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 |
|---|---|
| tokcalc MCP Server stevecrates489-commits/tokcalc LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost. | |
| videoFn stevejhiggs/videofn-mcp Video editor for your AI assistant. Builds, checks and renders edits on your Mac. | |
| Hiveround stevemilton/hiveround Marketplace MCP server for live venture-capital raises and agent-mediated dealflow. | |
| app.homotope/homotope stevenroman91/homotope-engine Vectorize images to SVG, PDF, EPS or DXF, and check a DXF before cutting. | |
| Launchpad HQ stevensonzj-ai/launchpad-hq Read-only, sourced and dated facts on AI tools: search, compare, pricing, free alternatives. | |
| Dubai Diligence stevenworlow/dubai-diligence-mcp Dubai Land Department prices, rents and yields by building, with ready and off-plan split out. | |
| MedXpert Regulatory Hub stevenzhao07/medxpert-reg-hub Read-only medical device regulatory data: NMPA UDI, FDA 510(k)/PMA/classification lookups. | |
| io.github.Steveser1989/opc-mcp-server steveser1989/main-my-opc-system OPC Suite — CRM, sales, inventory, accounting, HRM, payroll, claims, projects from any AI agent. | |
| io.github.steveweltman/4q-tokenz steveweltman/4q-tokens Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call. | |
| LokalBot stevyhacker/lokalbot Opt-in, read-only meeting and screen memory. Requires the LokalBot Mac app. | |
| Sthayi sthayi-ai/sthayi Local-first AI memory over MCP. No account; you own the store. | |
| io.github.stillmarcus24/stillos-kya stillmarcus24/stillos-kya Counterparty due-diligence infrastructure: OFAC screening, on-chain risk, signed verdicts. | |
| com.stimulsoft/docs stimulsoft/mcp-docs-server Stimulsoft Reports & Dashboards docs MCP server. Semantic search for all platforms. | |
| Stock Compass stock-compass/stock-compass-plugin Watchlist, signals, trades and journal for HK, US and China A-share stocks. Records only; no orders. | |
| Writing Clinic stockandawe/make-your-point Free MCP tool: paste your writing, get a one-line diagnosis and a tightened rewrite. | |
| OptionsBell Options Flow stockmarketscan/optionsbell-mcp Unusual options activity on 7,000+ US stocks: top prints, streaks, IV rank, sentiment, sectors. | |
| Unswell stokaro/unswell Offline self-checking to reduce AI-style wording in source code and documentation. | |
| io.github.stolarubrendang/tradar stolarubrendang/tradar Real-time market catalysts from 50+ primary federal sources, AI-classified for traders. | |
| StackSwap stonesofcreation/stackswap-mcp B2B GTM stack intelligence: search ~400 tools, compare vendors, find overlaps, audit SaaS spend. | |
| Stoory Hire Specialist stoorygitserver/stoory-mcp-server Find and hire a human specialist from the Stoory marketplace, right from chat. | |
| Stophy stophydotdev/stophy Give your agents the live web. | |
| StoriesIG Instagram MCP Server storiesig-info/instagram-mcp View and download public Instagram posts, reels, stories, highlights, followers, comments, no login | |
| Storybook MCP Addon storybookjs/mcp Help agents automatically write and test stories for your UI components. | |
| Agentzia stoyan-stoyanov/agentzia-plugins Test how AI assistants recommend your product and improve your landing page with evidence. | |
| Straight Line Golf Pro straightlinegolfpro/straight-line-golf-pro-mcp Read-only discovery and retrieval of current public Straight Line Golf Pro coaching resources. | |
| io.github.strangeadvancedmarketing/adam-framework strangeadvancedmarketing/adam Persistent memory tools for Claude Desktop. Search your vault or Obsidian notes mid-conversation. | |
| url-to-pdf strayly/url-to-pdf Convert public web pages to PDF, images, Markdown, or JSON using one API key. | |
| Quillm streamfog/quillm-plugin Dashboards, trackers and docs your agents build and keep current. Your team reads them by link. | |
| Streamkap streamkap-com/streamkap-mcp Streamkap CLI & MCP server - manage CDC pipelines, sources, destinations, and transforms | |
| Streamlivr streamlivrapp/streamlivr-x402-celo Access African & global creator profiles, music metadata, and posts via x402 on Celo. | |
| Stream Vessel streamvessel/ai-integrations Browse, upload, download, copy, move and share files in your own S3-compatible buckets. | |
| String Utility Belt string-utility-belt/string-utility-belt MCP server exposing String Utility Belt's utilities and pipelines as tools for AI agents. | |
| io.github.stringsofthemind-oss/once stringsofthemind-oss/once Developer assessment/setup MCP; admitted Once boundaries protect writes, not sibling connectors. | |
| com.stripe/mcp stripe/agent-toolkit MCP server integrating with Stripe - tools for customers, products, payments, and more. | |
| io.github.strontian/tidyvid strontian/tidyvid Remove background noise/echo from video and add captions (SRT/VTT or burned-in MP4). | |
| io.settlemesh/cli structureintelligence/settlemesh Deploy and monetize agent-built apps: login, database, usage billing, and end-user-pays. | |
| Strutter AI strutterai/strutterai AI-powered RFP response management. Search Q&A libraries, draft responses, and upload documents. | |
| io.github.Studio-Moser/shelbymcp studio-moser/shelbymcp Knowledge-graph memory server for AI tools via MCP | |
| Calligraphy Maker by Studio99 studio99-app/calligraphy-mcp Exact Hindi, Marathi, Gujarati and English calligraphy as editable artwork, from real fonts. | |
| ai.gency/gency-lite studiolab-dev/gency-lite Generate Amazon-style A+ Content and AI product images from product photos. | |
| ai.gency/gency-mcp studiolab-dev/gency-mcp Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code | |
| mcp-armor studiomeyer-io/mcp-armor Security sidecar for MCP servers: 11 read-only control-plane tools for prompt-injection checks. | |
| MCP Hook Conformance studiomeyer-io/mcp-hook-conformance Audits MCP servers for Claude Code mcp_tool hook readiness: idempotency, latency, side-effects. | |
| MCP Server Attestation studiomeyer-io/mcp-server-attestation Ed25519-signed MCP tool manifests + spawn attestation. Layer-2 supply-chain hardening. | |
| MCP stdio ShellGuard studiomeyer-io/mcp-stdio-shellguard Defense-in-depth for MCP stdio servers: shell-injection guard, AST audit CLI, RCE blocking. | |
| StudioMeyer MCP Suite studiomeyer/mcp-suite 8 MCP servers, 104+ tools: memory, social, PDF, email, images, calendar, scheduler, files. | |
| AI Stupid Level studioplatforms/aistupidlevel-sdk LLM benchmark rankings, drift status, incidents and Smart Router previews from AI Stupid Level. | |
| io.github.StudiousXiaoYu/oracle-link studiousxiaoyu/oracle-link Oracle MCP Query Server (Node.js) - Read-only SELECT via MCP | |
| Yandex Direct MCP stufently/yandex-mcp MCP server for Yandex Direct API v5 — campaigns, ads, keywords, reports | |
| Yandex Metrika MCP stufently/yandex-mcp MCP server for Yandex Metrika API — web analytics, traffic, audience data |
49,251–49,300 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.