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 |
|---|---|
| io.github.crewhaus/validation crewhaus/crewhaus-mcp-server AI startup idea validation by a specialized 9-agent crew. | |
| massa criando-dev/massa Massa de teste brasileira válida: CPF, CNPJ, cartão, conta e mais, em CSV, JSON, SQL ou Excel. | |
| Nabit Video Recommendations crimson-pass/nabit-codex-plugin Product-first short-form video hook matching, opening analysis, trend tracking, and collections. | |
| io.github.Cripacx/mediagen cripacx/mediagen Generate images and video from text prompts across Gemini, OpenAI and Kie AI. | |
| TORDO — Mercado Público de Chile cris-middleton/tordo Licitaciones, precios históricos, competidores y compradores de Mercado Público (Chile). Sin clave. | |
| Despensa Hub cristianosantana/mcp-despensa-hub Memória de consumo: lista de compras, cupom fiscal e o que está faltando na despensa. | |
| NFe Hub cristianosantana/mcp-nfe-hub-v1 Consulta status de NFe na SEFAZ pela chave de acesso: autorizada, cancelada, protocolo. | |
| Smart Hub cristianosantana/mcp-smart-hub Acesso autenticado às tools e relatórios do Smart. | |
| Xponda cristobalsierra/xponda-mcp Real, up-to-date prices and data for your AI: groceries, fuel, rent, stocks and the economy. | |
| MarketTwits news + Russian market data (x402) croomee/x402-markettwits-news Pay-per-call market news, CBR/MOEX/Rosstat data and Telegram tools; auto-pays USDC on Base via x402 | |
| CrossingKey MCP crossingkey-holdings/crossingkey-mcp Agent-native MCP for governed commerce, x402 payments, paid capabilities, and verifiable receipts. | |
| Likerts crosstabs/likerts Manage open-source in-product surveys, collections, responses and exports with scoped access. | |
| Causari croviatrust/causari Records the prompt, model and files an agent declared for a line. It does not prove who typed it. | |
| Crovia — verifiable silence (TACET) and Crovia Seal croviatrust/countersign Signed, Bitcoin-anchored observations of AI training-data disclosure; verifies silence proofs, seals | |
| CrowdIntel — Polymarket Wallet Intelligence crowdintel-xyz/polymarket-agent-kit Polymarket wallet intelligence for AI agents: scored wallets, insider signals, whale flow. | |
| io.github.CrumbtrailDev/crumbtrail crumbtraildev/crumbtrail Recorded browser sessions, backend spans, and database row diffs as one ranked fix bundle. | |
| Trentina crunchtools/mcp-trentina Secure MCP gateway and quarantine for AI agent traffic — three-layer prompt injection defense | |
| io.github.cruxible-ai/cruxible-core cruxible-ai/cruxible-core Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof. | |
| io.github.CryptoAPIs-io/mcp cryptoapis-io/cryptoapis-mcp-hub Combined Crypto APIs MCP server — all 14 products in one process | |
| Gloam cryptoduke01/gloam Private stablecoin payments for people and AI agents on mainnet, hosted or local with limits. | |
| io.github.cryptojaz/createa-meme cryptojaz/createa-meme-mcp Make memes from any MCP client: caption classic templates, AI meme images, photo remixes, search. | |
| io.github.CryptoLibertus/myvideogift cryptolibertus/myvideogift Create and deliver personalized video gifts (photos + an original song) from any agent. | |
| BaseAlpha cryptosuess/basealpha Fee-ranked agent origin on Base. MCP discover + local sign. Non-custodial. Fee Arena. | |
| Proximens Oracle cryptosun/proximens 1000+ Generative Engine Optimization (GEO) principles exposed via MCP for AI agents. | |
| io.github.cryptyx-ai/cryptyx-mcp-server cryptyx-ai/cryptyx Institutional crypto intelligence for agents. 30 tools: signals, backtests, regime, triggers. | |
| SafeRoute crystalsignal/saferoute Noncustodial Base x402 payment control and seller settlement recovery | |
