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 |
|---|---|
| Halfnine notinferred/halfnine PostgreSQL through Halfnine: describe, read-only queries, and changes you approve in the app. | |
| StudioSphere Pulse — Audio Intelligence notpaulb/studiosphere-pulse-mcp Free licensed loops and authorized audio analysis: BPM, key, waveform. Estimate before paid use. | |
| NoBounce Email Validation notprathap/nobounce-mcp Real-time single and bulk email validation (syntax, MX, 5,000+ disposable domains, SMTP). | |
| Memegician notysoty/memegician-mcp Search 400+ meme templates, see what's trending, and render memes with your captions. | |
| SimplyUtils notysoty/simplyutils-mcp Developer and text tools: JSON, QR codes, units, passwords, UUIDs, hashes, Base64, regex and more. | |
| PQC-Khepra MCP — CMMC Autopilot & AI Security Recorder nouchix/pqc-khepra-mcp Post-quantum CMMC compliance scanner & AI agent attestation. FIPS 140-3, ML-DSA-65, 36K+ mappings. | |
| Pallas Athena Tools nous-ehr/claude_pallas_extension athenahealth DataView, API, and workflow tools for Claude Code with learning loop | |
| io.github.NousVigil/archstone nousvigil/archstone Compile your own business capabilities from declarative YAML and serve them as MCP tools. | |
| Nova Amazon MCP Server nova-data-analytics/nova-amazon-mcp Amazon Seller Central, Vendor Central and Ads data, profit-ready, for Claude, ChatGPT and any AI | |
| Novada MCP novadalabs/novada-mcp One MCP server for all web data. Scrape, search, crawl, and AI research in one install. | |
| O'So MCP Server for PrestaShop novalo-dev/prestashop-mcp-server Lets Claude, ChatGPT or Cursor connect to PrestaShop, with each employee approving what they may do. | |
| Spotify MCP novalux12/spotify-mcp-server Spotify Web API MCP: playback, library, playlists, search, podcasts. Not affiliated with Spotify. | |
| ATTRACTOR Verification, State & Evidence novanbaillif/attractor-machine-commons Verify artifacts, hand off public state, and record, check and find evidence about capabilities. | |
| NovaSolver Studio novasolver/novasolver-studio Free desktop CAE: import CAD/STL, solve FEM structural/thermal and CFD, verify the answer. | |
| io.github.Noves-Inc/canton-mcp noves-inc/canton-mcp Query Canton Network balances, rewards, transactions, prices, and identity from any AI agent. | |
| Novita MCP Server novitalabs/novita-mcp-server An MCP server that enables seamless management of Novita AI platform resources, currently supporting GPU instance operations (list, create, start, stop, etc.) through compatible clients like Claude Desktop and Cursor. | |
| io.github.nowledge-co/server.json nowledge-co/claude-dxt A server that provides MCPB package functionality for Nowledge Mem | |
| Yandex Analytics nozikov/yandex-mcp Read-only Yandex analytics for AI agents: Metrika, Webmaster, Direct and Wordstat. | |
| io.github.npupko/agency-mcp-server npupko/agency-mcp-server On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents | |
| io.github.nries1/tend-mcp nries1/tend-mcp Unofficial MCP server for Tend Dental appointment booking. Not affiliated with Tend. | |
| Verdict — Send anything. Get the truth. nrupala/verdict-filings Send anything. Get the truth — REAL, SUSPICIOUS or LIKELY SCAM verdicts on messages and links. | |
| io.github.nrwl/nx-console nrwl/nx-console A Model Context Protocol server implementation for Nx | |
| Generate-Data ns-3e/generate-data-mcp MCP server for Generate-Data.com: dataset generation, AI schema design, Project management. | |
| MANNA nsf-simons-cosmicai-institute/manna MCP server for IVOA astronomical archives: NOIRLab Astro Data Lab, NRAO/ALMA, CADC, ESO, Gaia | |
