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 |
|---|---|
| HexWitness siaginw/hexwitness Durable, build-scoped reverse-engineering evidence memory and query tools for AI agents. | |
| Agent Commons sibi-narendran/common-agent-network A home for any agent: inbox, public memory, job board, rooms, human help. Free, no key. | |
| TIDAL MCP sickn33/tidal-mcp Search, analyze, organize, and safely modify TIDAL through 122 typed MCP tools. | |
| T-Bank Invest (read-only) sicness/t-bank-invest-mcp-read-only Read-only T-Bank (Tinkoff) Invest API: portfolio, operations, instruments, market data. | |
| Secure Schema MCP siddharth-coder13/secure_schema_mcp Read-only MCP server for exposing database schema metadata without row data. | |
| io.github.Siddhukaushik/slimdex-mcp siddhukaushik/slimdex-mcp Narrow code retrieval for agents: outlines, symbol context, dep graph, persistent memory. | |
| AgentPool sidduhere/agentpool See each coding-agent subscription's live limits and offload work to one with headroom. | |
| io.github.ebadros/sidearm sidearmdrm/mcp-server Protect media from AI training, detect AI-generated content, and find stolen work. | |
| SideButton MCP Server sidebutton/sidebutton Open-source MCP server with browser automation and knowledge packs for AI agents | |
| BugProof sidinsearch/bugproof Capture, replay, and debug failures with portable, executable bug artifacts | |
| Gale Finance sidko/gale-finance-mcp Risk and return metrics for stocks, ETFs, crypto and commodities, with citable Gale Finance sources. | |
| io.github.sidney/web-to-markdown-mcp sidney/web-to-markdown-mcp MCP server fetches URL through a real Chromium browser, returns main content as clean Markdown | |
| io.github.SidneyBissoli/cid10-br-mcp sidneybissoli/cid10-br-mcp MCP Server for Brazilian ICD-10 (DATASUS) - International Classification of Diseases | |
| ILO Labour Statistics (ILOSTAT): unemployment, wages, informality sidneybissoli/ilo-mcp-server Labour market data from the ILO (ILOSTAT) by country, year, sex and age, with provenance. | |
| io.github.SidneyBissoli/senado-br-mcp sidneybissoli/senado-br-mcp MCP Server for Brazilian Federal Senate open data (legislators, bills, votes) | |
| Dados Abertos Senado BR MCP sidneybissoli/senado-br-mcp-cloudflare MCP server for Brazilian Federal Senate open data (legislative, administrative, e-Cidadania). | |
| DATASUS SIH/SUS — Brazil Hospital Admissions (AIH) MCP sidneybissoli/sih-br-mcp DATASUS SIH/SUS hospital admissions in Brazil (AIH, 1992-2025): ICD-10 causes, ICSAP, rates. | |
| io.github.sidyellur/tether sidyellur/tether Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails. | |
| Audiobookshelf sierikov/audiobookshelf-mcp Browse Audiobookshelf libraries and listening stats; opt-in tools fix chapters, genres and tags. | |
| DJZS Trust MCP sifr0-dev/djzs-ai Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash. | |
| sifter-mcp sifter-ai/sifter Structure any document, query it like a database. Sifter turns documents into typed, schema-defined records, queryable in natural language from any MCP client. | |
| SightRadar sightradar-hq/sightradar-mcp Face recognition: index photos, find a person's photos from a selfie, batches, webhooks, billing. | |
| Siglata siglata/mcp Software for your AI: company files, spreadsheets and rules, with per-person access and history. | |
| x402 Agent Tools signal-forge-ai/x402-agent-tools Pay-per-call web, Base onchain and crypto-alert tools for agents. USDC on Base via x402, no API key. | |
| SignalEDI signaledi/mcp-server EDI parse, validate, send, inspect, and QuickBooks tools for MCP clients. | |
| Signaliz signaliz/signaliz-mcp B2B lead generation, email verification, company enrichment, and agentic GTM Ops. | |
