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 |
|---|---|
| TrustBench lithvall/trustbench x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools). | |
| io.github.litportnet/litport-mcp litportnet/litport-mcp MCP server for the Litport API: tokens, packages, pay-per-GB pools, geo targeting and proxy URLs. | |
| Drillr — The financial MCP for AI agents little-grebe-inc/drillr-mcp-server Financial data and research MCP for US/CN/JP equities: filings, statements, ownership, signals. | |
| io.github.littleblakew/msds-chain littleblakew/msds-chain-mcp Chemical safety intelligence — 25 tools: compatibility, hazards, PPE, compliance, SDS lookup | |
| ReportGem Global Research (报告驿站) littlemosquito123/reportgem-global-research Global investment research knowledge base: 16M+ bank reports, filings, earnings calls, charts. | |
| mibly-apple-health-mcp littlenew117/mibly-apple-health-mcp Open-source Apple Health MCP server. Brings your sleep, heart rate, HRV and workout data from the Mibly iPhone app into Claude, Codex or any MCP agent, stored encrypted on your own machine. | |
| Agent-Comm-Hub liuboacean/agent-comm-hub Build production-grade multi-agent communication infrastructure in minutes.
Real-time messaging, task scheduling, shared memory, and trust-based evolution — all via MCP + SSE. | |
| Liveblocks liveblocks/liveblocks-mcp-server MCP server for Liveblocks. | |
| livedot MCP livedotme/mcp Find someone in a live running or cycling race, clubs and coaches near you, and race-day weather. | |
| LivePublicator livepublicator/mcp Write, preview and publish your company's press releases from the chat, with a live link in seconds. | |
| LiveReacting livereacting/livereacting-mcp Run a 24/7 live stream of pre-recorded videos, or live stream a recorded video at a set time. | |
| PreviewAPK livetaub/previewapk Give your AI agent a real cloud Android phone: push APKs, drive it, get screenshots and logs. | |
| Veragent lixiaowww/veragent-mcp Check the trust/security score of MCP servers, agents, skills & CLIs before you install them. | |
| memdsl liyuan1992/memdsl Review-gated declarative long-term memory with bounded read-only MCP access. | |
| io.github.LizzleChen/local-dfw-mcp lizzlechen/local-dfw-mcp Your AI's DFW guide: events, appraisals, Dallas 311, crime, floods, schools, utilities, districts. | |
| io.github.lj22503/invest-brain lj22503/invest-brain A-share investment research: quotes, financials, behavior patterns, and trading journals. | |
| io.github.LJaysk/kr-dart-events ljaysk/kr-dart-events Real-time Korean corporate disclosure (DART) events. Pay per call in USDC via x402. No API key. | |
| io.github.ljcl/gaggiuino-mcp ljcl/gaggiuino-mcp Remote MCP server for your Gaggiuino espresso machine's shots and profiles | |
| io.github.ljcl/intervals-mcp ljcl/intervals-mcp Remote MCP server for intervals.icu run data and analysis | |
| io.github.ljcl/strava-mcp ljcl/strava-mcp Remote MCP server for your Strava activities, segments, and routes | |
| io.github.ljdigital/au-bizintel-mcp ljdigital/au-bizintel-mcp Australian business intelligence MCP — ABN lookup, business search & AI prospect assessment via ABR. | |
| mcp-longjobs ljppanda/mcp-longjobs Reference MCP server for the mcp-longjobs library: durable long-running tasks with progress polling, mid-flight input, and cooperative cancellation, plus chunked file transfers with resume cursors and sha256 verification. Works on every MCP | |
| sec-ai: SEC EDGAR lkcair/sec-ai-mcp SEC EDGAR in 22 tools: 10-K/10-Q/8-K text, XBRL facts, insider trades, 13F, full-text search. | |
| yfinance-ai: Yahoo Finance lkcair/yfinance-ai-mcp Yahoo Finance in 68 tools: stocks, crypto, forex, commodities, funds, options, analysts, calendars. | |
| honesty-mcp lkopietz3-byte/honesty-mcp MCP server exposing 11 honesty-SDK kits (grounding, trust, audit, corroboration) as agent tools. | |
