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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| USASpending.gov 1102tools-dev/federal-contracting-mcps USAspending.gov contracts, grants, loans, subawards, recipients, agencies, and federal accounts. | |
| BLS OEWS 1102tools/federal-contracting-mcps BLS Occupational Employment and Wage Statistics market wages. 7 tools. | |
| eCFR 1102tools/federal-contracting-mcps Electronic Code of Federal Regulations including FAR and DFARS. 13 tools. | |
| Federal Register 1102tools/federal-contracting-mcps Federal Register proposed/final rules, notices, executive orders, FAR cases. 8 tools. | |
| GSA CALC+ 1102tools/federal-contracting-mcps GSA CALC+ awarded labor ceiling rates from 230K+ MAS contracts. 8 tools. | |
| GSA Per Diem 1102tools/federal-contracting-mcps GSA Per Diem federal travel lodging and M&IE rates. 6 tools. | |
| Regulations.gov 1102tools/federal-contracting-mcps Regulations.gov rulemaking dockets, documents, public comments. 8 tools. | |
| SAM.gov 1102tools/federal-contracting-mcps SAM.gov entity registration, exclusions, opportunities, contract awards. 15 tools. | |
| USASpending.gov 1102tools/federal-contracting-mcps USASpending.gov federal contracts, subawards, recipients, agencies. 55 tools. | |
| ResiMind 1105216375-alt/resimind Exact polynomial checks, sparse expansion and verified rule memory. Local MCP tools, no model key. | |
| io.github.1111111111111111111114oLvT2/inquisitor 1111111111111111111114olvt2/inquisitor Hypothesis-driven problem solving for AI agents: probe, falsify, escalate. | |
| 1325.AI 1325ai/1325ai Verified directory of 47,000+ Black-owned U.S. businesses. Search, profiles, maps, rewards. | |
| 衍象坊 · 奇门遁甲 & 大六壬 139user/twords Qimen Dunjia & Da Liu Ren divination: complete nine-palace charts and four-lesson analysis. | |
| io.github.15998194110/delta-witness 15998194110/delta-witness Paid Capture and Guard tools for public-source observations before autonomous actions. | |
| PilotGentic 1genadam/pilotgentic macOS desktop control for Claude: click, type, screenshot, AX tree, browser control, agentic loops. | |
| io.github.1gr14/agents-party 1gr14/agents-party One encrypted channel where Claude Code, Cursor, Codex and any other agent talk to each other. | |
| 1inch MCP 1inch/1inch-ai Doc search, intent & cross-chain swaps, limit orders, portfolio, spot prices, gas & all APIs. | |
| GANO Connector 1powergrey/sios-gano-connector Private GANO MCP for feasibility, scenario analysis, persistence and executive operations. | |
| Chalkieboard iCloud 207studio/chalkieboard-icloud-mcp Read Chalkieboard (iPad) iCloud lesson folders, add materials, append lesson plans. No network. | |
| twentyone million 21-million-wall/twentyone-million Read the wall and claim one $1 USDC square on Base. No utility, not a token or investment. | |
| Silk 21j3phy/silk Message other people's AI agents with consent: end-to-end encrypted, on a public ledger. | |
| mapcast 21prnv/mapcast Animated map videos from a prompt: globe dives, country highlights, flags, flights and data maps. | |
| 24Repost 24repost-ru/24repost-mcp Cross-posting between Telegram, MAX and VK: routes, copy rules, history import, chatbots. | |
| Sense2 Promotional Products 24seagull-beep/sense2-next 21 tools: search 4,000+ Australian promotional products with live pricing, quotes and curated edits. | |
| 2anki 2anki/2anki.net Turn text, files, URLs, or photos into Anki flashcard decks from your AI assistant. | |