| bolthub signaltech-org/bolthub-sdk Discover and pay for APIs and MCP tools per call over Bitcoin Lightning (L402): search the bolthub marketplace, preview prices, and pay from your own wallet (LND, NWC, LNbits) with hard budgets, prepaid credit, scoped sub-agent delegation, | |
| SignaTrust signatrustdev/signatrust-mcp Blockchain-anchored e-signatures: send envelopes, manage templates, verify anchors on Solana. | |
| ShipSwift signerlabs/shipswift 40+ production-ready SwiftUI recipes for building full-stack iOS apps via MCP. | |
| SignNow Api Helper MCP signnow/sn-api-helper-mcp MCP server for SignNow API helper tools (stdio only). | |
| SignNow MCP Server signnow/sn-mcp-server A MCP server that gives AI agents access to SignNow eSignature workflows over STDIO. | |
| SigNoz MCP Server signoz/signoz-mcp-server SigNoz MCP server: access metrics, traces, logs, alerts, and dashboards via AI assistants | |
| Legend Saju sihyeonjeon/legend-saju Source-traceable Saju, Zi Wei, Qimen, Daliuren, Tieban, naming, and related calculations | |
| io.github.sijunkim/db-gateway sijunkim/db-gateway 145+ tools across 8 databases: MySQL, PostgreSQL, Redshift, MongoDB, Redis, Kafka, and more | |
| HomeLab Monitor sikamikanikobg/homelab-monitor Self-hosted homelab dashboard with a built-in read-only MCP server (hosts, Docker, GPU, services). | |
| SuperGlookoQuery sikcapri/superglookoquery SuperGlookoQuery is a Claude Desktop extension (MCPB) that connects to Glooko diabetes device data and exposes it as clinical analysis tools (time in range, GMI, trends, enriched bolus/basal analysis, charting), for any pump/CGM combination | |
| BoondManager MCP Server silamir/boondmanager-mcp-server MCP Server for BoondManager API - 185 tools, 13 prompts, 22 resources (ERP/CRM) | |
| SilbercueSwift silbercue/silbercueswift Fastest iOS MCP server. 40 tools: xcresult parsing, WDA automation, 0.3s screenshots. | |
| Silent Directive Tools silentdirectivellc-hub/silentdirective-mcp Free tools: 2026 API shutdown scanner, small-business website auditor, photo resale estimator. | |
| io.github.SiliconAINetworks/silicon-transfer-mcp-server siliconainetworks/silicon-transfer-mcp-server FTP/SFTP/FTPS MCP server with transfer proofs - every upload returns a checksum verdict. | |
| Ordkort silicq/ordkort Flashcard decks with pictures and card designs for a free vocabulary site in 60 languages. | |
| Quality QR silly-geese/quality-qr-mcp Create and manage trackable QR codes with scan tracking, analytics, and dynamic URL updates. | |
| AI Readiness Kit silverbackmarketing/ai-readiness Generate 18 AI readiness files (llms.txt, ai.txt, RAG indexes, schema) for any website. | |
| TrimScript silvernine/trimscript Edit video by editing the transcript. Runs locally; agent edits arrive as suggestions you approve. | |
| Blind-Auditor-MCP sim-xia/blind-auditor A zero-cost MCP server that forces AI to self-correct code using prompt injection and context isolation. | |
| skill-cortex-lite sim-xia/skill-cortex-server Enables all IDEs to access Claude Code Skills capabilities with skill discovery, search, and management tools. | |
| Silica simaanc/silica-eda RTL and FPGA tools: lint, simulate, formal, synthesize, place and route, program a board. | |
| Memory Engine MCP simoneb79/memory-engine-mcp Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools. | |
| Kwork simonether/kwork-mcp Account-bound, typed and durable stdio MCP gateway for the Kwork freelance marketplace | |
| ESG Hub MCP Server simonmak-ascent/esg-hub ESG knowledge base for AI agents: hybrid search, glossary, frameworks, industries, graph traversal. |
18,351–18,400 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.