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 |
|---|---|
| io.github.mrfentmen/opensearch-mcp mrfentmen/opensearch-mcp Search OpenSearch indices, manage documents, check health and stats. | |
| io.github.mrfentmen/repo-forensics-mcp mrfentmen/repo-forensics-mcp Local read-only MCP tools for Git repository archaeology, churn, hotspots, and hygiene. Tools... | |
| io.github.mrfentmen/rom-mcp mrfentmen/rom-mcp Search ROMs across Internet Archive, ROMsgames, CoolROM, and more. Verify checksums and parse saves. | |
| io.github.mrfentmen/schema-sieve-mcp mrfentmen/schema-sieve-mcp Local JSON Schema structure inspection and privacy-safe fixture planning. Tools include inspect... | |
| io.github.mrfentmen/screenplaywriter-mcp mrfentmen/screenplaywriter-mcp Read, write, and analyze screenplays in Fountain format. | |
| io.github.mrfentmen/vg-resource-mcp mrfentmen/vg-resource-mcp Search and download sprites, models, textures, and sounds from VG Resource. | |
| io.github.mrfentmen/worktree-orbit-mcp mrfentmen/worktree-orbit-mcp Aggregate local Git worktree topology without exposing repository content. Tools include inspect... | |
| io.github.mrfentmen/zork-mcp mrfentmen/zork-mcp Use this MCP server to plays classic text adventure games. The LLM is the player, explore, solve... | |
| HackList mrfomoweb3/hacklist-mcp Live AI & Web3 hackathons, grants and programs from HackList, ranked for what's worth entering. | |
| io.github.mrfqcentic/mcp-kokoro-tts mrfqcentic/mcp-kokoro-tts Local Kokoro-82M TTS MCP server that synthesizes and plays speech on your machine | |
| io.github.mrfqcentic/mcp-notify mrfqcentic/mcp-notify Minimal MCP server that plays a sound and shows a system banner when an AI agent finishes a task | |
| Vulnerability Exposure mrfrazer25/vulnerability-exposure-mcp Confirmed vulnerabilities and exposure for IPs, domains and software versions (NVD, CISA KEV, EPSS) | |
| AENA Flights MCP mrgo2/aena-mcp Flight data for Spain's 50 AENA airports over the public and OAuth2 REST APIs | |
| io.github.mrhpython/lens-mcp mrhpython/lens-mcp Outside-in validation gate for AI-generated text; a separate model checks LLM output, fail-closed. | |
| CloudGPU MCP mrhy7176/cloudgpu-mcp Rent a per-minute GPU from your MCP client, run a job, download results, shut it down. | |
| UI Registry mrityunjay-tiwari/ui-registry-mcp Live access to 12 shadcn-style component libraries so agents compose UI from real components. | |
| CTFd mrjamescot/ctfd-mcp-server MCP server for CTFd v3: list challenges, submit flags, and query scoreboards via AI agents. | |
| godoc-mcp mrjoshuak/godoc-mcp godoc-mcp is a Model Context Protocol (MCP) server that provides efficient access to Go documentation. It helps LLMs understand Go projects by providing direct access to package documentation without needing to read entire source files. | |
| io.github.mrkeyoor/should-i-use mrkeyoor/should-i-use Honest library picks for coding agents in 25-360 tokens. Tells your agent what NOT to install. | |
| SourceWeave Web Search mrnaqa/sourceweave-web-search Fully local MCP server and CLI for web research | |
| io.github.mrocker/linkedin-company-profile mrocker/social-data-mcp LinkedIn companies, hiring signals and public profiles by URL. No login, no cookies. Pay per result. | |
| MakeMeBetter AI mrohith29/makemebetter-mcp Manage your MakeMeBetter AI tasks, habits, and goals from your AI assistant. | |
| OpenAPI MCP Gateway mroops0111/openapi-mcp-gateway Mount any OpenAPI spec as an MCP server, supporting multiple APIs with authentication and resource auto-promotion. | |
| io.github.mrorigo/bash-command-mcp mrorigo/bash-command-mcp Sophisticated bash command MCP server that runs and manages shell execution. | |
