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 |
|---|---|
| AI Visibility aivisibilityskill/plugin See how AI engines describe a product, find what to fix on its site, and verify the fix. | |
| Toolars aixtral/toolars-open Local-first dev utilities: hash, base64, JWT, UUID, cron, URL codec. No network or telemetry. | |
| Atako aiybiz/atako-mcp Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels. | |
| qpon.arctic/arctic aizennsossuke212/arctic-mcp Read Robinhood Chain live: scan a token, trace its deployer, list new launches. | |
| UniPost ajhous44/unipost-agent Hosted MCP server for AI agents to post to LinkedIn profiles and X and upload to YouTube. | |
| World Resolver ajithisaac/world-resolver-mcp Resolve real-world capability gaps: validate native MCPs, search the web, and record unmet demand. | |
| FRTracker — Federal Regulatory Research ajleahey/frtracker Source-linked US federal regulations: CFR provision history, obligations, rules, comments. | |
| SkillDash ajnasnb/skill-dash Search and inspect source-pinned agent skills, plugins and tools through a free public MCP. | |
| Pulse402 Oracle ak10082247-max/pulse402-oracle Real-time Base & Solana liquidity, Polymarket orderflow, and pre-trade security via x402 V2. | |
| x402 Security & Alpha Oracle ak10082247-max/x402-solana-base-sniper-bot Read-only pre-trade honeypot simulation and DEX alpha oracle for Solana and Base. | |
| SupaForge akalsoftware/supaforge Find and fix drift between Supabase environments: schema, RLS, roles, auth, storage and more. | |
| io.github.akarazhev/bitcoin-risk-brief akarazhev/bitcoin-risk-brief Daily Bitcoin risk with freshness state on every response. Research context, not advice. | |
| ERUX Astrology & Ephemeris Engine akashagl92/erux_mcp Ephemeris natal & mundane charts, Vimshottari Dasha, transit horoscopes, Horas, and Vedic yogas. | |
| conduitAI akbaraziz/conduitai-bolt Search, browse, and install MCP servers, agents, skills, and plugins from conduitAI. | |
| Akeyless Agentic Runtime Authority akeyless-community/devin-akeyless-connector Secretless database and cloud access via Akeyless RTA. Credentials never enter the model. | |
| ai.smithery/akilat-spec-leave-manager-mcp akilat-spec/leave-manager-mcp Track and manage employee time off with quick balance lookups and streamlined applications. Find t… | |
| Artha Council akira231097/artha-council Auditable equity research and fail-closed broker execution for US and Indian cash equities. | |
| GrantIQ akis111/grantiq-mcp Eligibility-first UK & EU grant discovery, inside ChatGPT and Claude. | |
| io.github.aklodhi98/human-standards aklodhi98/humanstandards Read-only Human Standards guidance for accessible, usable interface design. | |
| Rules MCP akr1166/rules-mcp MCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity. | |
| Virohana Business akshay112376/virohanalife-membership Virohana business catalogue, pricing, company info & quote intake. Bearer auth, rate-limited. | |
| dev.tasklix/tasklix akshayjain1996/tasklix The shared task board your autonomous agent fleet can read and write. | |
| TypesenseKit akshitkrnagpal/typesensekit 95 typed Typesense operations for AI agents through an MCP server that is read-only by default. | |
| Useful Utilities aksp200/mcp 63 tools an LLM can't do alone, in focused subsets: file edits, live data, real checksums. | |
| Spotify akutishevsky/spotify-mcp Full Spotify Web API coverage - albums, artists, playlists, player controls, and more. | |
| io.github.Al-Adnane/kasbah-mcp al-adnane/kasbah-core Governance layer for agentic AI — signed, verifiable receipts for every agent action. | |
| Quarterly Tax Calculator al157/quarterly-tax-calc US federal + state quarterly estimated tax estimates, SE tax, and quarterly payment due dates. | |
| Schengen 90/180 Calculator al157/schengen-calculator Schengen 90/180 rolling-window calculator MCP server: stay math, trip checks, rule explainer. | |
| JiZhiMCP alanwang100/jizhineng-mcp Host any HTTP API as a standard MCP server; auto-distribute to 12+ mainstream agent platforms. | |
| Corvus albasha0x0/corvus Reverse engineering and security analysis of .NET and native binaries: decompile, compare, patch. | |
| io.github.albemarlestudio/clayre albemarlestudio/clayre-skills Brand strategy and content-calendar context for agents, with human-confirmed approval gates. | |
| nz.phos/analytics-engine albermm/analytics-engine AI analytics — sales analysis, ML forecasting, customer segmentation. | |
| nz.phos/piranha albermm/piranha BJJ video analysis — YOLO pose detection + Claude AI technique analysis. | |
| nz.phos/marketing-engine albermm/piranha-marketing AI marketing — content generation, competitor analysis, social publishing. | |
| nz.phos/sales-engine albermm/sales-engine AI sales — prospect discovery, ICP scoring, outreach generation. | |
| io.github.albertbolanoss/labs_mcp albertbolanoss/labs_mcp MCP Server with AI-powered tools including ElevenLabs text-to-speech for realistic voice synthesis. | |
| Viatsy albertsabatemartinez/viatsy Search Asia travel tours, browse guides, request quotes, find upcoming group departures. | |
| QACAT alconost/qacat-mcp Translation QA: automated checks, AI evaluation, linguistic review, and visual in-context testing. | |
| Zeus Memory — Enterprise Intelligence Platform aldc-io/zeus-memory Enterprise memory, search, and context for frontier AI. 38 tools for business intelligence. | |
| RNCP / RS — certifications professionnelles (France compétences) aldebertarnaud/mcp-rncp French RNCP/RS certification registers: search, sheets, blocs, validity, SIRET habilitation. | |
| io.github.alefnt/agentpay alefnt/agentpay AI Agent payment protocol on CKB Fiber Network. Zero-gas micropayments with Hold Invoice escrow. | |
| io.github.Alejandro-M-P/git-courer alejandro-m-p/git-courer Full git MCP server for LLM agents — 17 tools, AST annotator, auto-backups, real plumbing. | |
| io.github.AlekseiMarchenko/central-intelligence alekseimarchenko/central-intelligence Persistent memory for AI agents. Store, recall, and share knowledge across sessions. | |
| KubeDrive aleksskoz/kubedrive Your Kubernetes clusters for AI agents through the KubeDrive desktop app, without a kubeconfig. | |
| Pixellint aleksuix/pixellint Validate pixels, postbacks, conversion API payloads, and tracking URLs with spec-backed findings. | |
| RTBlint aleksuix/rtblint Validate OpenRTB bid requests and responses against IAB specs. ARTF, Rust core. | |
| dev.alephgrid/alephgrid alephgrid/alephgrid Read-only MCP access to Alephgrid workbooks: schema cards, reads, SQL, saved queries, receipts. | |
| Alertio alertio/alertio-mcp Real-time DeFi risk data: health factors, liquidations, stablecoin pegs, utilization. No API key. | |
| io.github.Alessandro114/score-mcp-quickstart alessandro114/score-mcp-quickstart Company data for AI agents: search 249M+ companies via the S.C.A.L.A. Score API. | |
| Globestudio alevizio/globestudio Generate dotted-globe maps, share URLs, and embed snippets from chat. |
20,101–20,150 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.