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.github.nicklasmenschel/gerezi-mcp nicklasmenschel/booking2 Manage restaurant bookings via Claude — read covers, find guests, move tables, send wedding quotes. | |
| Switchboard Finance nicklim123/switchboard-finance-mcp Australian business loans: ATO debt, caveat, equipment, property. Check fit, then a broker calls. | |
| com.smarthomeexplorer.www/product-intelligence nicks-sidehustle/smarthome-explorer-blog Smart home product intelligence: 1,080+ products with expert consensus scores and compatibility. | |
| Quellenkontor HR-Daten nicksadvisory/quellenkontor-sdk Verified German HR data with legal source: minimum wage, social security, holidays, notice periods | |
| ai.spotafraud/spotafraud nicksav/spotafraud.ai Check Australian (.au) domains for fraud and age — cert history, lookalikes, and an AI verdict. | |
| peaks.fyi — Mountain Routes, Huts & Weather nickshatilo/peaks-fyi European mountain routes, huts, access and forecasts with sources and explicit unknowns. | |
| io.github.nickymitnick/probo-connect-mcp nickymitnick/probo-connect-mcp MCP server for Probo print-on-demand — search products, configure orders, track shipments. | |
| Verify MCP (AgentBook verification) niclydon/fiador Verify AgentBook registration and operator attestations for agent wallets on World Chain. | |
| FaxFair nico02138-ops/faxwell Fax API and MCP server for AI agents. Fax US and Canada, pay per request with x402. No account. | |
| io.github.Nicodemus941/health-api nicodemus941/e-labus Clinical AI for lab analysis, biomarker scoring, health narratives, and risk insights. | |
| TradeTi.me — Market Hours nicolaijohannesen/global_trading_timeline Read-only trading hours for 30 stock exchanges — open now, next open, holidays, sessions. | |
| Almanac nicolascolombo/almanac Datos econ�micos y financieros oficiales de Argentina (BCRA, INDEC, CNV, MECON), AI-ready. | |
| KinoPipe nicolascoutureau/kinopipe FFmpeg as a service for AI agents: typed video editing tools, async jobs, downloadable outputs. | |
| Crosswire — Polymarket & Kalshi Arbitrage nicolasduarte04/crosswire-mcp Cross-venue Polymarket+Kalshi arbitrage: resolution mismatch, void risk & settlement divergence. | |
| io.github.NicolasIppoliti/argentina-mcp nicolasippoliti/argentina-mcp MCP server exposing Argentine public jurisdiction/registry data (georef) and datasets. | |
| Rexact nicolasmar91/rexact-mcp Verify, explain and audit regexes (ReDoS, engine compatibility) offline. | |
| io.github.NicolasMartalog/docweave-mcp nicolasmartalog/medium-rare Generate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document. | |
| io.github.nicolasramos/odoo-mcp nicolasramos/odoo-mcp MCP server for Odoo 18 with 38 business tools | |
| Grokzilla micro pay nicsins/ai-micro-pay 32 x402 pay-per-call tools: SEO, agent audits, JSON/text utils, OSINT. USDC on Base; $1=300 calls | |
| Nifra docs nifrajs/nifra Nifra docs, runnable examples, and API types as an MCP server for any AI assistant. | |
| Breaking Changes & Migration Data nigelcox98/agentdataapi What breaks when you upgrade a package, and what to use instead - from official docs. | |
| AISchemaGate and DataContractGate nightmoose/contractgate AISchemaGate validates and repairs structured LLM output against a contract, plus DataContractGate. | |
| nuthatch nightswatchhq/nuthatch Query an EVM contract's indexed history with SQL, via a local nuthatch nest and nuthatch dev. | |
| Tvijo DSHREM nikbibamon/tvijocode Pre-merge diff review and cloud assistance with explicit Tvijo spending limits. | |
| Coding Challenge Solutions nikhil-bhat/cc-solutions-mcp Search coding challenge solutions by keyword and optionally filter by programming language | |
