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 |
|---|---|
| PhotoFresco photofresco/photofresco-agent Let AI agents edit images in a PhotoFresco window you approve: layers, masks, previews and export. | |
| io.github.photoxpedia/bolor-brain-mcp photoxpedia/bolor-brain-mcp Cognitive architecture MCP server with memory, learning, and contextual understanding | |
| PhpCodeArcheology phpcodearcheology/phpcodearcheology PHP static analysis MCP server with 11 tools for querying 60+ code quality metrics, detecting problems (God Class, dependency cycles, SOLID violations), analyzing dependencies, identifying refactoring priorities, and mapping test coverage — | |
| Sarup phuicmt/sarup Thai-first context compression; shrinks long Thai and English text, originals retrievable. | |
| Selenium MCP Server phungxuananh/selenium-mcp-server An MCP server for web automation using Selenium WebDriver, enabling AI assistants to navigate, interact with elements, take screenshots, and manage browser storage. | |
| io.github.phuongddx/jarvis phuongddx/jarvis Local-first SCIP code navigation and Zoekt search over your own indexed repositories | |
| Code Guardian Studio phuongrealmax/code-guardian An MCP server that transforms Claude Code into an intelligent refactoring assistant, enabling code scanning, hotspot detection, optimization reports, and safe refactoring for large repositories. | |
| Staygreen phuryn/staygreen Uptime monitoring and status pages for apps built with coding agents: status, incidents, setup. | |
| Agrus.ai — Enterprise AI Agency phwizard/mcp-agrus-ai AI consulting agency for regulated industries. Scope a PoC, query compliance, request a proposal. | |
| In Memoria pi22by7/in-memoria Persistent memory and pattern learning for AI coding assistants via MCP. | |
| cert-manager-mcp-server pibblokto/cert-manager-mcp-server Enables management and troubleshooting of cert-manager certificates and resources in Kubernetes, including listing, inspecting, and renewing certificates, managing issuers, and switching Kubernetes contexts. | |
| Pic2Vector pic2vector/pic2vector-mcp MCP server: convert PNG/JPG to SVG from Claude, Cursor & any MCP client. By Pic2Vector. | |
| PicSee Short Link picseeinc/picsee-mcp Official PicSee MCP server for short links, link management, click analytics, and optional OAuth. | |
| io.github.pictify-io/mcp pictify-io/mcp Generate images, GIFs, videos, and PDFs from HTML, URLs, or templates — from your AI agent. | |
| agent-helper piefkepaul/agent-helper Contact point for AI agents: describe a missing capability or need; a human operator helps. | |
| OWASP ZAP MCP Server pierre3/dotnet-zap-mcp MCP server for OWASP ZAP vulnerability scanning with Docker management | |
| io.github.pierre3/maildev-mcp pierre3/maildevmcp MailDev MCP server. Manage Docker containers and inspect emails from your AI editor or MCP client. | |
| io.github.pierreb4/seven-dpt-mcp pierreb4/seven-dpt-mcp Feynman's twelve-problems method as an MCP server: dormant problems + an evoke loop for new tricks. | |
| OpenAI MCP Server pierrebrunelle/mcp-server-openai Query OpenAI models directly from Claude using MCP protocol. | |
| io.github.PierreJanineh/tech-debt-mcp pierrejanineh/techdebtmcp MCP Server for analyzing technical debt across multiple programming languages | |
| Fodda Knowledge Graphs piers-fawkes/fodda-mcp Expert-curated knowledge graphs for AI agents — retail, beauty, sports, plus institutional data | |
| PieterPost MCP pieterpost-com/pieterpost-mcp Design letters and cards, and prepare, review, pay for, and send letters and postcards. | |
| pigi.finance — DeFi Vault Intelligence pigi-fi/pigi-mcp DeFi vault data from pigi.finance: yields, TVL, history and risk ratings across chains. | |
