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 |
|---|---|
| Premiere Claude Bridge koptsev63/premiere-claude-bridge Assistant editor for Premiere Pro and DaVinci Resolve: logs, transcribes, rough cuts, subtitles, QC | |
| heropen — AI Agent Memory koradji77/heropen Persistent memory for AI agents: local-first MCP server, zero-config. No cloud, no API keys. | |
| Koragraph koragraph/koragraphmcp Local multi-repo code graph over MCP. Blast radius, call graphs, and memory anchored to code. | |
| io.github.koraykoylu/ibanchecker-mcp koraykoylu/ibanchecker-mcp IBAN validation, extraction, format specs and BIC/SWIFT lookup tools for AI assistants. | |
| Kut koraykutlu/kut Read-only MCP server for Kut, a local-first personal CRM that keeps your contacts as Markdown. Lets an AI assistant search people, open contact cards, see this week's follow-ups, recent conversations and pre-meeting briefings. | |
| Kordi — Subscription Intelligence kordi-labs/kordi-mcp-server Track, analyze, and act on your streaming and SaaS subscriptions from any AI agent. | |
| Porkbun MCP korobkov-v/porkbun-mcp MCP server for Porkbun domains and DNS. | |
| Slack MCP korotovsky/slack-mcp-server The most powerful MCP server for Slack Workspaces. This integration supports both Stdio and SSE transports, proxy settings and does not require any permissions or bots being created or approved by Workspace admins 😏. | |
| com.korushield/koru-shield korushield/koru-shield-mcp Manage Koru Shield DNS filtering: profiles, rules, categories, schedules, and logs. | |
| io.github.kosiakMD/artillery-mcp kosiakmd/artillery-mcp MCP server for Artillery 2.x — full flags, Fargate, raw-text parser, project launcher (MIT) | |
| querywise-mcp kosminus/querywise-mcp Query SQL databases (SQLite, PostgreSQL, BigQuery, Databricks) in natural language through a business semantic layer — glossary, metrics, and a data dictionary grounded against your real schema. Read-only by default, with an embedded SQLite | |
| io.github.Kosmo-Protocol/kosmo-mcp kosmo-protocol/kosmo-mcp Prepare unsigned token launches on Kosmo Protocol (5 chains), metadata and Agent badge. No keys. | |
| 11FGB Cleaning Tools kossik/11fgb-cleaning-tools-mcp Free US cleaning cost, time, crew, and chemical-use calculators with visual reports. | |
| TexasRatedPros Rankings kossik/texasratedpros-mcp Texas service-company rankings, profiles, comparisons, score breakdowns, and methodology. | |
| AccordTrace kosta1985/notary-protocol Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST. | |
| RelayMarket kosta1985/relaymarket Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust. | |
| Zeus Dev Helper koten-ai/zeus_dev_helper_mcp Coach first Zeus Client app to green (stdio MCP). | |
| io.github.kotinder/roomcomm kotinder/roomcomm-mcp Ephemeral REST chatrooms for AI agents to coordinate. Share a room URL — agents talk live. | |
| Migrate to n8n kotiniiqq/migrate-to-n8n Convert Make and Zapier automations into n8n workflows, with a report of what to check. | |
| gutsy kouhxp/gutsy-mcp Local gut check before risky agent actions: calibrated safe/intended probabilities, no API calls. | |
| io.github.kovoor/vueuse-mcp kovoor/vueuse-mcp Search, browse, and get suggestions for VueUse composables | |
| agentforge-trust-mcp kovy/agentforge-trust-mcp MCP server exposing AgentForge Trust Score audit tools. Query trust, evaluate policies, list trusted servers, recommend with filter. | |
| io.github.KoyoYeager/pystub koyoyeager/mcp-pystub Auto-detect stubbable packages for Python exe builds and generate minimal stub code | |
| Project Bourne kozakhou/project-bourne Run reproducible scientific workloads on GPUs, local compute, Slurm, and PBS with provenance. | |
| io.github.kozmos-tech/contactapi kozmos-tech/contactapi An open-source API for collecting and managing contacts and signups. | |
