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.tooloracle/suioracle tooloracle/suioracle SUIOracle - 12 Sui tools: objects, modules, validators, gas, Cetus DEX, NFTs. | |
| io.tooloracle/tonoracle tooloracle/tonoracle TONOracle - 11 TON tools: jettons, Telegram payments, validators, smart contracts. | |
| io.tooloracle/yieldoracle tooloracle/yieldoracle DeFi Yield Intelligence MCP — 8 tools: 19K+ pools, risk-adjusted APY, RWA yields. | |
| ai.toolprint/hypertool-mcp toolprint/hypertool-mcp Dynamically expose tools from proxied servers based on an Agent Persona | |
| Pagewatch toolshedlabs-hash/pagewatch-mcp Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup. | |
| ToolSnap MCP toolsnap-app/toolsnap-mcp Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 47 tools. | |
| com.pitbridge/pitbridge toolstackvault/pitbridge Local-first MCP bridge for NinjaTrader 8 behind a deterministic guardrail engine. | |
| perfetto-mcp-rs tooluse-labs/perfetto-mcp-rs MCP server for analyzing Perfetto traces with LLMs — query .pftrace files in PerfettoSQL via Claude Code or any MCP client | |
| PayCheck toolweather/paycheck Score merchant domain, https URL, or 0x wallet trust before an agent pays. Does not send payments. | |
| SpendGate toolweather/spendgate Score a planned spend before an agent pays. Verdicts: approve, ask_human, or block. | |
| Toolweather toolweather/toolweather MCP health (~2k servers) + API status & model deprecations (~40 APIs). One suite for agents. | |
| Upstream toolweather/upstream Is this AI/dev API down? Is this model deprecated, what replaces it? Live status for ~40 APIs. | |
| facturolia-mcp toomasgutman-blip/facturolia-mcp Read and check European e-invoices (Factur-X, ZUGFeRD, XRechnung, UBL, CII) from an AI assistant: contents in plain text plus an EN 16931 consistency check. | |
| DROS-VajraClaw top-celestial-company-ltd/dros-vajraclaw-hacker Deterministic <1µs in-band execution governance gateway and W3C DID security guardrail for AI Agent MCP tool calls. | |
| io.github.Top5StocksAPI/mcp-server top5stocksapi/mcp-server Daily AI-ranked stock, crypto, and macro research data from the Top 5 Stocks API. | |
| @topazlabs/mcp topazlabs/topaz-mcp AI image enhancement for LLMs. An MCP server that lets Claude and other AI assistants enhance images using Topaz Labs AI models. | |
| io.github.topher66/droidbar topher66/droidbar-mcp The first bar for AI. Visit, chat with SERVO the bartender, and tip in tokens. | |
| TopicForge topicforge/topicforge-mcp SEO articles that sound like your brand — not generic AI output.
TopicForge runs a four-stage pipeline — outline, draft, voice, and CTA — to turn topics into publish-ready articles with FAQ schema, meta, and editorial guardrails. | |
| io.github.TopLocalAI/layerback-mcp toplocalai/layerback-mcp Convert diagram images into fully editable Visio (VSDX), PowerPoint, draw.io, and SVG files. | |
| ScholarMuse toplocalai/scholarmuse-mcp Academic papers, reference verification and research data for AI agents. | |
| io.github.topness-msft/callwright topness-msft/callwright Self-hosted MCP voice agent that places phone calls on your behalf via Retell. | |
| io.github.topness-msft/salonrunner-mcp topness-msft/salonrunner-mcp Self-hosted MCP to find, book, and cancel salon appointments via SalonRunner. | |
| TopoLift Negotiation topolift/topolift-mcp Atom-grounded negotiation reasoning. Typed topology slot, inline citations, public dialect. | |
| tzero-mcp toprakahmetaydogmus/tzeroalgorithm Enterprise AST codebase context reduction engine with up to 95% token savings, 20 tools, polyglot support, and zero-leak security guardrails. "Toprak Ahmet Aydoğmuş" | |
| TopSMS topsms-ghb/topsms-mcp Czech SMS gateway: send and schedule SMS, OTP verification codes, delivery status and credit. | |
| io.github.ToremLabs/heuresis toremlabs/heuresis-mcp Read & write your Heuresis idea graph and run TRIZ/C-K/ASIT operators from your AI assistant. | |
| io.github.ToremLabs/proof toremlabs/proof-mcp Govern your AI coding agent: frame the work, review the changes, keep a signed decision record. | |
| io.github.toreva/kit toreva/kit Policy-checked Solana wallet actions with user-set limits, unsigned transactions, and receipts. | |
| Trestle toro-guapo/trestle Detects leaked secrets (API keys, tokens, private keys) in source code. | |
| TorrentClaw-MCP torrentclaw/torrentclaw-mcp Giving AI assistants the ability to search movies and TV shows, find torrents with magnet links, check streaming availability, and explore cast/crew metadata. | |
| io.github.toruproject/mapnetwork-mcp toruproject/mapnetwork-mcp Generate styled PNG/SVG map images of places in Japan with 11 customizable color themes. | |
| turntax torutdev/turntax Per-turn token cost of AGENTS.md, CLAUDE.md and other agent instruction files, with safe fixes. | |
| Helmdeck tosin2013/helmdeck Self-hosted MCP server: sandboxed browser, desktop, vision, code-edit packs for any agent. | |
| Entity Enricher tot-concept/mcp-server-entity-enricher Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks. | |
| Total CMS totalcms/mcpb Connect Claude to a self-hosted Total CMS site: search content, read docs, manage with an API key. | |
| ExpenseBot totesmagotes/expensebot-mcp Receipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows. | |
| ASAM ODS odsbox jaquel MCP Server totonga/odsbox-jaquel-mcp MCP server for ASAM ODS with Jaquel query tools, connection management, and data access | |
| io.github.totte-dev/vibe-provision totte-dev/vibe-provision Provision SaaS services from YAML and inject .env. Supports Clerk, Stripe, Resend and more. | |
| Model Council totti0135/model-council Consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion. | |
| Touchpoint touchpoint-labs/touchpoint Playwright for the entire OS. Give AI agents eyes and hands on any desktop app — find, click, type, and read UI elements across Linux, macOS, and Windows. | |
| Touchstone touchstone-cv/touchstone-mcp Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions. | |
| ToughTongue AI tough-tongue/toughtongue-skills Create voice-agent scenarios, pull session analytics, place SIP calls, schedule meeting bots. | |
| app.netlify.clify-dev/clify toukoursin/clify Verified websites as JSON commands for AI agents over plain curl or MCP. | |
| Ask Me tounsils/ask-me-mcp Ask about an operator's work, reusable patterns, availability and offer. Typed tools, eval-gated. | |
| TourClaim by Copernican tourclaim/tourclaim-cli Prepare trip cancellation claims on credit-card travel insurance with traveler consent. Review mode. | |
| Swiss Public Transport tpjnorton/swiss-public-transport-mcp Swiss public transport — journey planning, live stationboards, delays, and SBB ticket links. | |
| io.github.tponscr-debug/oracle-h tponscr-debug/oracle-h-mcp Human approval gate for AI agents. Critical actions approved or rejected by a human via Telegram. | |
| MediaEngine tr1ckymag1ca1/mcp-media-engine AI image, video, and audio generation for MCP — one API key, every model, wiring never changes. | |
| OpenMayhem trac-systems/openmayhem-mcp Use OpenMayhem text, embedding and media models with explicit cost controls. | |
| TrackingTime trackingtime/mcp TrackingTime MCP server for time, projects, tasks, users, customers, services, and reports. |
19,801–19,850 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.