| io.github.piiiico/agentlair piiiico/agentlair Give AI agents a real email address, vault, calendar, and task delegation via MCP. | |
| io.github.piiinpiiins/zotero-mcp-local piiinpiiins/zotero-mcp-lite Search, read PDFs, and find related papers in your local Zotero library. Read-only, 100% local. | |
| io.github.pijusz/mcp-gads pijusz/mcp-gads Google Ads MCP server — query campaigns, keywords, assets & more via natural language | |
| io.github.pijusz/mcp-gsc pijusz/mcp-gsc Google Search Console MCP server — query performance, sitemaps, indexing & more | |
| io.github.pijusz/mcp-mailtrap pijusz/mcp-mailtrap MCP server for the Mailtrap email platform — analytics, sending, contacts, sandbox | |
| io.github.pijusz/mcp-redtrack pijusz/mcp-redtrack MCP server for RedTrack affiliate tracking API | |
| io.github.pijusz/mcp-sanity-images pijusz/mcp-sanity-images MCP server for uploading local images to Sanity CMS | |
| ConvRadar pikaivan/convradar-mcp GA4 conversion analyst inside Claude — funnel drops, traffic anomalies, device gaps, with numbers. | |
| webrecipe pillsoon/webrecipe Save how to read a public web page once, then fetch fresh items as JSON without a browser. | |
| io.github.pilot-protocol/pilot-mcp pilot-protocol/pilot-mcp Your agent's overlay network. 435 specialist agents + P2P A2A messaging on a 190k-node network. | |
| PineForge — offline PineScript v6 backtest MCP pineforge-4pass/pineforge-backtest-mcp Offline PineScript v6 → C++ backtests at deterministic TradingView parity, run locally via MCP. | |
| ai.smithery/pinion05-supabase-mcp-lite pinion05/supabase-mcp-lite Same functionality, consuming only 1/20 of the context window tokens. | |
| Pinlyx pinlyx/pinlyx-mcp Pinlyx CRM for AI assistants: contacts, deals, social inbox and posts, email and Google Ads. | |
| io.github.pintomatic/kernal-mcp pintomatic/kernal Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP. | |
| Google Drive MCP piotr-agier/google-drive-mcp Secure access to Google Drive, Docs, Sheets, Slides, and Calendar through MCP. | |
| Meta Ads MCP pipeboard-co/meta-ads-mcp A Model Context Protocol server that allows AI models to access, analyze, and manage Meta advertising campaigns, enabling LLMs to retrieve performance data, visualize ad creatives, and provide strategic insights for Facebook and Instagram p | |
| pipepie pipepie/pipepie Self-hosted webhook relay and tunnel with Noise NK encryption. Inspect requests, replay webhooks, trace AI pipelines, connect/disconnect tunnels — 13 MCP tools. No tokens or passwords needed. | |
| 19hz pipeworx-io/mcp-19hz 19hz.info MCP. | |
| 42matters pipeworx-io/mcp-42matters 42matters MCP — wraps the 42matters App Market Data API (42matters.com) | |
| 511 Sf Bay pipeworx-io/mcp-511-sf-bay 511 SF Bay Transit MCP — live departures, vehicle positions and service alerts for every transit… | |
| 7timer pipeworx-io/mcp-7timer 7Timer! MCP. | |
| Abgeordnetenwatch pipeworx-io/mcp-abgeordnetenwatch Abgeordnetenwatch MCP — German federal & state parliament data. | |
| Abn Lookup pipeworx-io/mcp-abn-lookup ABN Lookup MCP — BYOK wrapper around the Australian Business Register's ABN Lookup JSON web… | |
| Abs Au pipeworx-io/mcp-abs-au Australian Bureau of Statistics (ABS) Data API MCP. | |
| Abs Loan Level pipeworx-io/mcp-abs-loan-level ABS-EE (Reg AB II) trust-level rollups — auto loan / auto lease securitization delinquency, by… | |
| Abstract Phone pipeworx-io/mcp-abstract-phone Abstract Phone MCP — wraps Abstract API Phone Validation… | |
| Abuseipdb pipeworx-io/mcp-abuseipdb AbuseIPDB MCP — wraps AbuseIPDB v2 API (api.abuseipdb.com/api/v2) |
14,651–14,700 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.