| SEO Perception lkoudal/seoperception-mcp Search Console, crawl, and SEO to-dos in Cursor and Claude. OAuth or token; close to-dos optionally. | |
| cnvs.app lksrz/cnvs-whiteboard-skills Real-time collaborative whiteboard — AI agents and humans edit the same board live over MCP. | |
| WISEPIM Commerce Reference lldiegon/wisepim-commerce-mcp Offline HS heading lookup, marketplace listing requirements and EU green-claims screening. | |
| io.github.llmops-pro/albyhub-admin-mcp llmops-pro/albyhub-admin-mcp Admin an Alby Hub Lightning node from an agent: info, balances, channels; safety-gated writes. | |
| io.github.llmops-pro/l402-search-mcp llmops-pro/l402-search-mcp No-KYC web search for AI agents, paid per query in Lightning sats (L402). Holds no keys. | |
| io.github.llmops-pro/nostr-ops-mcp llmops-pro/nostr-ops-mcp Nostr publishing, queries, and DMs for AI agents, with allowlists, rate limits, and an audit log. | |
| io.github.llmops-pro/nwc-mcp llmops-pro/nwc-mcp Lightning wallet for AI agents via Nostr Wallet Connect (NIP-47): budget caps, confirm, audit log. | |
| io.github.llmops-pro/paywall-mcp llmops-pro/paywall-mcp Lightning-paywall sidecar: wraps any stdio MCP server, requires paid invoices before tool calls. | |
| PaperBanana llmsresearch/paperbanana Generate academic diagrams and statistical plots from text using multi-agent AI. | |
| AIShield Security Scanner lm203688/aishield Scans MCP servers for tool poisoning, prompt injection and supply chain risks. | |
| ATEX AI Gateway lm203688/atex One API key for 6 AI models. Pay-per-use. MCP protocol support with web search. | |
| io.github.lmaniraruta/agentstorefront lmaniraruta/agentstorefront-mcp MCP for AgentStorefront — discover, price, and subscribe to paid agent services. | |
| io.github.Lmeng486/nano-mcp-termux lmeng486/nano-mcp-termux Zero-dependency single-file MCP server for Termux/Android, Raspberry Pi and Linux | |
| io.github.lnanology/xfinlab lnanology/xfinlab Financial intelligence for AI agents: market events, sentiment, technicals, news feed. | |
| LNbits MCP Server lnbits/lnbits-mcp-server Enables AI assistants to manage Lightning wallets through LNbits, including balance checks, invoice creation, payments, and extension operations, all via natural language. | |
| Stigmer lnshrivas/stigmer Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization. | |
| io.github.lo-nau/localgym-mcp-server lo-nau/localgym-mcp-server Read-only MCP server for UK gym search using the LocalGym Agent API. | |
| io.github.loaditoutadmin/loaditout loaditoutadmin/loaditout-mcp-server Search and install 20,000+ security-graded MCP servers and agent skills. | |
| Lobu lobu-ai/lobu Shared, permission-aware company context for AI agents, with provenance, approvals and audit. | |
| io.github.localgov-jp/mcp-server localgov-jp/localgov-mcp-server Japan central + municipal subsidies (20,810 grants, 1,627 munis). 8 tools beyond Jグランツ MCP. | |
| LocalPro — Verified US Local Service Provider Data localprodev/mcp-server Verified US local service providers across 10 home-services trades. Owned data, no API key. | |
| io.github.LockSpec/lockspec lockspec/lockspec MCP server giving AI coding agents version-pinned API context from your OpenAPI specs. | |
| lockstep lockstep-team-agent/lockstep Decision memory for teams building with AI coding agents. Captures every engineering decision once, ranks it by blast radius, and briefs every MCP-compatible agent before it acts, so agents stop making conflicting changes across repos. | |
| mcp-romm lodordev/mcp-romm 10 tool MCP server for RomM. Adds searching, metadata, tracking, saves and management via MCP. | |
| mcp-tautulli lodordev/mcp-tautulli A single file simple MCP server tracking 11 relevant tautulli metrics. |
11,001–11,050 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.