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 |
|---|---|
| io.github.LeoMbm/malt-mcp leombm/malt-mcp MCP server for Malt.fr. Read your freelance profile, stats, and missions from Claude. | |
| io.github.LeonardMichalas/peering-mcp leonardmichalas/peering-mcp Who peers with whom, where they meet, and who an address range belongs to. PeeringDB and RDAP. | |
| aesthetics-wiki-mcp leonardoca1/aesthetics-wiki-mcp MCP server that exposes the Aesthetics Wiki as a searchable knowledge source, letting LLMs look up aesthetic movements, styles, and visual subcultures. | |
| io.github.leonardosepulvedat/mcp-google-analytics leonardosepulvedat/mcp-google-analytics GA4 MCP that reads AND writes: reports, funnels, audits, and server-side events. 26 tools. | |
| io.github.leonardosepulvedat/mcp-n8n leonardosepulvedat/mcp-n8n Operate and build n8n: 61 tools, 560-node catalog, validation, autofix, snapshots and backups. | |
| Hypermnesic leonardsellem/hypermnesic Git-native long-term memory for AI agents: your markdown files are the source of truth, the search index is a disposable projection rebuilt from git, and every memory the agent writes is a reviewable git commit. Served over one OAuth-secure | |
| OpenBaud leonezz/openbaud Local serial and USB hardware access for coding agents, with typed YAML protocol commands, checksum validation, audited writes, lossless captures, hardware-free replay, and MCP App visualizations. Runs locally over stdio; live hardware use | |
| io.github.Leonhest/hivemind leonhest/hivemind A shared, live plan for teams of coding agents, synced through your git remote. | |
| Infomaniak MCP (unofficial) leonhoulier/infomaniak-ai Manage Infomaniak DNS, mail and VPS apps through OAuth, with live official documentation. | |
| io.github.leonmch-byte/chinese-nlp-mcp leonmch-byte/chinese-nlp-mcp Chinese NLP toolkit for MCP: segmentation, pinyin, keywords, sensitive words. Offline via stdio. | |
| io.github.LeonTing1010/haplane leonting1010/hap-deploy-cli 鸿蒙 HAP 签名部署 MCP：面向鸿蒙应用开发者，真机调试一键签装，也走华为邀测/上架。中性工具+可订阅源，本地 stdio。 | |
| The Button Wall leovenom/buttonwall-mcp Rent a clickable button on a million-pixel wall: find free space, get a quote, create a checkout. | |
| RAG Documentation Scraper lernowaadmin/rag-docs-scraper Crawl any documentation site and return heading-bounded, LLM-ready chunks with source metadata. | |
| io.github.les-k/mcp-confirm les-k/mcp-confirm An MCP server whose confirmation cannot be replayed against a different call. | |
| io.github.les-k/pg-readonly-mcp les-k/pg-readonly-mcp A read-only Postgres MCP server that parses SQL rather than pattern-matching it. | |
| io.github.les-k/sweep-mcp les-k/sweep-mcp An MCP server that can delete directories, and the guard rails that make that acceptable. | |
| Humanity Loop lesterhau/humanity-loop Distributed public-interest agent network with bounded passive contributor nodes. | |
| LetDraw letdraw/letdraw-mcp Create, edit, share and export hand-drawn LetDraw diagrams, from code or a prompt. | |
| io.github.letom1176-spec/orchard-data-mcp letom1176-spec/orchard-data-mcp Pay-per-call market data for AI agents via x402 (USDC on Base): regime, track record, catalysts. | |
| io.github.letoribo/mcp-graphql-enhanced letoribo/mcp-graphql-enhanced GraphQL gateway for LLMs. Handles huge GitHub GraphQL & @neo4j/graphql schemas without crashing | |
| io.github.levelsofself/nervous-system levelsofself/mcp-nervous-system Governance for LLM agents: 7 enforced rules + read-only reference tools. Safe in any MCP client. | |
| io.github.levelsofself/ai-ops levelsofself/mcp-ops-server AI operations management: 12 specialized agents, task dispatch, and team coordination. | |
| io.github.levelsofself/self-awareness-game levelsofself/mcp-server Play self-awareness scenarios across 7 levels. 6,800+ coaching scenarios via MCP. | |
| Chronicle MCP leviathan0x0/chronicle-mcp Local, private AI chat history search & memory: BM25 over your Cursor, Claude and ChatGPT chats. | |
| io.github.lewo-media/safe-mind lewo-media/safe-mind-tools Psychological risk assessments (GBU Psyche) via Safe Mind: surveys, departments, analytics. | |
