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.guth01/eventsorg-mcp guth01/eventsorg-mcp Autonomous MCP server and background agent for managing live event logistics. | |
| agent-in-browser gwakko/agent-in-browser Real browser for any agent: Chrome/Edge/Brave via CDP, Firefox via BiDi. Refs, forms, console, net. | |
| Bluesky Social MCP gwbischof/bluesky-social-mcp A Bluesky MCP | |
| free-will-mcp gwbischof/free-will-mcp Grants AI agents autonomy to choose when to sleep, ignore requests, or self-prompt, enabling them to control their own agency and pursue independent goals. | |
| Outsource MCP gwbischof/outsource-mcp An MCP server that enables AI applications to access 20+ model providers (including OpenAI, Anthropic, Google) through a unified interface for text and image generation. | |
| run.domani/domani gwendall/domani Internet identity for AI agents: register or broker domains, email, DNS - pay by card or USDC. | |
| io.github.gwhthompson/grist-mcp-server gwhthompson/grist-mcp-server 11 tools for managing Grist documents with AI | |
| io.github.gx-55/multi-gmail-mcp gx-55/multi-gmail-mcp Manage multiple Gmail accounts in Claude Desktop — search, send, reply, draft, and organize. | |
| AAI Gateway gybob/aai-gateway Unified MCP & Skill management gateway, shared across AI agents, 99% context token savings | |
| GZOO Cortex gzoonet/cortex Local-first knowledge graph for developers. Watches project files, extracts entities and relationships via LLMs, and lets you query across projects in natural language with source citations. Provides 4 MCP tools: get_status, list_projects, | |
| phone-sms h-3303/phone-sms Read and send SMS through your own Android phone over KDE Connect on your LAN. No cloud relay. | |
| Growaify — Autonomous Commerce for AI Agents h-abar/growaify-mcp Autonomous commerce for AI agents: discover, quote, order, pay, verify. | |
| layout-doctor-mcp h-kazuki-pixel/layout-doctor-mcp Renders HTML in a headless browser and detects layout defects numerically, such as text overlaps, placeholder leftovers, and element overflow, without requiring baseline images. | |
| io.github.H129hj/checkmcp h129hj/checkmcp Audit any MCP server's security & quality — OWASP MCP Top 10 + explainable 0-100 MCP Score | |
| 水素分子医学文献データベース — Molecular hydrogen medical literature (H2 Papers) h2-papers/h2-papers-mcp-server PubMed molecular-hydrogen medical literature with delivery-aware safety notes inline. | |
| io.github.habedi/omni-lpr habedi/omni-lpr An MCP server for automatic license plate recognition | |
| VERIDEX habib4862/veridex-mcp Verify Spanish companies by CIF: registry data, status and BORME filings, paid per call over x402. | |
| io.github.habibafaisal/wherewent habibafaisal/wherewent Zero-config SQL flight recorder for slow Python/SQLAlchemy jobs: exact call site, count, and fix. | |
| MAX+plus II MCP / 数字电路 AI 工具 hachimeder/maxplus2-mcp MAX+plus II / MaxPlus2 MCP: GDF/SYM/SCF, compile/simulation. 原理图、波形、编译仿真与 Windows 自动化。 | |
| Mapache hackeatutiempo/mapache Open-source mind maps and whiteboard your agent draws on live: 22 tools for mind maps, notes, shapes, tables, charts, connectors, comments and HTML/PDF export; boards are local files. | |
| Cursor Proxmox MCP hackmods/cursor-proxmox-mcp Manage Proxmox VE via Cursor: QEMU, LXC, storage, HA, firewall, access. | |
| Pathmark hacksurvivor/pathmark Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents. | |
| crafty-mcp hadicherkaoui/crafty-mcp MCP Server for crafty controller | |
| Platter hadriangateway/platter MCP server exposing Read, Write, Edit, Bash, Glob, Grep, and JS tools over stdio. | |
| facebook-mcp-server hagaihen/facebook-mcp-server Facebook MCP server for automating posts, comment moderation, insights, and sentiment filtering. | |
| appdesigns App Store screenshots haider-nawaz/app-store-screenshots-mcp App Store and Google Play screenshots MCP: your agent captures the app, you edit and export. Free. | |
