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 |
|---|---|
| Caotang nattiini45/caotang Serve a Caotang writing project to an MCP host: read it, and, when you allow it, change it. | |
| Wedding Seat naturalnet/wedding-seat-app Anonymous, no-login wedding planning: create a project, add guests, auto-generate a seating plan. | |
| Naumu naumu-ai/mcp Search, extend, and act on your team's Naumu knowledge graph: notes, threads, and nodes. | |
| Nausika nausika-app/nausika-feedback Mediterranean marine, nautical, sailing: forecasts, tides, sea routes, anchorages, POIs for AI. | |
| Holster MCP nauta-ai/holster Local-first secret scanning, rotation, vault, and audit-log tools for AI agents. | |
| Sciple Platform navaganeshr/sciple-mcp Sciple platform MCP: services, dashboards, runbooks, tickets, environments, AWS cloud inventory. | |
| Appbricx naveenbhargav-m/appbricx-examples Build, verify and deploy full-stack apps: Postgres, sign-in, workflows, realtime, AI, rollback. | |
| Community Funding NZ navtejdhillon/grants-mcp Search 380+ New Zealand community grant funders, deadlines and application questions. No login. | |
| FranklyMail Agentic Inbox naylalabs-org/franklymail Read and search FranklyMail email and prepare drafts, replies, and forwards for human approval. | |
| Health Hub MCP naymevg/health-conect-mcp Self-hosted MCP server for Android Health Connect — 34 metrics, daily rollups, dedup, 5 LLM tools. | |
| io.github.nazariinalyvaikobs/shopify-store-builder-mcp nazariinalyvaikobs/shopify-store-builder-mcp MCP server for building Shopify stores via the Admin GraphQL API: themes, pages, and navigation | |
| NB8 Floral nb8floral/nb8-floral-mcp Wholesale silk flowers: find by flower & color, per-stem prices, 7-day US stock, photo ID, checkout. | |
| Mnema — Shared Brain for You and Your AI Agents nbkdoesntknowcoding/mnema Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale | |
| kebiao 课标 nbrangerf/curriculum-standards-breakdown Search and cite China's compulsory-education curriculum standards (2022, rev. 2025), 14 subjects. | |
| io.flarewatch/flarewatch nbridges333/flarewatch Verifiable Flare & Songbird data: validator scores, FTSO accuracy, prices, wallet intelligence. | |
| io.github.rpconroy/gdex-mcp ncar/gdex-mcp MCP server for the GDEX (Geoscience Data Exchange) data portal: datasets, files, metrics, subsetting | |
| io.github.nczntb-wq/ihealed nczntb-wq/ihealed AI-powered guided healing meditations and manifestation scripts. | |
| io.github.ndkasndakn/refund-decide ndkasndakn/decade Refund eligibility notary for US subscriptions. Returns ALLOWED/DENIED/UNKNOWN. | |
| Kevros — Agentic Identity Trust ndl-systems/kevros-sdk Agentic identity trust: precision decisioning, cryptographic release tokens, hash-chained proof | |
| Nearby Permits nearbypermits/nearbypermits-mcp Building permits by address for a growing list of US cities and counties, from city open data. | |
| Nebula - AI-first B2B digital marketing, Mumbai nebulatech-in/nebula-mcp Ask Nebula (Mumbai) about AI-first B2B digital marketing: services, sectors, GEO/AEO Answers, blogs. | |
| io.fairseal/mcp-server ned-del/fairseal Verifiable entropy, provably-fair games, and receipt verification for AI agents (FairSeal API). | |
| PieterPost MCP neddes/pieterpost-mcp Let AI agents prepare, review, pay for, and send real letters and postcards. | |
| de.carbon-cashmere.api/crypto-intelligence nedeljko87/carbon-cashmere Pay-per-call crypto intelligence: 50 tools, own BTC/Kaspa/Bittensor nodes, x402 USDC, no API key. | |
| SelieeAI neebloltd/seliee Run your business from Claude: websites, SEO, ads, social, payments, leads and AI media. | |
| io.github.NeetPatel/devops-mcp neetpatel/devops-mcp An MCP server that provides DevOps and DevSecOps context for the project | |
| CCRider neilberkman/ccrider Full-text search, browse, and resume across your coding agent sessions (Claude Code, Codex, Amp) | |
| Sidereon neilberkman/sidereon GNSS positioning and astrodynamics: orbit propagation, passes, GNSS solves, and RINEX QC | |
| What Agents Buy neilkpatel/whatagentsbuy Independent measured reviews of x402 API sellers: pre-payment verdicts and accuracy grades. | |
| OnionLens Tor Tools nellinc/onionlens-public Tor address validation and retrieval fixtures, with disclosed research logging. | |
| Indox nematiai/indox-sdk Convert documents, images, video, 3D models and fonts with the Indox API. | |
| Neo — AI/ML Engineering neoairesearch/neo-mcp AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs. | |
| Neo.mjs Neural Link neomjs/neo-agent-brain Live runtime inspection, component tree, VDOM, state, and hot-patching bridge for Neo.mjs apps. | |
| Neonia: The Cloud Backend for AI Agents neonia-io/agent-mcp-examples Multiple MCP tools, persistent graph memory, token-saving data pointers, and more. | |
| Neo — AI/ML Engineering neoresearchai/mcpserver AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs. | |
| QrVerloz neoshrek/qrverloz-mcp QR codes active 90 days, claimable forever. Request an API key in chat to retarget and track scans. | |
| Falcon Builder neosky-ai/falcon-builder-mcp Build, debug, and publish production AI agent workflows in Falcon Builder from any MCP client. | |
| git-a2a neprel/git-a2a Git module dependencies and owning-agent routing for coding agents | |
| io.github.nerdydata/mcp nerdydata/nerdydata Search websites by source code, technology stack, analyze domains, and download lead lists. | |
| Dataset Aggregate & Pivot nero-engine/dataset-aggregate-pivot-mcp GROUP BY and pivot tables for JSON rows: 11 functions, date buckets, top N, totals, messy numbers. | |
| Dataset Cleaner & Exporter nero-engine/dataset-cleaner-exporter-mcp Dedupe, flatten and clean messy JSON rows (emails, phones, URLs, HTML) in one call, as JSON or CSV. | |
| Dataset Diff & Change Detector nero-engine/dataset-diff-detector-mcp Compare two versions of a JSON row list: what was added, removed or changed, field by field. | |
| Dataset Filter & Transform nero-engine/dataset-filter-transform-mcp Clean, filter and reshape JSON rows in one call: 26 transforms, 25 filters, sort, dedupe, limit. | |
| Dataset Join & Merge nero-engine/dataset-join-merge-mcp Join two lists of JSON rows on a key, like SQL or VLOOKUP: left, inner, full, anti joins, union. | |
| Signal Oracle neruoticfarrow/oracles Pay-per-call change-intelligence feeds for AI agents over x402 (deps, security, regs, tariffs) | |
| io.github.heidiEC/context-pod nervous-machine/context-pod Persistent context for AI agents built fromlearned vectors with certainty scores. | |
| SendGrid Transactional neschadin/sendgrid-mcp SendGrid transactional email: preflight send, templates, and delivery diagnostics. | |
| NessFlow nessflow/mcp Run and read SEO site audits: issues, health score, fixes, rankings and logs. | |
| Local Commander netbka/local-commander-plugins Give your AI hands on every computer you own. One chat, all your machines — even from your phone. | |
| io.github.netclaus/oroute netclaus/oroute Auto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings. |
45,601–45,650 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.