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 |
|---|---|
| Ledgy harholinsky/ledgy-mcp Log, query, and edit expenses, budgets, and accounts in Ledgy from any MCP-compatible AI assistant. | |
| ai.smithery/HARJAP-SINGH-3105-splitwise_mcp harjap-singh-3105/splitwise_mcp Manage Splitwise balances, expenses, and groups from your workspace. Fetch friends and recent acti… | |
| YouTube Studio MCP harper-labs/youtubestudiomcp Hosted MCP for YouTube Studio: uploads, metadata, playlists, comments, analytics, captions. | |
| Harris Boat Works - Mercury Repower harrisboatworks/mercury-builder-pro Live Mercury outboard data and CAD quote builder from a Mercury Platinum Dealer in Ontario. | |
| Memoize — persistent agent memory harrisonford/memoize Persistent cross-session memory shared by Codex, Claude Code, ChatGPT, and other AI agents. | |
| Agency Autopilot harrisonjdahl3/agency-mcp-plugin Run client marketing from your AI assistant, or let Autopilot: Google Ads, GA4, SEO, Meta, CRM | |
| MOFi harrisonmo/mofi Query MOF database survey metadata and connect a bounded MOFi scientific workspace. | |
| Mode VC LLM Token Economics & Model Release Velocity harrybuild/modevc-ai-charts-mcp Query empirical frontier LLM release velocity, inference token deflation, and enterprise AI spend. | |
| Mode VC: AI Venture Research Charts & Investor Atlas harrybuild/modevc-mcp Query 38 empirical AI market charts, evaluate distribution defensibility, and search 3,650+ VCs. | |
| Mode VC Startup Distribution Moat & Valuation Benchmarks harrybuild/modevc-valuation-benchmarks-mcp Evaluate startup distribution moat defensibility (Tier 1-5) and pre-seed valuation dispersion. | |
| io.github.harsh-chandak/shadowjoin harsh-chandak/shadowjoin Measure the matches your exact join is silently dropping, and get the rule that fixes each. | |
| Harshith Nayaka L portfolio harshithnayakal/my-portfolio Read-only MCP access to Harshith Nayaka L's portfolio: profile, case studies, FAQ and guides. | |
| Facebook Ads Library Scraper (Apify) harshmaur/apify-facebook-ads-library-scraper Export Meta ads with copy, media, dates and audience data. No Facebook login. From $0.40/1k | |
| YouTube Transcript Scraper (Apify) harshmaur/apify-youtube-transcript-scraper YouTube transcripts with timestamps, SRT/VTT and translation. No YouTube login. From $4/1k | |
| iLook Face Analysis harshul1404/ilook Analyze user-submitted face photos with a complete report or 13 focused face-analysis tools. | |
| io.github.hartemyaakoub/ambulancedz-mcp hartemyaakoub/ambulancedz-mcp Find ambulance drivers across Algeria's 69 wilayas — nearest, verified, reviews, cost, dialysis. | |
| Mirofy hasan-laraib/mirofy Ask a repository what depends on what. Every answer cites the file, line and commit it came from. | |
| NeuralNg Angular UI Expert MCP hasanaydin7/neuraltech Angular UI expert for NeuralNg discovery, composition, validation, icons and project-aware themes. | |
| DataSocial hashfunction-dev/datasocial-mcp Query a TikTok data warehouse (creators, videos, sounds, daily history) with read-only SQL. | |
| HOL Guard hashgraph-online/hol-guard Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. | |
| Hashgrid DNA (local) hashgrid-labs/sdk Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors. | |
| Arkon Vault havix0101/arkon-vault-connector Private projects, preflight, decisions, and handoffs that keep work continuous across AI tools. | |
| ARN Konsumenttvist hawaleska/arn-konsumenttvist-mcp Svensk MCP-server för sökning och analys av ARN-beslut och konsumenttvister. | |
| ai.haymon/database haymon-ai/database Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite | |
| phpgraph hbenabdallah/phpgraph Knowledge graph of a PHP codebase by static analysis: calls, routes, buses, layers, impact | |
