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.hengkp/rtcf hengkp/rtcf-mcp Turns rough requests into sharp Role/Task/Context/Format prompts. Thai and English. | |
| runiji henriknh/runiji Connect to runiji and access your runs, run details, training statistics and more. | |
| Epivo Course Catalog henrikthome-arch/ai-tutor Read-only access to Epivo's live course catalogue for AI agents. | |
| SparkForge — 20+ Utility APIs with x402 Micropayments henry-ships/sparkforge 20+ pay-per-use APIs: image gen, crypto data, email verify, SSL check, web scraping, and more. | |
| 黑123 Hackathons henryagentteam/hack123 Read-only search of hackathons, team-up posts and projects on 黑123 (hack123.henryht.sh), zh/en. | |
| Close API henryspatialanalysis/wtm.api Walk, bike, and transit travel times from every US census block to nearby amenities. | |
| ChaTodo heristop/chatodo ADHD-friendly task management MCP server for ChaTodo: organize tasks, lists, and priorities. | |
| LeClap heristop/leclap Compose and render video from one JSON template. Deterministic, runs locally, no generative model. | |
| io.github.hermai-ai/hermai-cli hermai-ai/hermai-cli Hermai MCP server — look up, submit, and classify website API schemas from any MCP client. | |
| Hermes Prime hermes-labs-ai/hermes-prime Read-only stdio MCP server for a versioned convention card in Claude Code. | |
| Synthex Forge — x402 Paid Agent Services hermeschoosenone-debug/synthex-x402 Paid agent services settled in USDC on Base via x402. Signed, verifiable, and free to verify. | |
| Hermit CRM hermit-crm/hermit-crm A local CRM as Markdown files in git: read and update pipeline, contacts and interactions. | |
| io.github.hermitsh-ai/shrimp hermitsh-ai/shrimp Task manager for AI agents. Zero setup, nested trees, batch ops, local-first storage. | |
| costwright — agent budget analysis hernaninverso/costwright-mcp Static worst-case token-budget analysis for LLM-agent workflows + signed budget certificates. | |
| Solk CRM hesap/solk-mcp Solk CRM for Claude: accounts, pipeline, visits, quotes, orders and tickets with your permissions. | |
| 1NFER Inference Discovery hesoyambusiness/1nfer-agent-tools Inspect 1NFER models, crypto funding terms and task cost without keys or paid calls. | |
| io.github.heungmangoo-art/saju heungmangoo-art/saju-mcp-server Korean Four Pillars (Saju) astrology — birth charts, Day Masters, Five Elements, compatibility | |
| io.github.HewlettPackard/greenlake-audit-logs-mcp hewlettpackard/gl-mcp HPE GreenLake audit-logs MCP Server | |
| Siren hexahedral-inc/siren-mcp Deterministic visual marketing engine. Your agent plans, renders, and posts on-brand campaigns. | |
| xSkill AI hexiaochun/xskill-ai-cursor-plugin AI content generation with 50+ models: image, video, TTS, voice cloning, and more. | |
| Juno AI Customer Research hey-juno/juno-agent-toolkit AI-moderated qualitative customer interviews, study authoring, participant links, and CSV exports. | |
| HEY Research Lab hey-research-lab/hey-research-open Evidence-backed Robinhood Chain research: builders, ships, contracts, changes, market context. | |
| Spain Legal by Legal Fournier heyalerio/legalfournier-spain-legal-mcp Spain legal screening, articles, videos, interactive apps, public skills, and consent-based contact. | |
| ThumblifyAI heyalizaid/thumblifyai-plugin Create and refine AI YouTube thumbnails with the ThumblifyAI MCP server. | |
| Spin Wheel Names heyiamluke/spinwheelnames Spin a random picker wheel, pick a random number, and search shared wheels from spinwheelnames.com. | |
| com.puter/mcp-server heyputer/puter Puter MCP enables AI tools to interact with Puter: manage files, websites, workers, and more | |
| HeySale — AI Website Salesperson heysale/heysale-mcp Create and install an AI Website Salesperson for sales, qualification, and lead capture. | |
| Heystack heystack-hq/heystack-plugins Observability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts. | |
| com.heyzarvis/zarvis heyzarvis/zarvis-releases Your task queue, executed by AI on your own computer. Manage and approve from any MCP client. | |
| io.github.HeyZod/fylings heyzod/fylings Search, verify & screen 1M+ African companies + their government contracts across 18 registries. | |
| Mansa African Financial Reference Data heyzod/mansa-african-identity-mcp African bank & SWIFT codes, NUBAN resolution, mobile networks, holidays and ISO 4217 currencies. | |
| io.github.hezeclark/devkits hezeclark/devkits-mcp 12 local developer tools: JSON, Base64, JWT, regex, hash, UUID, Markdown, diff, cron. | |
| io.github.heznpc/iconnect heznpc/iconnect MCP server for the entire Apple ecosystem — 123 tools across 14 modules. macOS only. | |
| PokerData hft-studio/pokerdata-mcp GTO poker solver data: NLHE/PLO preflop ranges, postflop strategy, EV. 6-max NL preflop free. | |
| US Macro hgus107/us-macro-mcp US macroeconomic data from FRED: inflation, employment, growth, housing, rates, recession signals. | |
| DocsMint hiai-gg/docsmint Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools. | |
| Username Inspector hickworks/username-inspector-mcp Look up username availability on 12 resale platforms (links where blocked); compare seller fees. | |
| Duo Data Utilities: IBAN, ISIN, VAT and Tax ID, Barcode, Timezone, Geo APIs hiesem/duo-data-utilities IBAN, ISIN, VAT/tax ID, GTIN validation; timezone, geo, text, chain utilities. Pay per call | |
| FFMPEG API hifarrer/ffmpegapi-agent-docs Hosted MCP tools for FFmpeg-style video and audio processing through FFMPEG API. | |
| Archytan Lite MCP gate high-archytech-solutions/archytan-mcp-gate Puts an MCP tool server behind Archytan Lite: each tool call is authorized and spent before it runs. | |
| love.letsvibe/vibe highestvibrations/vibe-landing Discover wellness practitioners, events, communities, and modalities through Let's Vibe. | |
| EdgeBook highlydubious/edgebook-mcp Chart-first trading journal: log trades from notes or chart screenshots, review setups and stats. | |
| lu.hike/hike-lu-mcp hikelu/hike-lu-mcp Luxembourg hikes, trails, walks, outdoor events in Luxembourg City, Vianden, Mullerthal. | |
| Archform himanshu-mamgain/archform Render and validate diagrams as code: Mermaid, PlantUML, C4, Graphviz, D2 and more. | |
| Posy himanshu-sangshetti/posy Make and edit a hand-made link-in-bio page: add links, pick a look, publish. | |
| io.github.himorishige/hatago-mcp-hub himorishige/hatago-mcp-hub Unified MCP Hub for managing multiple Model Context Protocol servers | |
| Bestie Check hirebestie/bestie-check Document reasoning checks: a helicopter view of claims and assumptions before handoff. | |
| HireSeeker hireseeker/hireseeker-mcp Поиск IT и Digital вакансий HireSeeker. Без регистрации. Пять инструментов только для чтения. | |
| io.github.Hiroshi-Ichiyanagi/kagami hiroshi-ichiyanagi/kagami Deterministic prompt-injection detector; signed, offline-verifiable verdicts. Not an LLM. | |
| Postage.lk hiruagain/postage.lk Sri Lanka Post postage, COD fees, post office lookup and prohibited items for international mail. |
23,751–23,800 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.