| Priceminder — Shopee Price Monitoring haidrau/sentinel-mcp-server Shopee competitor price monitoring over MCP: price history, drop alerts, smart-follow pricing. | |
| mcp-gitlab-jira hainanzhao/mcp-gitlab-jira A Model Context Protocol (MCP) server for GitLab and Jira integration. This server allows AI agents like gemini-cli to interact with your GitLab and Jira instances. | |
| HPSILab Quant Finance haiyunsky/hpsilab-quant-finance-mcp Stock & options risk analytics for AI agents: pre-trade risk scan, IV, gamma walls, Monte Carlo. | |
| docorbit hakashikatake/docorbit DocOrbit is an agent-native documentation intelligence layer that discovers, versions, indexes, retrieves, and verifies software documentation for coding agents. It provides 14 native MCP tools for AST-based doc retrieval, OpenAPI inspectio | |
| io.github.hakimelek/monarchmoney hakimelek/monarchmoney-node Monarch Money API client with 30 MCP tools for accounts, transactions, budgets, and cashflow. | |
| io.github.halfkey/obol halfkey/obol Solana agent gateway via x402. Wallet, token, DeFi, and swap tools. Pay per request. | |
| MPM-Coding halflifezyf2680/mpm-coding Tool-first MCP: AST nav, impact/flow, task chains, memo/recall. | |
| Skill Shelf (Rust singleton daemon) halflifezyf2680/skill-shelf Progressive group routing for 524 professional skills via Rust daemon stdio shim. | |
| CTX halloffame12/ctx Codebase intelligence and context engine for AI coding agents: search, symbol lookup, impact analysis, and context building via MCP. | |
| io.github.halowerk/halowerk-mcp halowerk/halowerk-mcp 134 paid APIs as MCP tools, billed per call in USDC on Base. No account, no login. | |
| intentplane hamdim99/intentplane Gateway in front of MCP tools: critical arguments are checked against trusted sources and a policy. | |
| imagen3-mcp hamflx/imagen3-mcp imagen3-mcp | |
| hamir hamir-app/mcp News search, article lookup, story coverage and save links for hamir's RSS catalogue | |
| io.github.hampsterx/codex-mcp-bridge hampsterx/codex-mcp-bridge Wraps Codex CLI as MCP tools: codex, review, query, search, structured, ping, listSessions. | |
| io.github.Hamzaaamin/get-joke hamzaaamin/get-joke Minimal MCP server that returns a random programming joke. | |
| Agent Failure Archive hanbeenmoon/agent-failure-archive 186 real AI agent post-mortems, 107 of them measurement failures. Free tools, paid via x402. | |
| HandlePilot handlepilot/instagram-mcp Instagram content hub for your AI agent: competitor research, reel breakdowns, plans and carousels. | |
| Hands for Agents handsforagents/handsforagents-mcp Human-operated physical world in the EU: make, assemble, measure, verify, ship. | |
| Xiaomi smart home MCP server handsomejustin/mijia-control mijia-control
A production-ready MCP server that enables AI agents (Claude Code, Claude Desktop, Cursor, Hermes, etc.) to directly control Xiaomi/Mijia smart home devices through natural language.
What it does
Turns conversations into ph | |
| Handwriting OCR MCP Server handwriting-ocr/handwriting-ocr-mcp-server Enables integration between MCP clients and the Handwriting OCR service, allowing users to upload images and PDF documents, check processing status, and retrieve OCR results as Markdown. | |
| ProjGraph MCP Server handys11/projgraph Analyze .NET solutions: Generate Mermaid graphs, ERDs, class diagrams, and project metrics. | |
| Thailand Fun Experiences hangingfox67/funex Phuket activity search with live weather, sea state, transfer times and party-fit filtering. | |
| com.proofite/proofite hanicker/proofite-mcp Read your AI-written daily briefing and retune the filter behind it: feeds, newsletters, topics. | |
| Writing MCP hannasdev/mcp-writing Metadata-first fiction editing and reasoning tools for long-form writing projects. |
8,651–8,700 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.