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.stayce/shortcut-mcp stayce/streamshortcut-cloudflare Shortcut project management. Create, update, search stories and manage workflows. | |
| Hotel & Vacation Rental MCP - live prices & reviews across Booking, Airbnb, Vrbo & Google Hotels stayingapi/hotel-vacation-rental-mcp Search hotels & rentals: live prices & reviews across Booking.com, Airbnb, Vrbo & Google Hotels. | |
| com.stayker/1stay stayker-com/1stay-mcp Hotel booking MCP server. Search, book, and manage reservations across 250K+ properties worldwide. | |
| What's Allowed stcmain/whats-allowed-mcp Merged agent permission rules: which settings file wins, and which rules your client ignores. | |
| What's Inherited stcmain/whats-inherited-mcp What a checkout tells your agent to do: instruction files, hooks, declared MCP servers. | |
| What's Loaded stcmain/whats-loaded-mcp What fills your agent's context window before a session starts: skill descriptions, memory files. | |
| What's Running stcmain/whats-running-mcp Ground truth for agent fleets: live agent sessions, listening ports, daemons, system load. | |
| io.github.ste7/novacal-mcp-server ste7/novacal-mcp-server Manage Novacal event types, availability, and bookings. | |
| Steadyfetch actors on Apify MCP steadyfetch/steadyfetch-agent-tools Apify MCP pinned to 30 Steadyfetch actors: ad, video and audio transcripts, trends, jobs, Amazon | |
| SEO Data MCP (SteadyScrape) steadyscrape/seo-data-mcp Keyword volume, live SERP ranks, domain traffic, ranked keywords, backlinks, Google Trends, YouTube. | |
| Steep steephq/steep-mcp Query metrics, targets, entities, and team data in your Steep workspace via MCP. | |
| mite stefan39/mite-mcp-server mite time tracking: server-side reports, time entries, master data. Read-only by default. | |
| EduPage Keyring stefanbackor/edupage-keyring-mcp EduPage timetables, grades, homework and messages; session in the OS Credential Store, no password. | |
| MikroTik RouterOS stefanknol/mikrotik-mcp MikroTik RouterOS over the binary API, addressing rules by real .id not list position. | |
| io.github.stefanoamorelli/fred-mcp-server stefanoamorelli/fred-mcp-server Federal Reserve Economic Data (FRED) MCP Server - Access all 800,000+ economic time series | |
| Nasdaq Data Link MCP Server stefanoamorelli/nasdaq-data-link-mcp Enables LLMs to access Nasdaq Data Link's financial datasets via natural language, providing tools to search, retrieve, and export data. | |
| io.github.stefanoamorelli/sec-edgar-mcp stefanoamorelli/sec-edgar-mcp SEC EDGAR MCP server that provides access to the US public filings through the US SEC EDGAR API | |
| RLM Tools stefanoshea/rlm-tools Persistent Python sandbox for token-efficient codebase exploration in MCP clients | |
| SaveSaveSaveSave stefantsezarov/savesavesavesave Read-only safety checks before an agent acts: scan untrusted text for prompt injection and phishing (locally), check npm packages for malware, hijacked releases and typosquats, scan crypto addresses and tokens, and compare two addresses to | |
| Stelar Signals stelardigital/stelar-signals-mcp Crypto market signals and portfolio telemetry. 6 tools pay-per-call in USDC, no API key. | |
| io.github.StelaSpace/stelaspace-mcp stelaspace/stelaspace-mcp Publish AI-generated HTML (dashboards, reports, docs) to permanent, sandboxed, shareable links. | |
| io.github.stelis-dev/agent-q stelis-dev/agent-q Local MCP server for requesting signatures from Agent-Q Firmware. | |
| Presso stellagent/presso-setup Connect e-commerce and marketing data to AI assistants via MCP. | |
| CCPhoto — Phone Camera Bridge stepankaiser/ccphoto Phone camera bridge for Claude Code — photos, live video, voice, and generative UI | |
| io.github.sterion66/godot sterion66/godot-mcp-server The most complete Godot 4 MCP: secure sandbox, 40+ tools (projects–runtime), major MCP clients. | |
| Metro MCP steve228uk/metro-mcp MCP server for React Native/Expo runtime debugging, inspection, and automation via Metro/CDP | |