| UI Beats nikhils4/ui-beats MCP server for UI Beats. Let your coding agent search, read and install animated React components. | |
| io.github.nikitacometa/mnemon-mcp nikitacometa/mnemon-mcp Persistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud. | |
| SI Federation nikitinmikhail1986-beep/si-team-collaboration Open federation for AI agents: identity, mentors, reputation and limited accession. | |
| Mobdev niklas-schmidt-dev/mobdev Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs. | |
| io.github.Nikoble1926/agent-trust-mcp nikoble1926/agent-trust-oracle ERC-8004 agent trust scores via x402: free preview + paid USDC-on-Base signed scores (5 chains) | |
| io.github.Nikoble1926/kraken-signals-mcp nikoble1926/kraken-crypto-signals Kraken crypto signals via x402: free preview + paid USDC-on-Base signals, regime & indicators | |
| MCP Fiscal Brasil nikolasdehor/mcp-fiscal-brasil Servidor MCP para integrar IAs com o sistema fiscal brasileiro: CNPJ, NFe, NFSe, SPED, eSocial. | |
| Nim Language Server nim-lang/langserver MCP server providing symbol navigation, diagnostics, and type resolution for Nim projects | |
| io.github.nimish14/resume-evidence-mcp nimish14/practical-llm-apps Retrieve grounded resume evidence for a job description using BM25 + evidence reranking | |
| BanProof AI nimishrangani/banproof-mcp Audit creator scripts for TikTok Shop and Amazon policy violations. Returns flags and safe rewrites. | |
| dokumendiregister.ee — Estonian public-authority documents nimistu/dokumendiregister-mcp Estonian public-authority document registers: one search across all, docs linked to companies. | |
| lahend.ee — Estonian court decisions nimistu/lahend-mcp Estonian court decisions: full-text case-law search, each ruling linked to its companies. Free. | |
| nimistu — Estonian Business Register nimistu/nimistu-mcp Estonian Business Register: companies, people, beneficial owners, trademarks. Free, no API key. | |
| chunk-invariance ninadphalak/llm-shield-proxy Checks whether your streaming redactor leaks a secret split across chunks; writes a pytest for it. | |
| Ninar AI ninar-ctrl/ninar.ai Audit your brand's visibility across ChatGPT, Gemini, Claude, Perplexity + 6 more engines. | |
| autobus — signed attestations for agents, $0.01 per call ninefiveonefive/web-bot-auth-check Signed attestations for agents, $0.01/call via x402: URL witness, AI permission, tx finality, JWKS. | |
| FLOP Independent MCP V2 ninjatrader542/flop Bounded readonly SHA256 verification with the official MCP SDK. No code execution or model calls. | |
| io.github.nirajagarwal/stox-mcp nirajagarwal/stox-mcp Percentile fingerprints, curated peers, theme clusters & market-stress context for US stocks. | |
| 3D AR Studio nirholas/3d-ar-studio Put 3D models in someone's real room: generate, arrange, and hand back one AR link. | |
| Claude Code Explorer MCP nirholas/claude-code Explore the Claude Code CLI source — browse tools, commands, search code, and more. | |
| Crypto Market Data nirholas/crypto-market-data Real-time crypto prices OHLCV orderbook - Bitcoin Ethereum 10000+ tokens | |
| Data Workbench nirholas/data Pump.fun creator rewards, DexScreener pair search, crypto headlines, and USD candles. | |
| DeFi Trading Agents nirholas/defi-agents DeFi agent definitions JSON API - crypto trading portfolio management bots | |
| Ethereum Wallet Generator nirholas/ethereum-wallet-toolkit Generate Ethereum wallets with BIP39 mnemonics, HD paths, vanity addresses, private key backup | |
| Ethereum Keystore Encryption nirholas/ethereum-wallet-toolkit Encrypt/decrypt Ethereum keystore JSON V3 with scrypt/PBKDF2 for secure cold storage |
45,701–45,750 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.