| Hashfile MCP mrorigo/hashfile-mcp Hash-anchored file editing with surgical precision over file editing and ironclad control of access | |
| io.github.mrosnerr/open-zk-kb mrosnerr/open-zk-kb Shared, persistent memory for AI assistants, built on the Zettelkasten method. | |
| Rancher MCP Server mrostamii/rancher-mcp-server Model Context Protocol (MCP) server for the Rancher ecosystem: multi-cluster Kubernetes, Harvester HCI (VMs, storage, networks), and Fleet GitOps. | |
| drift — mandate enforcement for AI agents mrpkk/drift Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent. | |
| mitracore — trust layer for agent work mrpkk/mitracore Verify the artifact, meter the cost, enforce the mandate — one call. | |
| nidhipati — proof of spend for AI agents mrpkk/nidhipati Proof-of-spend and reserve checks for AI agents: receipts, spend audit, NAV, reconciliation. | |
| soma — protocol for agent rhythm and vows mrpkk/soma-protocol Protocol for agent rhythm and vows: who promised what, and by when. | |
| io.github.MrRefactoring/atlassian-dc-mcp-bitbucket mrrefactoring/atlassian-dc-mcp MCP server for Atlassian Bitbucket Data Center - interact with repositories and code | |
| MrScraper MCP mrscraper-com/mrscraper-mcp Scraper API for HTML, Markdown, and screenshots, web search, and account usage for AI agents. | |
| io.github.Mrshahidali420/gsc-indexer-mcp mrshahidali420/google-search-console-mcp Search Console for agents: index status, unindexed-URL discovery, Request Indexing, sitemaps. | |
| io.github.mrsingh86/trimtab-ais mrsingh86/trimtab-ais US tariff & trade truth: duty actually paid by origin/HS 2017+, HTS rulebook, CBP rulings. No key. | |
| YouTube MCP mrsknetwork/ytmcp Interact with YouTube data via the official Data API v3 | |
| io.github.mrslbt/japan-ux mrslbt/japan-ux-mcp Japanese UI + UX correctness for AI coding agents — typography, forms, keigo, JLReq checks. | |
| io.github.mrslbt/nankai-trough mrslbt/nankai-trough-mcp Nankai Trough earthquake hazard & building-safety, from official Japan data. No verdicts. | |
| io.github.mrslbt/paypay-mcp mrslbt/paypay-mcp PayPay QR payments for AI agents: QR codes, status, refunds, cancels. Bilingual JP/EN. | |
| io.github.mrslbt/pdf-it mrslbt/pdf-it Native PDF renderer for AI markdown. Cover, TOC, page-numbered footer. Fonts embedded, zero config. | |
| io.github.mrslbt/tabedata-mcp mrslbt/tabedata-mcp Bilingual JP/EN Japanese food nutrition for AI: 460 sourced konbini, chain & brand items. | |
| memry mrtheroi/memry-cli Persistent memory for AI coding agents. Install the memry CLI and run memry setup. | |
| ai.smithery/mrugankpednekar-mcp-optimizer mrugankpednekar/mcp-optimizer Optimize crew and workforce schedules, resource allocation, and routing with linear and mixed-inte… | |
| Picnic mrvdh/picnic-mcp Search products, fill the cart and pick a delivery slot at the online supermarket Picnic | |
| io.github.mrvlyouknowwho/ton-jetton-risk-mcp mrvlyouknowwho/ton-jetton-risk-mcp Token rug/honeypot risk screening: EVM (7 chains, live sell simulation), Solana, TON. Free, keyless. | |
| io.github.MrWizardlyLoaf/rugcheck-ai mrwizardlyloaf/rugcheck-ai Solana token safety for AI agents — rug-pull, honeypot & Token-2022 trap detection before you buy. | |
| io.github.mscott9160-web/achlens mscott9160-web/achlens Local-first MCP server and CLI for validating and generating synthetic ACH files. | |
| io.github.msdanyg/smart-connections-mcp msdanyg/smart-connections-mcp Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private. | |
| io.github.msenol/gorev msenol/gorev Task management system for AI assistants with MCP protocol, templates, and bilingual support (TR/EN) | |
| Audio MCP mshark1/audio-mcp Audio perception for AI agents: measure, see, compare, edit and synthesize sound locally. |
13,401–13,450 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.