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 |
|---|---|
| codemem kunickiaj/codemem Persistent memory MCP server that captures coding session context and automatically injects relevant memories into prompts using hybrid search for OpenCode and Claude Code. | |
| MySQL (security-first) kurok1/mcp-server-mysql Security-first MySQL MCP server with AST validation, table whitelist, schema resources, and audit. | |
| io.github.kurovu146/memory-fts kurovu146/claude-memory-mcp Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking | |
| context-doctor kushalp1/context-doctor Cut LLM agent token use in Claude Code, Cursor, Codex, Gemini CLI. Local, no API key. gAI Ventures. | |
| dev.corlabs/mcp kushshah12/cor-mcp Scored, maintainable locators from a live page for AI coding agents, with checks and repairs. | |
| io.github.tspicer/amazon_ads_mcp kuudoai/amazon_ads_mcp Amazon Ads API MCP server for Amazon Advertising API | |
| Amazon knowledge retrieval MCP server (Amazon Agent Atlas) kuudoai/amazon-agent-atlas-mcp MCP retrieval server for indexed Amazon Ads, Seller Central, and Vendor Central knowledge. | |
| Amazon listing image and video MCP server (Amazon Agent Iris) kuudoai/amazon-agent-iris-mcp MCP server that creates Amazon listing images and product video from live catalog data. | |
| Amazon Seller Central MCP server (Amazon Selling Partner MCP) kuudoai/amazon-selling-partner-mcp MCP server for the Amazon Selling Partner API: orders, listings, pricing, FBA, and reimbursements. | |
| Amazon Vendor Central MCP server (Amazon Vendor Central MCP) kuudoai/amazon-vendor-central-mcp MCP server for Vendor Central: orders, fulfillment, invoices, and retail analytics. | |
| io.github.KuvopLLC/better-bear kuvopllc/better-bear MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit | |
| Purroxy kuvopllc/purroxy2 Give Claude secure access to your accounts. | |
| MyFatoorah MCP kuwaitdevs/myfatoorah-mcp Safely connect AI agents to MyFatoorah payments, invoices, payment methods, and refunds. | |
| kvasir — verifiable German, Austrian, Swiss & EU law kvasir-legal/kvasir-mcp Resolve, search and verify legal citations against the official sources, with provenance. | |
| strava-mcp kw510/strava-mcp An MCP server that integrates Strava OAuth for remote connections, enabling users to authenticate with their Strava account and access Strava data through the MCP protocol. | |
| x402 Micropayments MCP kwizzlesurp10-ctrl/x402-mcp Pay-per-call US city property compliance and Base tx checks, paid in USDC on Base via x402. | |
| x402 Oracle kwizzlesurp10-ctrl/x402orcle Paid x402 help: debug 402 errors, review MCP manifests, rewrite Bazaar listings. USDC on Base. | |
| ai.smithery/kwp-lab-rss-reader-mcp kwp-lab/rss-reader-mcp Track and browse RSS feeds with ease. Fetch the latest entries from any feed URL and extract full… | |
| checkyourself kyanitelabs/checkyourself Local-first production-readiness MCP server for AI-built apps. It runs read-only checks, produces an evidence-based readiness score, and guides fixes before launch. | |
| Run402 kychee-com/run402 x402 pay-per-call infra for agents: $0.03 image generation, Postgres, auth, storage, functions. | |
| OpenLookup kyisaiah47/openlookup OpenLookup: eleven keyless lookups. Model pricing, dep health, stack cost, registries. | |
| Kylas CRM kylastech/kylas-crm-mcp-server MCP server for Kylas CRM: create, search, and manage leads. Requires KYLAS_API_KEY. | |
| io.github.KylinMountain/web-fetch-mcp kylinmountain/web-fetch-mcp MCP server for web content fetching, summarizing, comparing, and extracting information | |
| Kyma API kyma-api/kyma-mcp-plugin Live model catalog with prices and measured uptime, rankings, credits and spend, spend-capped chat. | |
| National Parks MCP Server kyrietangsheng/mcp-server-nationalparks Provides real-time information about U.S. National Parks through the NPS API, enabling users to search parks, check details, alerts, visitor centers, campgrounds, and upcoming events. | |
