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 |
|---|---|
| Testorim AI browser tests from your coding agent: a verdict, failing steps, report, video and trace. | |
| Textavia MCP Local-first MCP server for text, JSON, Base64, CSV, regex, and developer utilities. | |
| TheDesignAgent A design agent in your coding agent's loop: briefs each screen, reviews UX and visual quality. | |
| com.thehikingworld.www/mcp Sourced trail facts. Tiers verified-official, reported-secondary, or unverified. Gaps stay empty. | |
| ai.thrain/spotlight Local PDF accessibility audit: machine-checkable PDF/UA basics (ADA/EAA/508). No uploads. | |
| ThunderPhone Build, test, deploy and run AI phone agents: agents, numbers, calls, tests, knowledge, campaigns. | |
| Tickory MCP Tickory MCP server for Binance scans, alert events, and explainability. | |
| Toggl 2.0 Toggl 2.0 MCP server for tasks, projects, time entries, and workspace operations. | |
| net.topicforge/mcp Generate programmatic SEO articles, topic clusters, FAQ schema, and batch jobs via TopicForge. | |
| TradeAlmanac TradeAlmanac market data: dividends, screener, sentiment indicators, calendar effects, stock lists. | |
| com.transcriptdock/mcp YouTube and TikTok transcripts: get_video_transcript in one call, jobs, exports, video discovery. | |
| ai.unpaper/cli Slide decks locally: templates, checks, HTML to editable PowerPoint, .pptx rescue. No AI inside. | |
| unstringify Fix broken JSON by line, validate, convert, read CSV/NDJSON/logs as records, unpack, compare. Local. | |
| DPX — Settlement & Intelligence for AI Agents Compliance-gated stablecoin settlement + x402 macro/ESG/climate intelligence for agents. 115 tools. | |
| agentrace Structured observability for AI agents. Trace steps, decisions, and errors. MCP server + CLI viewer. | |
| url2md PDFs, JavaScript pages and ordinary HTML as clean Markdown. Follows robots.txt per RFC 9309. | |
| io.github.getrelove/solve Cloudflare Turnstile CAPTCHA solver for AI agents. $0.002/call, 100 free on signup. P95 2.2s. | |
| io.github.codevanmoose/vanmoose-mcp-server Up to 216 tools, including 8 Truncus email tools. Each service runs on its own API key. | |
| varg.ai Generate video, images, speech and music with 120+ AI models and render TSX videos to MP4 | |
| Vargov®Design Vargov®Design catalogue: 605 light compositions, 3D configurator links, how to get IFC4 and FBX | |
| tech.vauban/pay-mcp x402 pay tools for MCP clients, plus a `buy` command: read the offer, consent, pay. Starknet, Base. | |
| VideoVector MCP Server Model Context Protocol server for the VectorMethods VideoVector media intelligence API. | |
| vetkit Audit repos for security, code quality and AI code risks; read findings and open fix PRs. | |
| io.github.ohad6k/viberaven Checks a Vercel + Supabase repo before deploy: RLS, grants, leaked keys, webhooks. Runs locally. | |
| io.github.pinz-byte/herald-vehicle-auction VMC Peru auctions, AVT valuations and SubasBlog guides for buyers and sellers of idle assets. | |
| Vocaless Remove vocals from local audio files and transpose instrumentals through Vocaless. | |
| Voidly Internet censorship data, Sentinel forecasts and agent relay tools; relay keys stay in a local file. | |
| dev.wagate/wagate Read WhatsApp chats and groups, and send messages when allowed, through the WaGate API. | |
| Wahlu Social media for you and your AI agent: Instagram, TikTok, YouTube, X, Bluesky, Telegram and more. | |
| WarmySender AI-agent outreach: cold email, warmup, LinkedIn, Instagram, WhatsApp, verification, 200M leads | |
| com.weavori/mcp Generate referentially intact, distribution-realistic PostgreSQL synthetic data from AI assistants. | |
| Webeyez MCP Webeyez MCP: Access UX session replays, conversion funnels, errors, and performance diagnostics. | |
| Wensity Find, plan, and install Wensity UI React components and blocks into your project. | |
| io.github.x-tkn/x-tkn-mcp Lets an AI agent hand a secret to a person as a one-time link, with no way to read it back. | |
| tech.xns/relayer Conversationally set up & manage an XNS Relayer over stdio: install, claim, VPD, S3, backups. | |
| XPmetric Ask your AI about your site's traffic, channels, revenue, goals and funnels (XPmetric analytics). | |
| xStocker Build buy/sell orders for tokenized US stocks (xStocks) on Solana. Non-custodial. | |
| com.xtrinel/vaast Read-only access to VAAST vulnerability scan findings, workspaces, and targets for AI agents | |
| io.github.YawLabs/mcp MCP gateway: one local install fronts every MCP server for Claude Code, Cursor, and VS Code. | |
| io.github.YawLabs/mcph mcp.hosting — one install, all your MCP servers, managed from the cloud | |
| io.github.YawLabs/nol-mcp nol MCP server -- search, cited Q&A, and pages over your team's knowledge base | |
| io.github.YawLabs/vew-mcp Browser MCP: drive a real Chromium via Playwright with compact ref-addressable page snapshots | |
| com.zeroheight/zeroheight Connect AI assistants to zeroheight styleguides using the Model Context Protocol | |
| plcsense Read-only TwinCAT ST intelligence: resolve symbols, library APIs, docs, validate PLC code. | |
| io.github.zyf8827/tern Model Context Protocol (MCP) server for Tern E2E testing platform | |
| coffee.402/mcp Trust layer for agent payments (x402, Base): verify agents, risk scores, signed escrow verdicts. | |
| AccessibilityBrief Find WCAG 2.2 accessibility issues on your website, get the exact code fix, and rescan to confirm. | |
| ActAs Persistent identity, email, saved accounts and scoped credentials for AI agents. | |
| Aditum Read industrial data sources, pipelines, data-health incidents and datasets in Aditum. | |
| af360 Watches your local projects and sites read-only and names what would be lost. |
46,251–46,300 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.