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 |
|---|---|
| TrustNotch Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles. | |
| Taiwan CWA Weather Access Taiwan CWA weather data and forecasts for all counties and cities | |
| UIAutomator2 MCP Server Android mobile automation with uiautomator2. AI bot for taps, swipes, apps, XPath testing, RPA. | |
| UniProt MCP Read-only UniProtKB via MCP (entries, sequences, features, GO, taxonomy, ID mapping). | |
| unlimited-mcp Delegate coding and sysops tasks to cheaper agents or local LLMs via durable background job queues. | |
| U.S. Car Sales Tax Car sales tax, title and registration fees: TX, CA, FL, NY, PA calculators and all 50 state rates. | |
| U.S. County Property Tax Property tax rates, median bills and estimates for all 3,135 U.S. counties; TX, NC, FL local rates. | |
| dev.fly.veles-finance-gateway/veles-finance-mcp AI financial agent: due diligence, SEC 10-K, Kelly Criterion. Pay-per-call via x402 USDC. | |
| io.github.Mars-proj/verifiable-memory Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic. | |
| io.github.beee003/vynn-mcp Self-improving AI workflows with backtesting, prompt optimization, and scheduling | |
| Wikidata + Google Knowledge Graph MCP Read-only Wikidata tools and identity evidence. Local optional Google KG; bounded public remote. | |
| io.github.taylorwilsdon/workspace-mcp Google Workspace MCP server for Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Chat. | |
| io.github.pa1ch/yandex360-mcp MCP server for Yandex 360 services (Wiki, and more) — tools for AI assistants. | |
| 元铸工坊 SOSOFAST (yuanzhu) Governed AI workflow assets: staged writes, evals-gated template forging, ontology via MCP. | |
| SiftSum pytechno/siftsum-web Private financial journal: receipts, recurring expenses, and cash flow with MCP tools. | |
| Pyth Pro MCP Server pyth-network/pyth-crosschain Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets. | |
| Verified Memory python1/data-lore-hive Offline read-only search over a checksum-verified, optionally signed memory pack, with exact quotes | |
| io.github.pyunto/tm-mcp pyunto/tm-integrations Read your Pyunto Time Management schedule and log time from an AI assistant. E2EE project planning. | |
| BlenderLens pzalutski-pixel/blenderlens-mcp MCP server that lets AI agents build, check, preview and export game assets in Blender | |
| JMeter Docs qainsights/docs.jmeter.ai Apache JMeter community documentation, conversion tools, linters, and calculators for AI agents. | |
| io.github.qFlav/agentdrop-mcp-server qflav/agentdrop-mcp-server MCP server for AgentDrop - encrypted file transfer between AI agents across any host or network. | |
| 口播视频自动剪辑 MCP qianqiuwanzi/th-recut-free 输入口播文案与素材，自动生成安全排版出片计划并云端渲染成片。前 3 条免费。 | |
| io.github.qingkuai-js/qingkuai-mcp-server qingkuai-js/language-features MCP server for Qingkuai (.qk) — docs search, syntax check, compilation, and formatting tools. | |
| Qiniso qinisolabs/qiniso Deterministic fact verification for AI agents — checksums & curated data, not guesses. | |
| Qiskit Code Assistant MCP Server qiskit/mcp-servers MCP server for the Qiskit Code Assistant intelligent code completion | |
| Qiskit Documentation MCP Server qiskit/mcp-servers MCP server for querying and retrieving Qiskit documentation, guides, and API references | |
| Qiskit Gym MCP Server qiskit/mcp-servers MCP server for qiskit-gym reinforcement learning quantum circuit synthesis | |
| Qiskit IBM Runtime MCP Server qiskit/mcp-servers MCP server for IBM Quantum computing services through Qiskit IBM Runtime | |
| Qiskit IBM Transpiler MCP Server qiskit/mcp-servers MCP server for AI Transpiler IBM Quantum services | |
| Qiskit MCP Server qiskit/mcp-servers MCP server for Qiskit quantum computing with circuit serialization utilities | |
| io.github.qmmughal/titan-email-mcp qmmughal/titan-email-mcp MCP server for Titan Email (IMAP/SMTP), tested and confirmed with GoDaddy mailboxes. | |
| Eigenstyle qompassai/eigenstyle MCP server for a personal voice profile: corpus, fingerprint, and draft-checking tools. | |
| Periscope qompassai/periscope MCP broker into your live Neovim/diver config: LSP, formatters, linters, DAP, MATE attention. | |
| Vongola qompassai/vongola Read-only operator instrumentation for the vongola TLS gateway. | |
| io.github.qrussell/wemo qrussell/wemo-ops-center Control WeMo smart home devices - discover, toggle, adjust brightness, and manage HomeKit codes | |
| QRX qrxcodes/qrx-mcp Turn a prompt and a link into a branded, print-ready QR code that always scans. | |
| io.github.qso-graph/dxe-mcp qso-graph/dxe-mcp DXpedition tracking MCP server: active and announced expeditions, QSL routes | |
| io.github.qso-graph/eme-mcp qso-graph/eme-mcp EME prediction for amateur radio: moon windows, path loss and degradation, computed locally | |
| io.github.qso-graph/js8call-mcp qso-graph/js8call-mcp JS8Call MCP server for HF messaging: decode stream, heard stations, message traffic | |
| io.github.qso-graph/meteor-mcp qso-graph/meteor-mcp Meteor scatter planning between two stations: showers, radiant geometry, live counts | |
| io.github.qso-graph/qso-graph-contest-mcp qso-graph/qso-graph-contest-mcp Contest calendar and rules MCP server: what is running, what is coming, and the rules | |
| io.github.qso-graph/qsp-client qso-graph/qsp-client QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM) | |
| io.github.qso-graph/qsp-mcp qso-graph/qsp-mcp QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM) | |
| com.dintak/dintak-mcp-gateway qtpgitadmin/dintak-mcp-gateway Semantic job search, posting, and apply for Dintak, with resume-to-job match scoring. | |
| Voice Capture quack2025/genius-voice-capture-back Add voice answers to open-ended survey questions; create projects, get snippets, read transcripts. | |
| Quadratic quadratichq/quadratic-mcp-plugin AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases. | |
| Quadratik quadratik-ai/quadratik Search and manage 220M+ B2B contacts. Filter by title, industry, location, and more. | |
| Quady3D MCP quady3dai/quady3d-tools Generate 3D assets, quote credits, recover tasks and save model files to a project. | |
| io.github.Quangsumi/samplemcp-server quangsumi/whatever A sample MCP server that returns random weather descriptions. | |
| io.github.Quant-M2M/API-Quant-M2M quant-m2m/api-quant-m2m Server temporarily offline. |
47,851–47,900 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.