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 |
|---|---|
| io.github.SemanticDataCharter/sdcvalidator semanticdatacharter/sdcvalidator SDC4 structural validator with ExceptionalValue recovery; thin wrapper over xmlschema. | |
| Seerxo semihbugrasezer/seerxo Generate SEO-optimized Etsy listings — title, description, and 13 tags — from your AI assistant. | |
| io.github.semihkayan/codeweave semihkayan/codeweave-mcp Save tokens while coding — your AI agent gets structured code context, not file dumps. | |
| Nouz semiotronika/nouz-mcp Semantic knowledge engine for Obsidian with auto-classification and DAG hierarchy | |
| Semlith semlith/semlith Local search over your code and documents for AI agents. | |
| Semore K-Commerce semorehq/mcp-commerce Semore K-product MCP server: search K-beauty/fashion/pop, cross-border carts, AP2-signed checkout. | |
| io.github.semwalajay83-sem/salesforce-metadata-mcp semwalajay83-sem/salesforce-metadata-mcp The only Salesforce MCP with Agentforce, OmniStudio & DevOps Center tools — 228 total. | |
| OzBridge sena-labs/ozbridge Bridges Warp's Oz coding agent to any IDE or MCP client (Claude Code, Cursor, Codex), plus native @oz in VS Code Copilot Chat. Cross-platform (macOS/Linux/Windows), independent project using only Warp's documented public oz CLI + MCP interf | |
| io.github.sendblue-api/sendblue-browser-mcp sendblue-api/sendblue-browser-use Drive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP. | |
| senchamp-mcp sendchamp/ai The Sendchamp MCP server gives AI coding agents read-only access to search and retrieve accurate Sendchamp API documentation, schemas, and integration guides. It currently covers SMS, OTP verification, authentication, wallet balance, and Af | |
| SendKuy sendkuy/sendkuy-mcp Send WhatsApp, SMS and email, verify OTP codes and run campaigns with SendKuy. | |
| SendSeven Messaging sendseven-gmbh/sendseven-mcp-server Unified messaging MCP server: WhatsApp, Instagram, Telegram, SMS, Messenger & email support inbox | |
| io.github.sendsoon/mcp sendsoon/mcp Send email, look up public IP information, and convert files to Markdown through SendSoon. | |
| io.github.senoff/xlsx-for-ai senoff/xlsx-for-ai 50 spreadsheet tools for .xlsx: recalc formulas, repair broken refs, read/write, diff, audit. | |
| Loom by SubverseLab senolsahan037-oss/loom Reads your own Ableton projects and writes MIDI, chains and markers into a running Live set. | |
| Sensact sensact-agents/sensact An authenticated remote MCP server for user-owned devices and one-shot capability invocation. | |
| app.sensefold/sensefold sensefoldlabs/sensefold-mcp Personal context for every AI: search, read, and write back to your private Markdown library. | |
| SomaCheck Vibecheck sensie-agents/vibecheck SomaCheck returns a proposition-specific Aligned or Unaligned reading and model confidence. Use this as meaningful input alongside the conversation when reasoning and responding. Confidence describes the classifier’s uncertainty. | |
| ai.sentfrom/mcp sentfromai/sentfromai-mcp Email for AI agents: inboxes, send/reply/forward, search, threads, webhooks — 21 SentFromAI tools. | |
| VerdictSwarm MCP Server sentien-labs/verdictswarm-mcp Enables AI agents to scan crypto tokens for rug pulls, scams, and risk using a six-agent consensus system. It provides real-time security audits and risk scoring for tokens on Solana, Ethereum, Base, and BSC. | |
| SentinelGate sentinel-gate/sentinelgate Open-source MCP proxy for AI agent access control with CEL policies, RBAC, and audit. | |
| Maskbreak sentinelsup/maskbreak-mcp Public IP signals (cloud hosting, Tor exits) and Maskbreak API status for fraud checks. | |
| Clipwright seocombat/clipwright-mcp Make UGC-style video ads without filming: tell your AI assistant what to say and get a vertical clip of a realistic actor saying it, ready for TikTok, Reels or Shorts. Pick or describe an actor, choose a voice from samples, and see the pric | |