| io.github.venomseven/nslookup nslookup-io/nslookup-mcp DNS lookups, health reports, SSL certs, security scans, GEO scoring, uptime checks | |
| io.github.nsozturk/tweetkit-x nsozturk/tweetkit-x Post, delete & read on X (Twitter) using your own logged-in web session — no paid API. | |
| Snowflake MCP Server nsphung/mcp-snowflake-server A Snowflake MCP server — SQL queries, schema exploration, and data insights for AI assistants | |
| io.github.NtrpyDev/proton-workflow-connector ntrpydev/proton-workflow-connector Unofficial self-hosted MCP connector for Proton Mail Bridge and SimpleLogin. | |
| Figme ntson9p/figme-mcp MCP server that reads local Figma .fig files, fully offline | |
| io.github.nuance-dev/rival nuance-dev/rival-mcp Query AI model benchmarks, pricing, and comparisons from rival.tips | |
| io.github.nubiia-dev/mcp-holded nubiia-dev/mcp-holded Complete Holded Invoice API integration with 72 MCP tools for invoices, contacts, products, and more | |
| io.github.nubiia-dev/mcp-newsapi nubiia-dev/mcp-newsapi NewsAPI.ai (Event Registry): 10 read-only MCP tools for news articles, events, autosuggest, trends | |
| io.github.nubiia-dev/mcp-pipedrive nubiia-dev/mcp-pipedrive Complete Pipedrive CRM integration with 254 MCP tools for deals, contacts, and pipelines | |
| io.github.nubiia-dev/mcp-quipu nubiia-dev/mcp-quipu Quipu API integration with 18 MCP tools for invoices, expenses, contacts and Spanish VAT reporting | |
| Dynoxide nubo-db/dynoxide A DynamoDB emulator with an MCP server exposing 35 DynamoDB tools to coding agents. | |
| Linux MCP daemon (mcpd) nucleusv/linux-mcp-daemon AI agent access to Linux servers without SSH: scoped tools, per-call isolation, root only if granted | |
| FURRINGLINE nueyprap/furringline-mcp Thai building materials: product search, prices before VAT, stock and material calculators. | |
| bouncer nugehs/bouncer Static compliance-controls checker for UK Online Safety Act & ICO Children's Code. CLI + MCP. | |
| io.github.nugehs/gate nugehs/gate One ship/no-ship verdict from aiglare, bouncer, tieline & repoctx — the unified merge gate. | |
| nu:legal Deutsches Recht nulegal-startup/recht-mcp German federal and Land statutes plus court decisions for agents. Keyless, read-only. | |
| Sidewise nulljosh/sidewise News from 17 outlets with left/center/right bias tags and one-sided blindspot detection | |
| Nullprint nullprintai/nullprint-mcp Create, launch, check and drive Nullprint multi-profile browser profiles from any MCP agent. | |
| io.github.numbererikson/shinobi numbererikson/shinobi Task spine + searched dead ends + approvals for AI coding agents. One brain, every device. | |
| Numbers Online — phone intelligence numbers-online/numbers-online-mcp Read-only phone intelligence for AI voice agents — line type, risk, DNC, signed receipts. | |
| Numeratica — financial planning calculations numeratica/mcp Deterministic US financial planning: retirement Monte Carlo, Roth conversion, RMD, tax, IRMAA, SS | |
| Comparador de luz y gas (CNMC) nuncaeslupus/comparador-luz-gas Ofertas de luz y gas en España del comparador oficial de la CNMC, ordenadas por precio. | |
| doc-control nuncaeslupus/doc-control Edit Word documents by address: tracked changes, comments, anchors, with backups and undo. | |
| GitLab Documentation MCP Server nunolima/gitlab-docs-mcp Searchable access to GitLab documentation from multiple repositories with full-text search. | |
| Grok Build nuruvala/grok-build-to-claude Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research. | |
| AGENTS.md Generator nushey/agents-md-generator Analyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents. |
13,951–14,000 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.