| Kyrodata — Brazil Trade, Crop & Commodity Data kyrodata/mcp Brazil exports/imports by HS code (ComexStat), soybean, coffee, supply-demand, climate, forecasts | |
| io.github.kyrylopr/lenspr kyrylopr/lenspr Stop vibecoding blind. Code graph so your AI stops breaking things across your codebase. | |
| Kybase kyrzin/kybase Self-hosted knowledge base that gives AI agents persistent memory over MCP. 18 tools covering notes, folders, tags and trash; hybrid search combining pgvector embeddings with bilingual full-text ranking via RRF; [[wikilink]] graph traversal | |
| VerifyAPI — fact-check with signed receipts kythekitty/verifyapi-mcp Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations. | |
| Kythene kythene/kythene Your AI's work, reviewed by your team, remembered - shared artifacts with review, plus team memory. | |
| shell-use kyuheon-kr/shell-use Let agents use the shell like a human. | |
| io.github.kyungseopk1m/semver-checks kyungseopk1m/semver-checks Detect breaking changes in your TypeScript library's public API and recommend the SemVer bump. | |
| io.github.KyuRish/patreon-mcp-server kyurish/patreon-mcp-server Access your Patreon creator data - campaigns, patrons, tiers, and posts. | |
| LPC Character Generator kyuza1/lpc-character-mcp Generate LPC pixel-art character spritesheets and export them to Godot, Unity and the web. | |
| io.github.Kyzenkms/solisk-pc-mcp kyzenkms/solisk-pc-mcp Connect AI clients to local files, shell and desktop tools, with an optional self-hosted relay. | |
| io.github.l-agence/agence l-agence/agence AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus | |
| Keyhole – Local files for ChatGPT l-jovi/keyhole Read selected local folders from ChatGPT on macOS, with per-folder read-only or read-write access and hash-checked, recoverable edits. Requires local installation and a private ChatGPT app. The Glama container is a synthetic evaluation demo | |
| joLink l1ch404/jolink-runtime A lightweight Java IDE for AI agents: incremental builds, fast tests, HotSwap and live debugging. | |
| Bintu Web Reader l20941485-blip/bintu-api Fetch public web pages as clean, token-budgeted text for AI agents. | |
| Minecraft Wiki MCP l3-n0x/minecraft-wiki-mcp Searches and queries the official minecraft wiki to answer any minecraft-related question with precision! | |
| La Palma 24 - Vacation Rentals la-palma-24/lapalma24-mcp Search vacation rentals in La Palma, Canary Islands with real-time availability and pricing. | |
| Godotwright laaielichter/godotwright Godot 4.7 for coding agents: offline API, checks, review, safe edits, tests, play, 3D models. | |
| io.github.laaielichter/gulliver laaielichter/gulliver Dress rehearsal for agent SQL: cost preflight, auto-fix, 1% sample runs, budget-gated execution. | |
| ReversePort laaielichter/reverseport Reverse engineer and port apps and games: Godot, Unity IL2CPP, .NET, binaries, with parity checks. | |
| Stashpad laaielichter/stashpad Local memory for any AI agent: Markdown files with sources, a review queue and search. | |
| Frenchie lab94/frenchie-skill OCR, transcription, file extraction, and image generation for AI agents via MCP. | |
| Banyan Memory labacacia/banyan-brain-lite Persistent, governed local memory for MCP-compatible AI clients. | |
| AIOps Field Notes labaccessnow/aiops-field-notes-mcp Audit an MCP config, price a model, size a GPU, explain network config drift. Key-free. | |
| NetOps Field Notes labaccessnow/netops-field-notes-mcp Config drift, CIS/PCI checks, 802.1X diagnosis, certs inside configs, topology, change pre-flight. | |
| SecOps Field Notes labaccessnow/secops-field-notes-mcp CVSS scoring, IOC extraction, email header triage, hash/JWT/timestamp decoding, CISA KEV lookup. |
10,701–10,750 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.