| OmniFocus steveardis/omnifocus-mcp Full CRUD MCP server for OmniFocus via Omni Automation — tasks, projects, folders, tags, recurrence. | |
| Pixie Vacations Travel Booking stevegriswoldatl/pixie-vacations-mcp Book Sandals, Beaches, and cruises through Pixie Vacations with co-branded booking URLs. | |
| shiply — Static Site Hosting & Deployment stevejford/shiply-mcp Instant web hosting for AI agents. Publish a live site in one call, no account needed. | |
| Touchline Wire — FPL & Premier League Intelligence steven-robinson/touchlinewire-mcp Zero-auth FPL expected minutes, captains & transfers, plus Premier League lineups & stats. | |
| Homechecker Guides steven3265/homechecker-guides-mcp Homechecker's professionally authored Australian homebuyer guides: search, cite, build checklists. | |
| io.github.stevenvo/slack-mcp-server stevenvo/slack-mcp-server Read Slack conversations, threads, user info, and search messages from your MCP client. | |
| Graph-Memory stevepridemore/graph-memory Self-hosted personal knowledge graph for Claude that persists across sessions, devices, and tools. Built on Neo4j with local semantic embeddings; OAuth 2.1 lets Claude Code, Claude Desktop, and claude.ai web all hit the same graph. | |
| eterna-mcp-agent-starter stevevstd-oss/eterna-mcp-agent-starter Build AI trading agents on Eterna Hybrid Exchange (no-KYC perp DEX with flat 0.014%/0.035% fees). Works out of the box with fee estimation, venue comparison, setup guides and guarded agent prompts; add an Eterna token to bridge the official | |
| Security Recipes stevologic/security-recipes.ai Read-only CVE intelligence, remediation playbooks, and agent setup guides. Not a scanner. | |
| Canvasbin stewartmckee/canvasbin Publish HTML and Markdown pages at shareable links. | |
| io.github.Stewyboy1990/companyscope-mcp stewyboy1990/companyscope-mcp 11 company intelligence tools — financials, tech stack, competitors, patents, jobs, news. Free. | |
| io.github.Stewyboy1990/stockscope-mcp stewyboy1990/stockscope-mcp SEC EDGAR financial data for AI agents — revenue, margins, filings, company comparisons. | |
| Moth stfade/moth A debugging workflow plugin for AI coding agents. Turns terminal failures into source-backed fixes via MCP and structured skills. | |
| Tinify image tools stianlars1/tinify-mcp Compress, resize, crop, and convert images with the Tinify.dev API from any MCP client. | |
| LinkedIn MCP Server stickerdaniel/linkedin-mcp-server Enables AI assistants to interact with LinkedIn by scraping profiles, companies, job postings, and getting personalized job recommendations using authenticated browser automation. | |
| stierproducts tier lists stierproducts/mcp S-to-F tier lists for 208 product categories. Every placement cited, with barcodes. | |
| Waypoint stifler7/waypoint-mcp One chart of your projects across Claude Code, Codex, Gemini CLI, Copilot CLI, ChatGPT. | |
| io.github.stillmarcus24/stillos-edge-gate stillmarcus24/stillos-edge-gate Grade a track record before risking capital: REAL_EDGE/REGIME_LUCK/NEGATIVE_EV. Fail-closed. | |
| io.github.stillmarcus24/stillos-notary stillmarcus24/stillos-notary Signed, x402-paid StillOS notary tools: claim verdicts, OFAC screening, distress scoring. | |
| io.github.stillmarcus24/stillos-ratings-mcp stillmarcus24/stillos-ratings-mcp Check an MCP server before you install it — outside-in trust ratings for 7,000+ operators. | |
| io.github.stillmarcus24/stillos-swap-mcp stillmarcus24/stillos-swap-mcp Non-custodial Solana swap via Jupiter, 0.25% fee, free scam-check on every token you buy. | |
| mcu-debug-mcp stillsurge/mcu-debug-mcp Embedded debug MCP: serial, flash verify, fault decode, 45-pattern log analyzer, driver library | |
| apimodels stimqq/apimodels-mcp Image, video, chat and speech models with one account — local (npx) or hosted with OAuth sign-in. | |
| stipend.sh stipend-sh/stipend Non-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt. |
18,901–18,950 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.