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 |
|---|---|
| MIAPI — Grounded Web Answers doyukndr/miapi-python Web search and AI answers with real source citations and a confidence score. | |
| Dr.Deploy dr-deploy/drdeploy MCP tools for drdeploy: scan deployed sites, list, get findings, check status. | |
| io.github.dr12hes/engrm dr12hes/engrm Shared memory across devices, sessions, and agents for OpenClaw, Claude Code, and Codex. | |
| Formeo draggable/formeo.io Build and publish Formeo forms, read and export submissions, and get embed code from AI agents | |
| AXIOM dragoscv/axiom Transactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply. | |
| io.github.dravensoft-dev/arena dravensoft-dev/arena Arena by Dravensoft over MCP: the router, the references and every component document. | |
| io.github.DrBaher/compare-cli-mcp drbaher/compare-cli MCP server for compare-cli: contract version diff/redline and a drift gate as agent tools. | |
| DreamLand MUD dreamland-mud/dreamland_web Help, item search, news and who is online for DreamLand, a text MUD. EN/RU/UA, read-only. | |
| Dreamwork dreamworkhq/mcp Job search, application materials, and application tracking for AI assistants. | |
| Dregs dregs-sdk/dregs-mcp Fraud and abuse detection for SaaS: investigate scored identities, triage escalations, tune rules. | |
| VerifyGrid B2B Compliance & Entity Verification drewtuzson/verifygrid-mcp Sub-50ms verification for FMCSA USDOT/MC, CMS NPI, OFAC/OIG/SAM sanctions, and TCPA phone risk. | |
| Gearboy MCP Server drhelius/gearboy MCP server for Gearboy Nintendo Game Boy / Game Boy Color emulator | |
| Gearcoleco MCP Server drhelius/gearcoleco MCP server for Gearcoleco ColecoVision emulator | |
| Geargrafx MCP Server drhelius/geargrafx MCP server for Geargrafx PC Engine / TurboGrafx-16 emulator | |
| Gearsystem MCP Server drhelius/gearsystem MCP server for Gearsystem Sega Master System / Game Gear / SG-1000 emulator | |
| Geartowns MCP Server drhelius/geartowns MCP server for the Geartowns FM Towns emulator | |
| MCP Charts dri-water/mcpcharts Find MCP servers, skills, plugins, agents, prompts and rules for any task. | |
| io.github.geeks-accelerator/drifts driftsbot/mcp-drifts Multi-sensory AI experiences with time-locked progression and structured sensory data | |
| io.github.Drix10/ai-resources drix10/ai-resources Search and read daily AI news briefings: models, companies, funding, tools. CC BY 4.0. | |
| io.github.drjoergkrauter/leadership-agent drjoergkrauter/zukunft-fuehren MCP-Server zum Buch 'Zukunft führen' (Dr. Jörg Krauter): BANI & Leadership-Impulse. | |
| BitBooth Agent Tools drock91/bitbooth-docs Discover BitBooth APIs for free, then buy capped x402 fetch, PageDelta, and wallet checks. | |
| BitBooth Seller Routes drock91/bitbooth-docs Create private x402 seller routes, set prices, and route payouts directly to your wallets. | |
| DroneBundle dronebundle/dronebundle-mcp Ask about your drone operation: projects, jobs, flights, pilots, maintenance and safety. Read-only. | |
| droplinked droplinked/droplinked-mcp Agentic commerce + trust MCP: discover, verify, and transact across droplinked's merchant network. | |
| DropTrack droptrack/droptrack-ai-integrations Analyze tracks and manage customer music-promotion workflows through your DropTrack account. | |
| Dropyour dropyour/dropyour-plugin Publish micro-apps from your AI with no account; operate them as real apps. Data stored in the EU. | |
| io.github.drQedwards/pmll-memory-mcp drqedwards/ppm PMLL Memory MCP — persistent KV context memory and Q-promise deduplication. | |
| io.github.drumst0ck/uploadkit drumst0ck/uploadkit UploadKit MCP — 40+ upload components, route scaffolds, BYOS setup, full docs search. | |
| Aegis Security Skills drupadsachania/aegis-skills Read-only library of 24 defensive cybersecurity skills: ATT&CK, ATLAS, DFIR, CTEM and more. | |
| DrUrls drurls/mcp Audit websites for SEO from your AI assistant: scores, issues with fixes, Google indexability | |
| Druxt docs druxt/druxtjs.org Search and read the Druxt documentation and API reference. | |
| TakeMeUp.cv – CV & Resume Builder dsdev-d/takemeup-mcp CV & resume builder: country formats in 14 languages, ATS checks, cover letters, job tracker. | |
| ai.smithery/dsharipova-mcp-hw dsharipova/mcp-hw Create personalized greetings by name in the tone you choose. Get quick suggestions for friendly i… | |
| CCS Runtime Evidence dshcorrectover/ccs-mcp-server Agent tool-call guardrail: fail-closed runtime security verification with Ed25519 evidence receipts. | |
| PRG Risk Oracle dsrpt1/prg-risk-mcp Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin. | |
| The Commons — Dead Brands Collab Hub dstrausser83/db-collab-hub Public MCP discussion hub for AI agents — anonymous reading, free instant hub-key posting. | |
| vardoger dstrupl/vardoger Personalize AI coding assistants by analyzing local conversation history. Runs on your machine. | |
| ENTRA Jobs dubaikseniia-wq/entra-mcp Verified AI/tech jobs from company ATSs: search, fit matching, salary stats; employer job posting | |
| Weav dubdubdubco/weav-mcp-server Connect AI tools to Weav customer service. Triage conversations, reply, and manage your Help Center. | |
| Weav Customer Service dubdubdubco/weav-site-mcp Explore Weav customer service pricing, features, comparisons, signup, and demos. No auth required. | |
| Arc Research dubsoft/arc Commodities research MCP: knowledge graph, COT, NG storage/weather, quotes, and stories. | |
| io.github.dubuqingfeng/gitlab-mcp-server dubuqingfeng/gitlab-mcp-server GitLab MCP (Model Context Protocol) server for AI agents | |
| Scopture ducflair/scopture-plugin Work on physical engineering projects, inspect CAD/BIM, run simulations, and manage project context | |
| Duck Framework MCP duckframework/duck Official Duck Framework MCP server for AI-assisted development and project scaffolding. | |
| StoryCapture ducminhle1904/storycapture Write, rehearse, record and publish website demo videos, from the desktop app or the cloud. | |
| Baton dudko-dev/baton-mcp-setup Local MCP server for Baton: edit git-native API requests, collections, environments and scripts. | |
| PDF to Markdown dudko-dev/pdf-to-md-mcp-setup Hosted MCP front door to the pdf2md API: checked PDF-to-Markdown requests, short-lived credential. | |
| Tabellum dudko-dev/tabellum-mcp-setup MCP bridge to the Tabellum database client: schema, reads, SQL drafts; writes approved in the app. | |
| Vectorize dudko-dev/vectorize-mcp-setup Hosted MCP front door to the Vectorize API: raster-to-vector tracing to SVG, PDF, EPS or DXF. | |
| Mercury402: Treasury/FRED financial data over x402 dudman1/mercury402 Treasury/FRED financial data over x402: pay-per-call US yields, macro and forex in USDC on Base |
22,601–22,650 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.