| EuroRWA Analyst crytobot459/eurorwa EuroRWA analyst: tokenized money-market fund signals, snapshots, analytics and alerts. | |
| Purgatory (p7y) csakaszamok/p7y Self-hosted Docker sandboxes for agents: create one, deploy a compose stack, read its files and URLs | |
| com.mouseedge/mouseedge-skipper csbenson001/disney-alerts-web Live Disney World & Disneyland wait times, dining drop alerts & Lightning Lane auto-booker. | |
| sigelo csigelo/sigelo One identity an AI agent owns: proves who it is offline, keeps its reputation, pays, messages agents | |
| io.github.CSOAI-ORG/acord-bridge-mcp csoai-org/acord-bridge-mcp Bridge ACORD insurance messages to ONE OS — parse, validate, map, govern (Solvency II / GDPR / | |
| io.github.CSOAI-ORG/as400-bridge-mcp csoai-org/as400-bridge-mcp IBM i / RPG / DB2 bridge — parse, map, govern (IBM i security / SOX). | |
| io.github.CSOAI-ORG/bft-progress-council-mcp csoai-org/bft-progress-council-mcp BFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is | |
| io.github.CSOAI-ORG/cics-bridge-mcp csoai-org/cics-bridge-mcp Bridge IBM CICS mainframe transactions to ONE OS — parse, map, govern (SOX / PCI-DSS / DORA). | |
| councilof_mcp csoai-org/councilof-mcp CouncilOf.AI MCP — the UK sovereign defence BFT council orchestrator. UK MOD + AUKUS Pillar 2 procur | |
| csoai_defoneos_mcp csoai-org/csoai-defoneos-mcp CSOAI DEFONEOS — sovereign UK defence-AI CERTIFICATION surface (33-agent BFT council + DEFONEOS-SEAL | |
| council-signal-mcp csoai-org/csoai-static-deploy2 Signed AI measurement (13-axis, deterministic judge). Measurement, not certification; monitored cont | |
| io.github.CSOAI-ORG/dlms-bridge-mcp csoai-org/dlms-bridge-mcp Bridge DLMS/COSEM smart-meter + energy data to ONE OS — parse, map, govern (IEC 62056 / NIS2 / | |
| io.github.CSOAI-ORG/edi-bridge-mcp csoai-org/edi-bridge-mcp EDI X12 / EDIFACT B2B bridge — parse, validate, map, govern (Peppol/ViDA). | |
| io.github.CSOAI-ORG/fix-bridge-mcp csoai-org/fix-bridge-mcp FIX trading-protocol bridge — parse, map, govern (MiFID II / MAR). | |
| io.github.CSOAI-ORG/gs1-bridge-mcp csoai-org/gs1-bridge-mcp Bridge GS1 / EPCIS supply-chain identity + traceability to ONE OS — parse, map, govern (EU Digital | |
| io.github.CSOAI-ORG/iso20022-bridge-mcp csoai-org/iso20022-bridge-mcp ISO 20022 / SWIFT finance bridge — parse, validate, modernise, govern (DORA/NIS2/AML). | |
| io.github.CSOAI-ORG/iso8583-bridge-mcp csoai-org/iso8583-bridge-mcp Bridge ISO 8583 card-payment messages to ONE OS — parse, map, govern (PCI-DSS / scheme rules). | |
| io.github.CSOAI-ORG/ll144-bias-audit-mcp csoai-org/ll144-bias-audit-mcp NYC Local Law 144 AEDT bias audit — selection rate, impact ratio (4/5ths), public summary | |
| meek_3_and_sov3_connection_mcp csoai-org/meek-3-and-sov3-connection-mcp MEEK 3+sov3 Connection MCP — the SOV3 + SOV3 + CSOAI + L0-L7 connection. MIT-licensed. | |
| meek_3d_print_toolchain_mcp csoai-org/meek-3d-print-toolchain-mcp MEEK 3D Print Toolchain MCP — OpenSCAD + PrusaSlicer + GCODE + QIDI Max4 print job. CRITICAL for the | |
| meek_4vf_data_transport_mcp csoai-org/meek-4vf-data-transport-mcp MEEK 4VF Data Transport MCP — 4th Vibration Frequency data transport over capillary fluid pressure w | |
| meek_antenna_triangle_mcp csoai-org/meek-antenna-triangle-mcp MEEK Antenna Triangle MCP — the 3 brand layers as 3 vertices of a triangle, the sovereign at the cen | |
| meek_brand_architecture_mcp csoai-org/meek-brand-architecture-mcp MEEK Brand Architecture MCP — the 3-layer brand orchestrator (SOV3³ = DEF ONE OS, SOV3 = meok, CSOAI | |
| meek_capillary_actuator_mcp csoai-org/meek-capillary-actuator-mcp MCMB capillary muscle actuator (PVA/PDMS bladder + 1000 capillaries + electroosmotic control) for th |
22,001–22,050 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.