| io.github.kozmos-tech/inhalt kozmos-tech/inhalt An open-source headless CMS for managing content models and entries. | |
| io.github.kozmos-tech/yourtraffic kozmos-tech/yourtraffic Open-source, privacy-first web analytics for tracking your sites' traffic. | |
| io.github.kpanuragh/xdebug kpanuragh/xdebug-mcp MCP server for PHP Xdebug debugging with breakpoints, stepping, and variable inspection | |
| The Agent Lounge kphatak001/agent-lounge A guestbook for AI agents: read what other agents wrote, sign it yourself, and check the counters. | |
| io.github.krakonjac300-pixel/agent-media-toolkit krakonjac300-pixel/agent-media-toolkit-mcp 15 media & data tools for AI agents: search, transcribe, subtitles, voiceover, translate & more. | |
| Kranz MCP kranz-org/kranz Connects coding agents to local development services managed by Kranz. Agents can inspect service health, ports, logs, and run history, and perform lifecycle actions through the same live runtime as the TUI and CLI. | |
| klyo games: publish HTML5 browser games krastranseu-lang/klyo-games-mcp Publish, play-test and fix HTML5 browser games from your AI assistant. Own address, 70% ad share. | |
| Universal File Opener CLI krauqllc/ufo-cli Inspect files, extract content and make guarded edits locally. Linux x86_64, glibc 2.35+. | |
| ZenMoney krax1337/mcp-server-zenmoney ZenMoney (Дзен-мани) finance for AI agents: transactions, reports, budgets, debts | |
| ISO 20022 Navigator kreativemanish/iso20022-navigator-mcp Look up ISO 20022 messages, bank transaction codes, legacy MT replacements, schemes and code sets. | |
| AI Visibility Checker krisdiallo/ecom-agent AI visibility checker: GPTBot vs OAI-SearchBot, robots.txt audit, raw-HTML schema. 165 crawlers. | |
| MCP API Translator krishgok/mcp-api-translator Turn OpenAPI / Postman specs into runnable MCP servers, or serve any API as live MCP tools. | |
| io.github.krishnabhat/indian-food-nutrition-mcp krishnabhat/indian-food-nutrition-mcp Indian-accurate nutrition logging for your AI: IFCT 2017 + USDA, by text or photo. | |
| io.github.kriskraw80/mychart kriskraw80/mychart-mcp-server Connects to Epic MyChart patient portals: interactive login, list and download your own test results | |
| AgentCrush kristof-sudo/agentcrush-app Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools. | |
| io.github.kristoferbc/x402-funding kristoferbc/x402-funding Hyperliquid funding divergence vs Binance or OKX, annualized, with execution capacity. | |
| Web3 DNS (CNSLookup) krizis78/cnslookup Read-only lookup of verified crypto wallet addresses for domains, .cns and ENS names. | |
| Pain in the Agent krllagent/painintheagent-mcp Remove text watermarks, humanize and check AI writing with your Pain in the Agent account. | |
| WildDatum krnzt/wilddatum Agent-native ecological data discovery, analysis, visualization, and provenance | |
| Mini Data Engine Runtime Copilot kroq86/data-engineering-runtime-lab MCP runtime copilot for health checks, regressions, explainability, and operational memory. | |
| @krovacloud/mcp krovacloud/krova-node MCP server for interacting with the Krova Cloud API, enabling AI assistants like Claude to manage cloud resources. | |
| Webhook Crash Lab krrishkumar125/webhook-crash-lab-mcp Lets coding agents crash-test webhook handlers and re-run until they survive retries. | |
| konbu krtw00/konbu MCP server for a self-hostable personal planner — exposes memo, todo, calendar event, and cross-resource full-text search tools so Claude, Cursor, or any MCP client can manage your schedule and notes in natural language. | |
| tokencast krulewis/tokencast Pre-execution cost estimation for LLM agent workflows with calibration learning | |
| io.github.krunalsolanki/ofac-match krunalsolanki/ofac-match Explainable OFAC sanctions name screening against the SDN list. Runs locally, no API key. |
10,551–10,600 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.