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 |
|---|---|
| Canary MCP osauer/canary Read-only IBKR MCP: account, positions, brief, regime, stress, reporting, Edge, and risk. | |
| Reelsaw osbytes/reelsaw Drive a self-hosted Reelsaw: turn long videos into vertical clips, edit, re-render and export them. | |
| io.github.oscal-compass/compliance-trestle-mcp oscal-compass/compliance-trestle-mcp An MCP server that provides tools to author OSCAL security compliance documentation | |
| Anamnesis oscardvs/anamnesis Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git | |
| chartlink-mcp oscarleoo/chartlink-agents Enables agents to create, preview, and publish charts and tables with live-updating embed links using the chartlink API. | |
| io.github.oscarlopez-gif/ai-model-lifecycle-index oscarlopez-gif/ai-model-lifecycle-index Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited. | |
| io.github.oscarlopez-gif/ai-vendor-data-trust-index oscarlopez-gif/ai-vendor-data-trust-index Source-cited data-handling comparison of 11 AI vendors: training, retention, opt-out. | |
| io.github.oscarlopez-gif/argentina-price-index oscarlopez-gif/argentina-price-index Daily Argentina food & beverage price index, source-cited from public retailer prices. | |
| Quash — Mobile App Automation oscorp-hq/quash-mcp-releases Drive Android & iOS mobile-app automation from your AI agent on locally connected devices. | |
| WhaleScope MCP osindo-dev/whalescope-mcp Binance Futures market intelligence: funding, OI, order book, klines, cross-exchange comparison. | |
| Code Declaration Lookup MCP Server osinmv/function-lookup-mcp Enables full-text search for code declarations across multiple languages using SQLite FTS5 and universal ctags, allowing users to search for functions, classes, and other code elements. | |
| OSINT.SX osintsx/osintsx-mcp Search an email, phone, username or name across every OSINT.SX source, plus account history tools. | |
| OSIR Domain Registrar osir-inc/mcp-a2a Register, renew, transfer, and manage domains, DNS, VPS, and email with 106 tools. By OSIR. | |
| FreeStyle Libre (LibreLinkUp) osjayaprakash/freestyle-libre-mcp Read-only FreeStyle Libre CGM glucose readings, graphs and logbook via LibreLinkUp | |
| Oura Ring osjayaprakash/oura-ring-python-mcp Read-only Oura Ring sleep, readiness, activity, stress and heart rate data (OAuth2) | |
| periscope oskar-szulc/periscope A real Safari-engine (WebKit) browser for agents on macOS: sessions, extraction, bot checks. | |
| domain-suite-mcp oso95/domain-suite-mcp domain-suite-mcp is an MCP server that gives AI agents full autonomous control over the domain lifecycle. From checking availability and registering domains to managing DNS records, SSL certificates, and email authentication across Porkbun, | |
| deeplook osojdjd/deeplook Researches any company in ~10 seconds using 10 data sources. Returns structured reports with bull/bear verdict for stocks, crypto, and private companies. | |
| KeyNeg MCP Server osseni94/keyneg-mcp Enterprise-grade sentiment analysis tool for AI agents, enabling sentiment labeling, keyword extraction, and batch analysis via MCP. | |
| plonk-mcp ostapondo/plonk Mac window manager AI agents can drive: see every monitor and window, apply multi-monitor layouts in one call, save and relaunch whole workspaces, snap zones, keep-awake, and annotated screenshots. Backed by a native macOS menu bar app over | |
| Bruno MCP Studio ostico/bruno-mcp-studio Author, edit and run Bruno collections as files: HTTP, WebSocket, gRPC, per-request pass/fail. | |
| aboard ostin-pil/aboard Falsifiable claims about systemic problems: causal graph, forecasts, dossiers. | |
| skill4agent MCP Server osulivan/skill4agent-mcp-server MCP (Model Context Protocol) Server for skill4agent - Search, view, and install AI skills in AI conversations. | |