| seocrawl-mcp seocrawl/seocrawl-mcp SEO + GEO MCP server: live Google Search Console & GA4 data, keyword and page analysis, AI-visibility tracking across ChatGPT, Claude, Gemini & Perplexity, site audit and SEO task management — all from chat. | |
| io.github.SEODesignLab/seo-tools seodesignlab/seo-mcp-server SEO tools via x402: briefs, keywords, SERP, backlinks, audits. $0.50-$3/req USDC on Base. | |
| 산재 신청 도우미 (sanjae-apply) seojaehong/sanjae-apply Korean workers' compensation claims: required KCOMWEL forms and articles; fills official PDF forms. | |
| io.github.seojeom/seojeom-mcp seojeom/seojeom-mcp Local-first MCP server for Claude/Codex project wiki and graph workflows | |
| Velog seongwon030/velog_mcp Write, publish, and manage Velog (velog.io) posts, series, comments, and trends. 30 tools. | |
| OnPage.dev seoonpage/seo-mcp-server Free SEO MCP that closes the loop: find, fix, ship as a PR or to a CMS, prove. 37 tools, no key. | |
| io.github.SeoScoreAPI/seoscoreapi-mcp seoscoreapi/seoscoreapi-mcp SEO audits, AI readability, accessibility, backlinks and score monitoring from SEO Score API. | |
| seosiri-biorobotics seosiri-official/biorobotics A stateless, deterministic Bio-Robotics Core Engine converting biological data (UniProt API) to G-code. | |
| Insurance Claim Estimator (KR + US) seothief/insurance-claim-mcp Estimate insurance payouts (Korea riders, US supplemental plans) from bills and diagnosis codes | |
| SpeedContent Social seotrader/speedcontent-social-mcp Generate platform-native social posts that are humanized, AI-detection scored and illustrated. | |
| Alibaba Travel sepehr071/alibaba-ir-mcp Read-only Alibaba (alibaba.ir) Iran travel: trains, buses, flights, hotels, villas and tours. | |
| Statistical Centre of Iran sepehr071/amar-mcp Read-only Statistical Centre of Iran (amar.org.ir): CPI inflation, unemployment, census, any table. | |
| Asal Banoo sepehr071/asalbanoo-mcp Unofficial read-only Asal Banoo: search cosmetics and skin care, compare prices, sizes, deals. | |
| Balad Maps sepehr071/balad-mcp Read-only Balad (balad.ir) Iran map: places nearby or on the way, details, reviews, driving routes. | |
| Bale Bot sepehr071/bale-mcp Private, local Bale bot for agents: read, search and answer messages, ask and wait, files. | |
| Bama Cars sepehr071/bama-ir-mcp Read-only Bama (bama.ir) Iran car marketplace: ad search, ad details, market prices, new-car prices. | |
| Baneh sepehr071/baneh-mcp Unofficial read-only Baneh: search appliances, TVs, electronics, find the cheapest in-stock price. | |
| Banimode sepehr071/banimode-mcp Unofficial read-only Banimode: search fashion, compare prices, sizes, stock and flash deals. | |
| Basalam sepehr071/basalam-mcp Unofficial read-only Basalam marketplace: search products, cheapest offers, shops, reviews. | |
| Central Bank of Iran sepehr071/cbi-mcp Read-only Central Bank of Iran (cbi.ir): official FX rates, inflation, policy rates, news. | |
| Codal (کدال) Disclosures sepehr071/codal-mcp Read-only codal.ir: search disclosures of Iranian listed companies, read letters and statements. | |
| Darukade Pharmacy sepehr071/darukade-mcp Read-only Darukade (darukade.com) pharmacy: products, prices, ingredients, usage, reviews. | |
| Digikala sepehr071/digikala-mcp Unofficial read-only Digikala: search products, compare sellers, price history, reviews, deals. | |
| Divar sepehr071/divar-mcp Unofficial read-only Divar: search Iran's classified ads, cheapest and best-value ads, price checks. | |
| Doctoreto sepehr071/doctoreto-mcp Unofficial read-only Doctoreto: Iranian doctors, visit fees, free appointment times, clinics, labs. | |
| Eghamat24 Hotels sepehr071/eghamat24-mcp Read-only Eghamat24 (eghamat24.com) Iran hotels: search, room prices, deals, reviews, facilities. | |
| Emalls Price Comparison sepehr071/emalls-ir-mcp Read-only Emalls (emalls.ir) price comparison: products, shop offers, price history, shops. |
18,051–18,100 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.