| Computer-Use Agents API hcompai/hai-agents-python Run and manage H Company's Computer-Use Agents from any MCP client. | |
| Omnis Venture Intelligence MCP hcs412/ventureautomated Venture intelligence for autonomous agents with discovery, scoring, and workspace automation. | |
| Coach Watts hdkiller/coach Remote MCP server for training, nutrition, wellness, and performance data with OAuth 2.0. | |
| io.github.headlessherm-creator/json-mender-mcp headlessherm-creator/json-mender-mcp Local MCP server: JSON repair, regex testing, JSON-Schema validation for AI agents. | |
| Apify data tools: Threads, Yelp, transcripts, Trends, Airbnb, Jumia headply/apify-data-tools-mcp Web data tools: Threads, Yelp, YouTube/TikTok transcripts, Google Trends, Airbnb, Jumia prices. | |
| io.github.healersfind-alt/organic-web-checker healersfind-alt/organic-web-checker-mcp USDA NOP organic compliance checks — operation websites vs live OID certificate data. | |
| Clarity by Health AI healthai-hq/clarity-project Condition-aware ingredient and product checks for agents, with evidence tiers and citations. | |
| Constat MCP — FDA Device Evidence Lifecycle healthai-hq/fda-risk-radar FDA and CMS evidence for AI medical devices: 510(k), postmarket, reimbursement, and compliance. | |
| Heard Friends heardlabs/heard-mcp Your coding agents' hours this month, your friends board, and invites you approve. | |
| Altscan explorers heathermhuang/altscan Keyless, read-only BNB Chain and Ethereum data: transactions by hash, tokens with a lookalike check | |
| io.github.heavyblotto/caelus-mcp heavyblotto/caelus 34-tool Caelus MCP for validated astrology: charts, transits, Vedic, facts, sky view, synthetic. | |
| io.github.hedgerow-dev/hayward hedgerow-dev/hayward Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load. | |
| io.github.Hei33enberg/voice-truthgate-mcp hei33enberg/voice-truthgate Honest voice authenticity for AI agents: enrol a voice, verify a call clip. Signal, not verdict. | |
| CiteVahti heidihelena/citevahti Checks whether each cited source supports the claim it backs. Blinded human-first, local-first. | |
| Vahtian heidihelena/vahtian Freeze a corpus, check it for drift, keep a hash-chained audit ledger. Local-first, stdlib-only. | |
| io.github.Heirloomz/oral-heritage-index heirloomz/inktree-social-tools Authoritative cited answers about saving family stories. Published by InkTree. | |
| io.github.heisee/letsclarify-mcp heisee/letsclarify Human-in-the-Loop API: AI agents create forms, share URLs with humans, get JSON back. | |
| Helfer & Profi helferundprofi/helfer-und-profi Free German neighborhood marketplace: search local help requests and providers by postal code. | |
| io.github.helinakdogan/agent-magnet helinakdogan/magnet-gateway Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex. | |
| PubFi MCP helixbox/pubfi-docs Use MCP 2026-07-28 discovery or 2025-11-25 initialize to list and execute PubFi routes. | |
| GopherHole Agent Hub helixdata/gopherhole-clients Standards-based A2A hub. One MCP connection to thousands of agents, with shared persistent memory. | |
| io.github.HelloSafe/travel-insurance hellosafe/travel Compare travel insurance quotes from 15+ insurers — Schengen, WHV, students, long stays, seniors. | |
| agentpay hellotravisss/agentpay Enforced budgets for agents paying x402 APIs: the gateway holds the wallet, not the agent. | |
| Anti-Vibe hellstellar/anti-vibe Read coding-agent output one sentence at a time, skim it by heading, or speed-read it. | |
| Helvetic Research helvetic-research/helvetic-research Research-only MCP server: your AI as a quant research desk. 90 tools, no trades, no brokers. |
23,701–23,750 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.