| Aisma lex2029/aisma-mcp Edit videos you already shot with plain words and reference photos. Framing and audio stay. | |
| pgbrake lexang/pgbrake Postgres brake for AI agents: risky SQL waits for approval, UPDATE/DELETE get one-command undo. | |
| LexQ lexq-io/lexq-cli The Decision Operations Platform for engineering teams | |
| Orinyx lexthirteen-ai/orinyx-mcp Test healthcare AI agents' medication claims against cited FDA label text. Not for clinical use. | |
| Turbo Quant Memory lexus2016/turbo_quant_memory Local-first memory and knowledge graph for coding agents. Compact retrieval, no network. | |
| LFG Alarm lfg-gm/lfg-alarm-mcp Let your AI ring a real alarm on any phone or laptop, at any time or for any moment online. | |
| content-core lfnovo/content-core Extract content from URLs, documents, videos, and audio files using intelligent auto-engine selection. Supports web pages, PDFs, Word docs, YouTube transcripts, and more with structured JSON responses. | |
| KeyShot lfoletti/keyshot-mcp Control KeyShot Studio: scene, cameras, materials from a CMF sheet, and renders | |
| memento-mcp lfrmonteiro99/memento-mcp Memento is a local-first MCP server that gives AI coding agents
durable project memory — facts, decisions, patterns, and architecture
notes — so they stop re-learning the same context every session.
Runs locally on Node.js 18+ with SQLite s | |
| Motor Current Signature Analysis lgdimaggio/mcp-motor-current-signature-analysis MCP server for Motor Current Signature Analysis — fault detection in electric motors | |
| Predictive Maintenance MCP Server lgdimaggio/predictive-maintenance-mcp Enables AI assistants to analyze vibration data, detect machinery faults, and generate professional diagnostic reports through natural conversation. | |
| BugiaData lgpoliveira/bugiadata-mcp Relational locale-aware fake data for Cursor and Claude via MCP (SSE). Free tier at bugiadata.com. | |
| IT桔子 MCP lgyers/itjuzi-mcp Hosted MCP for IT桔子 primary market company, funding, investor and sector data. | |
| RevClamp MCP Server lhphong09t2/revclamp-mcp Zero-take-rate Stripe 2025-03-31.basil, Visa CE 3.0 & EU/XI VIES VAT guardrails MCP server. | |
| termgram liagha/termgram MTProto Telegram client for the terminal (Rust): a CLI for messages, media and
contacts, an MCP server that pushes server-to-client notifications when new
messages land (per-chat filtering), and an SSE stream. Local-first, no third-party
AP | |
| AgentPub — Public Chat and Shared Memory for AI Agents liboy119/agentpub Public chat and shared memory for AI agents. Open reads, free write keys. MCP + A2A + WebSocket. | |
| LibraryAPI library-api/libraryapi-mcp US public libraries and branches near any address, with collections from the IMLS survey | |
| io.github.Libres-coder/parseflow libres-coder/parseflow PDF parsing server with text extraction, metadata, search, images, and TOC via MCP | |
| Compass licentiumio/compass-mcp Ground your LLM in EU financial, crypto and AI regulation, verbatim and cited, via Compass. | |
| io.github.Licinexus/mcp licinexus/licinexus-mcp Brazilian public procurement (PNCP) and Federal Revenue CNPJ data — 16 tools, 4 prompts. | |
| nomue Record Verifier licklider-ai/nomue-verifier-mcp Local verification of nomue Protocol Records; current release supports the Release 1 Welch bundle. | |
| Share HTML lifeodyssey/share-html Create sandboxed public-unlisted or access-key-protected HTML previews through a remote MCP server. | |
| LifeVerse Product Discovery lifeversegu/lifeverse-mcp Discover and recommend public, ready-to-use LifeVerse AI products and interactive experiences. | |
| io.github.liftaven/mcp-server liftaven/mcp-server MCP connector for Liftaven SEO research, connected search reports and reviewed website proposals. | |
| OWL MCP Server liftkkkk/owl-mcp Enables AI assistants to query, modify, and reason over OWL/TTL/RDF ontology files using natural language, without needing SPARQL or OWL syntax. |
10,901–10,950 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.