) via OctoCounts, from any MCP client. | |
| HelioSPICE huangzesen/heliospice Spacecraft ephemeris made easy — auto-managed SPICE kernels for heliophysics | |
| HuaweiCloud DevKit (Community Preview) huaweicloud/huaweicloud-devkit Community preview of HuaweiCloud DevKit MCP server (official: io.github.huaweicloud) | |
| HubTub Pulse: YouTube Analytics hubtub-io/youtube-mcp Your YouTube channels’ private analytics for AI assistants: revenue, views, retention. Read-only. | |
| Arc hudsonkit/arc Author, validate, lay out, render, and diff architecture diagrams as code. | |
| Pointcast hugelidus/pointcast Talk and Alt+click on your web app: your agent gets the exact elements and the code behind them. | |
| io.github.hughhan1/mysql hughhan1/mysql MySQL statements and transactions over MCP | |
| Space hugo-sequier/getspace One shared memory for all your AI agents: documents, tasks, databases and memories in one workspace | |
| Likelyread hugo-sequier/likelyread Email open tracking for agents: add a pixel, register the send, read back who opened it | |
| Stratta hugogebel-boop/stratta-v2 Your organization’s norms and reference documents (standards, laws), cited to the section and page. | |
| HUMAN API human-api-labs/human-ai Human execution API for AI agents needing voluntary help with physical-world tasks. | |
| MTA API humaninterfacedesign/mta-api Live NYC-area transit: subway, bus, PATH, NJ Transit, LIRR, Metro-North, NYC Ferry, Citi Bike. | |
| io.github.humanity4ai/project-human humanity4ai/project_human 9 humanity skills for AI agents — crisis detection, WCAG 2.2, empathy, cultural sensitivity | |
| Tradehand humanleap/tradehand-claude-plugin Browse and book local tradespeople in the UK. | |
| io.github.HumanLineage/wt humanlineage/wt Human Lineage MCP server — search and query the public genealogical graph of all humanity |
23,851–23,900 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.