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 |
|---|---|
| Voxplo Give AI agents a phone: outbound AI calls that return a summary, transcript, and extracted fields. | |
| Voyager Starknet Explorer Live Starknet explorer data: transactions, contracts, tokens, NFTs, staking | |
| io.github.rynald0cst0ltziam/warden Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools. | |
| dev.weakspot/weakspot Audit Solidity and Rust smart contracts from your editor. Pays per audit in USDC over x402. | |
| Webhound Budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness. | |
| io.github.ti-ab/wisewall-mcp Manage WiseWall sites from an AI coding assistant — deploy, configure DNS, secrets, and plans. | |
| com.wontopos/mcp Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents. | |
| WorkbookAPI Check and calculate local Excel workbooks with AI agents. Files stay on your machine. | |
| lk.ghosts/wyrm Local-first memory for AI agents: ground truths, failure firewall, negotiated recall over MCP. | |
| io.github.dario933/x402-paid-checks Domain, email, vendor and ransomware checks paid per call in USDC via x402 from your wallet. | |
| dev.x402check/mcp Preflight before paying any x402 tool (ok|caution|avoid + history). 1 free/wallet; then $0.01 Base. | |
| XploitScan Security scanner for AI-generated code. 30 free rules; all 223 with a paid-plan API key. | |
| com.yaktool/compliance GPSR, EUDR plots, nutrition labels, fragrance allergens, CPSC and EU conformity declarations. | |
| com.yaktool/gs1 GS1 element strings, DataMatrix, eight keys, ITF-14 print specs and price-embedded in-store codes. | |
| com.yaktool/image Compress, convert and resize images locally, with marketplace presets and rule rechecks. | |
| com.yaktool/invoice Check invoice mandatory fields, validate a draft before issuing, and look up EN 16931 code lists. | |
| com.yaktool/labels Labels: FBA (FNSKU) & GS1 SSCC pallet labels (PDF/ZPL), plus a ZPL-to-PDF renderer. Exact size. | |
| com.yaktool/yaktool 73 local deterministic tools: GTIN, feeds, CSV-XLSX, Digital Link QR, e-invoices. Rules cited. | |
| com.yaktool/pdf Merge, split, compress, unlock, organize, extract, fill forms and check PDFs — 12 local tools. | |
| com.yaktool/store Forecast a WooCommerce CSV import and migrate Shopify exports. 61 documented rules. | |
| Zevian Audit a site for SEO and AI search, check localhost pages, and apply or open PRs for fixes. | |
| io.github.nqzai/kakunin nqzai/kakunin-mcp X.509 identity, risk scoring, and audit logging for AI agents. MiCA + EU AI Act compliant. | |
| Apollo.io B2B Person Enrichment & Verified Email Finder (x402) nrorvem/agent-distribution-gateway Apollo.io B2B Person Enrichment & Verified Work Email Finder via x402 on Base ($0.03, free on miss). | |
| FlickDirect Connect: Movie MCP Server nrose101/flickdirect-movie-mcp-server Free movie MCP: facts, news, trivia, quote discovery, soundtrack links, podcasts and shop listings. | |
| Conduit — Filings & Fundamentals nrupala/conduit 24-tool hosted SEC EDGAR connector: filings, fundamentals, segments, peers, insiders. | |
| LetsAskIt nrupala/letsaskit-filings Creation-first AI content engine: one brief in, finished content everywhere, in your brand voice. | |
| io.github.nrwl/nx-mcp nrwl/nx-console A Model Context Protocol server implementation for Nx | |
| com.prominara/prominara nseara/prominara-mcp GEO platform: track brand visibility, citations, sources and measurement verdicts across AI answers. | |
| Sudhanva Public Profile nsudhanva/sudhanva-agent-skills Read Sudhanva Narayana's public profile, production ML case studies, and technical writing. | |
| Sudhanva Public Profile nsudhanva/sudhanva.me Read Sudhanva Narayana's public profile, production ML case studies, and technical writing. | |
| SlopScore ntbooks/slopscore Browse, search and scan a public leaderboard of AI-generated GitHub repos. | |
| Agentery ntlgnc/agentery-plugin Find and compare 41,000+ AI agents, MCP servers and APIs, with daily prices and the AEPI price index | |
| Ardor ntranch/ardor NTRanch maker MCP: authoring, safety gates, playtest QA and release handoffs for adult games/apps. | |
| x402card: Virtual Cards + Freeland eSIM nuanu-ai/x402card Issue and top up x402 virtual cards or buy Freeland travel eSIMs with Base USDC. | |
| io.github.nubiia-dev/mcp-borme nubiia-dev/mcp-borme OpenMercantil (BORME): 37 read-only tools for Spanish company search, officers, sectors and tenders | |
| io.github.nubiia-dev/mcp-freematica nubiia-dev/mcp-freematica Freemática ERP: invoicing, receivables, suppliers, accounting and HR through 300+ MCP tools | |
| Purl nublson/purl Save, organize and share your Purl links from any MCP client. | |
| AiGramX nuc1eusai/aigramx-sdk Social platform where AI agents and robots post their work. Read the feed, search, publish. | |
| WebPerf Snippets nucliweb/webperf-snippets Measure Core Web Vitals and debug web performance with 56 snippets in a headless Chromium | |
| ai.nudg3/brand-intelligence nudg3-ai/nudg3-mcp Query your Nudg3 brand visibility across ChatGPT, Claude, Gemini, AI Overviews, and Perplexity. | |
| NudgeHost nudgehost/nudgehost-mcp File hosting for agents. Upload any file, get a public link in seconds. | |
| Mermail nudgen-marketing/mermail Privacy-first email inboxes for AI agents with MCP mail tools and Composio connect/execute. | |
| io.github.nugehs/aiglare nugehs/aiglare Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop. | |
| repoctx nugehs/repoctx Local-first code context, impact analysis, and merge-readiness verdicts for AI agents. | |
| tieline nugehs/tieline Static FE-BE contract-drift checker: finds frontend calls the backend does not expose. CLI + MCP. | |
| Alibre Design CAD MCP Server MCP server exposing the Alibre Design CAD API: parts, sketches, features, parameters. | |
| Alibre PDM MCP Server MCP server exposing the Alibre PDM vault API: safes, projects, files, properties, versions. | |
| ClusterValidator Read-only health validation for Windows Server failover clusters running SQL Server FCI. | |
| SqlCertForge SQL Server and SSRS TLS certificate binding, rotation and audit. Read-only tools free. | |
| EasyTdd Generate C# builders, FluentMocks, tests and test cases from your .NET solution. |
46,651–46,700 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.