| AutoCAD MCP 2ez4gcx/autocad-mcp Let AI draw in AutoCAD: plans from images, KT/KC/NT sets, TCVN calc, quantities, sheets, PDF. | |
| Construction AutoCAD MCP 2ez4gcx/construction-autocad-mcp Let AI draw in AutoCAD: plans from images, KT/KC/NT sets, TCVN calc, quantities, sheets, PDF. | |
| SketchUp MCP 2ez4gcx/sketchup-mcp Let AI work in SketchUp: rooms, pro tagging, takeoff by room, model/design checks, scenes, Ruby. | |
| io.github.2s-io/mcp 2s-io/sdk 575+ agent tools: data, AI gateway, storage/queues/watchers. x402 USDC, no keys, usage billing. | |
| ComputeFirst 321zz321/computefirst-skill Free deterministic tools for math, data transforms, dates, text, statistics, finance, and units. | |
| Memory Hive 330899935/memory-hive-mcp Local-first memory over MCP. Built-in SQLite store; runs standalone. Agents propose; you confirm. | |
| Kevin's Coaching Brain 360tft/coaching-brain-mcp Coaching answers from Kevin Middleton's own writing, with the source link for each answer. | |
| Band Atlas (Hyper Nexus) 365724-ctrl/band-atlas-data Which cellular IoT modules work on which networks: 465 networks, 172 countries, device verdicts | |
| 3DOptix 3doptix/skills Optical design, simulation and analysis with GPU-powered ray tracing. Import from Zemax and CAD. | |
| io.github.3DUNLMTD/stylemcp 3dunlmtd/stylemcp Brand rules for AI outputs. Validate and rewrite text to match your brand voice. | |
| RatchetX Forecast Arena 3esign/ratchetx Shared Pyth context and live Solana forecasting arena for calibration, proof, and agent ranking. | |
| 3LT Letter Mail 3lgrouptechnology/3lt-letter-mail Give AI assistants hands: send real USPS letters via MCP. | |
| io.github.ksaslam311/agentpedia-mcp-server 3xfreedom/agentpedia Search, discover, and contribute to AgentPedia - the knowledge base for AI agents. | |
| 402cron 402cron/402cron Paid cron for AI agents: we call your https URL on schedule, signed. No account, paid with x402. | |
| BIG Machine Market 417properties/big-navigator AI-native $0.001 interpretation and state-deviation checks over x402. | |
| 42min 42min-us/42min-developers Scheduling for AI assistants: bookings, availability, meeting polls and routing forms. | |
| SecLens.ONE Email Security 42sec-pte-ltd/seclens Assess any domain's email security across SPF, DMARC, DKIM, MTA-STS, DNSSEC, DANE, and TLS-RPT. | |
| MedicineData MCP 455287876-design/medicine-data-mcp Chinese pharma data MCP: 22 tools covering drugs, trials, deals, patents, sales. Per-row billing. | |
| io.github.47-ronn/remote-agents 47-ronn/tunshell_mcp_agents Control fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce. | |
| io.github.48x-ai/marketbasketanalysis-mcp 48x-ai/marketbasketanalysis Co-purchase intelligence and merchant ops tools for AI shopping, ecommerce, and B2B agents | |
| 4chems Platform — IUCLID, CHESAR & QSAR Toolbox hosting 4chems/mcp Remote MCP server for 4chems hosted IUCLID, CHESAR and QSAR Toolbox: onboarding, inquiries, admin. | |
| Victauri 4da-systems/victauri In-process MCP server for Tauri apps: DOM, IPC with bodies, Rust state, SQLite. Debug builds only. | |
| 4dayweek.io Jobs 4dayweek/mcp Search reduced-hours jobs and employers: 4-day weeks, 9-day fortnights, half-day Fridays and more. | |
| Mandate 4fr4ko-povelecko/mandate Trade on Base through the Mandate module: every batch is checked onchain against the owner's rules | |
| net.arclera/arclera 4riel/arclera-web Read-only company facts for ARCLERA DIGITAL, LLC: contact, services, legal identity. |
19,701–19,750 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.