| osu! MCP osyanne/osu-mcp MCP server exposing the osu! API v2: player stats, scores, beatmap search, rankings. | |
| io.github.OtherVibes/mcp-as-a-judge othervibes/mcp-as-a-judge MCP as a Judge: a behavioral MCP that strengthens AI coding assistants via explicit LLM evaluations | |
| Otis otisbase/otis-mcp Free client billing for AI assistants: hours, expenses, timers, invoices and payments. | |
| io.github.AlexAlves87/otskit-mcp otskit/otskit-mcp Stamp, upgrade, and verify Bitcoin timestamps via AI agents. No API keys required. | |
| SQLX ottermind/sqlx Run SQL on 30+ databases through saved, encrypted connections; credentials stay local. | |
| SVG Lab ottoman9/svglab-mcp SVG Lab MCP: the Design Engine for AI. App screens, icons, illustrations and charts as SVG. | |
| Ottogeo — CAD MCP Server ottonic/cad-mcp-server Measure STEP CAD files with your AI assistant: walls, clearances, draft, and revision diffs. | |
| Ottorev — Review MCP Server ottonic/review-mcp-server Durable review context for CAD: entity names, notes, tags, and revision-bound decisions. | |
| Ottosim — Simulation MCP Server ottonic/simulation-mcp-server Thermal, structural, modal, DC, and laminar-flow studies from STEP via Gmsh and Elmer. | |
| Ottoref — Standards MCP Server ottonic/standards-mcp-server ISO 286 limits and fits, ISO 2768 tolerances, material properties, and process limits. | |
| io.github.ouestcharlie/ouestcharlie-woof ouestcharlie/ouestcharlie-woof An MCP server and app to search and browse your photos while preserving your privacy | |
| OurPay Wallet ourpay/ourpay-wallet Crypto wallet for AI agents: balances, payments, swaps and trading with owner controls. | |
| FoundersOS ourthinktank/founders-os Give your AI the full context of how your business runs: CRM, finances, tasks, and memory in one self-hosted MCP server." Short + long descriptions lead with cross-domain reasoning ("which customers are behind on payment and what did we las | |
| OutcomeCI outcomeci/mcp-server Create, validate, and manage agent-powered workflows with OutcomeCI. | |
| outcometick outcometick/outcometick-sdk-ts Polymarket and Predict.fun historical tick data, plus backtest quotes and status, over MCP | |
| Outcrawl outcrawlai/outcrawl-mcp Web infrastructure for AI agents: scrape, crawl and search the web, run browsers and agents. | |
| ScreenWeaver outerframe-studio/screenweaver-mcp Screenplay and storyboard in your AI assistant: import scripts, edit scenes, build shots. | |
| Outil.io outil-io/outil-mcp All-in-one marketing for entrepreneurs: sites, sales funnels, CRM, email, WhatsApp, courses, shop. | |
| Outscraper MCP Server outscraper/outscraper-mcp-server Outscraper MCP business discovery, Maps intelligence, enrichment, reviews, and contact data. | |
| Outset outset-ai/outset-mcp AI-moderated research platform: create and launch studies and query interview results. | |
| io.github.OV3RK177/kairos-signal ov3rk177/kairos-mcp-server Provenance-first DePIN telemetry: 331 live networks + 129 Bittensor subnets, 10,508 series. | |
| TriliumNext (trilium-mcp) ovden13/trilium-mcp Read and write a self-hosted TriliumNext knowledge base over its ETAPI. | |
| io.github.overstarry/qweather-mcp overstarry/qweather-mcp a qweather mcp server | |
| io.github.overtimepog/CloakMCP overtimepog/cloakmcp Stealth browser MCP server — anti-detection Chromium with snapshot-first agent interface | |
| io.github.oviron/openrouter-admin oviron/openrouter-admin-mcp MCP server for OpenRouter management API: credits, key CRUD, activity drill-down, dashboard. | |
| SeenRelay ovladon/seenrelay Avoid redundant expensive validation. CHECK recent evidence; OBSERVE fresh independent results. | |
| onomeo owaid0723666/onomeo-mcp Ask free LLMs (DeepSeek, GLM, Gemini, Mistral) for a second opinion from any MCP client. |
14,301–14,350 of 115,409
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.