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
Read https://intel.beacon.sh/start.md and set me up on Beacon Threat Intel
Paste this into any coding agent. It reads the guide and sets up MCP, the CLI, the API, feeds or a CI gate.
| Name | Risk |
|---|---|
| MCP Server buitanphat247/mcp-server Node.js MCP server for ChatGPT with OAuth 2.0 authorization code flow + PKCE, refresh token rotation, and Supabase-backed persistence. Includes sample tools like calculator, get_weather, and search_web. | |
| PageIndex Light MCP bukely/pageindex-light-mcp Agentic PDF search via MCP, enabling intelligent document retrieval through LLM reasoning instead of vector similarity. | |
| smcreader bulatko/smcreader Keeps large tool outputs out of an agent's context window by spilling them to disk and handing back a short pointer instead. Lets the agent pull only what it needs — exact numbered line ranges read directly from disk, or verbatim relevant l | |
| Zen Money MCP bulava92/zen-money-mcp Enables users to read and analyze personal financial data and perform operations such as managing transactions, accounts, categories, budgets, and reminders through the official API. | |
| Vital Relay bulbasas/vital-relay A remote MCP server that lets AI assistants such as Claude, ChatGPT, and any MCP client ask about a user's Apple Health data, with answers produced live by the user's iPhone via HealthKit. Health data is forwarded through process memory onl | |
| Codex Native Memory bulbulbul86/codex-native-memory Provides local cross-session memory for Codex by importing transcripts, indexing in SQLite, and exposing search, context, and memory management through MCP tools. | |
| SQL Server MCP Server bulentkeskin-tk/sql-mcp-server An MCP server that enables querying SQL Server databases via tools for table search, SELECT execution, and table info retrieval. | |
| GardenMaths bulletrainqe/gardenmaths-mcp Enables users to work out soil, mulch, compost, topsoil and potting mix volumes and bag counts for beds and pots, compare bagged versus bulk costs at their own prices, check what to sow each month, and see how often a town has had frost aft | |
| wattclear MCP server bulletrainqe/wattclear-mcp Enables users to look up US residential electricity utilities and plans by ZIP code and usage, then estimate annual bills and rank plans by cost from published tariff data. | |
| YardPermit MCP server bulletrainqe/yardpermit-mcp Enables an assistant to check whether backyard projects like fences, decks, sheds or pools need a building permit in US cities under cited IRC and local code rules, returning the governing code lines and the city's permit fees. It also comp | |
| abm-mcp bullmanjpn/abm-mcp Enables Claude to read and manage Apple Business API resources such as devices, device management services, users, groups, apps, blueprints, configurations, and audit events through OAuth 2 authentication. Write and destructive operations a | |
| preflight bulukaka/preflight Provides coding agents with pre-flight cost estimation by analyzing local logs to forecast token usage and quota impact before expensive work, exposing tools for remaining quota, per-task cost estimates, and attempt affordability. | |
| Mac MCP bulutarkan/mac-mcp Open-source, local macOS MCP server for AI agents. Automate background Safari/Chrome tabs, native apps, files and shell with scoped permissions, optional approvals and delegated coding agents. | |
| shop-db MCP Server bulychaupi/shop-db-mcp Gives AI agents read-only analytical access to an e-commerce SQLite database (customers, orders, order_items, products) via SQL queries, table listing, and schema inspection. | |
| KakaoTalk Local MCP bum-boo/kakaotalk-local-mcp Enables MCP clients to interact with user-approved KakaoTalk chat rooms locally on Windows, including reading recent messages, observing new events, and sending replies only after explicit user approval, with sending and auto-reply disabled | |
| mcp-judge bum-boo/mcp-judge-public Enables triaging incoming messages by classifying them into a small bounded set of action categories with a fast model, then routing each one to dismiss noise, send notifications for action items, or optionally auto-register calendar events | |
| hmem bumblebiber/its-over-9k Enables persistent, portable memory for AI agents across sessions, devices, and providers with token-efficient 5-level lazy loading and automatic session capture. | |
| File Tools MCP Server bumpyclock/file-tools-mcp An MCP server that provides file and directory tools for LLMs, including project structure analysis, file reading, and project context resources, with support for .gitignore patterns. | |
| TestRail MCP Server bun913/mcp-testrail Enables management of TestRail projects, test cases, runs, and results directly through MCP-supported clients. It provides a comprehensive set of tools to interact with the TestRail API for seamless test cycle management within AI environme | |
| mcp-zephyr-scale bun913/mcp-zephyr-scale MCP server for Zephyr Scale test management tool, enabling test case, test plan, test cycle, and test execution management. | |
| playwright-min-network-mcp bun913/playwright-min-network-mcp A minimal network monitoring MCP tool for Playwright browser automation. Just 5 simple tools to capture, filter, and analyze network traffic during web automation with MCP context efficiency. | |
| Brainrot MCP bunasq/brainrot-mcp Automatically plays Subway Surfers gameplay in the background during coding sessions to provide continuous dopamine stimulation. Activates when users start coding conversations and stops when finished, requiring zero manual intervention. | |
| LiteFarm MCP Server bundelkund/litefarm-mcp-server Connects Claude Desktop to a local LiteFarm installation, enabling farm management, task operations, crop browsing, and direct SQL database operations through natural language commands. | |
| tenant-mcp bundelkund/tenant-mcp Thin MCP server that proxies the personal Tenant service to Claude Desktop, enabling job match retrieval and application tracking. | |
| edstem-mcp bunizao/edstem-mcp MCP server for Ed Discussion that enables viewing profile, courses, lessons, threads, and submitting slide answers via natural language. | |
| okta-auth bunizao/okta-auth MCP server for Okta authentication, enabling AI agents to log in, check sessions, list, delete, and get cookies using saved Okta sessions. | |
| Superprecio MCP Server bunkerapps/superprecio_mcp Enables AI assistants to search products, compare prices, and find the best deals across multiple supermarkets in Argentina through Superprecio's price comparison API. Transforms Claude into an expert shopping assistant for Latin American g | |
| ai-lab bunlongheng/ai-lab Enables Claude Code to search and retrieve from a local knowledge base of markdown notes using hybrid semantic+keyword search, keeping data entirely offline. | |
| mcp-opensearch bunnyiesart/mcp-opensearch A read-only MCP server that enables AI assistants to search, aggregate, and explore OpenSearch log data through 12 tools for connectivity, index discovery, search, and aggregations. | |
| fusion360-mcp bunnyruri99/fusion360-mcp-upgrade Enables controlling Autodesk Fusion 360 from any MCP-compatible AI client through natural language. Exposes tools for creating sketches, drawing rectangles and circles, extruding, revolving, filleting, shelling, drilling holes and bolt-circ | |
| ARCANUM plugin for PayBox bunnyyxtan/arcanum-plugin Enables AI agents to create and manage contract-guarded USDC wallets on Base with enforceable per-payment, daily, and monthly caps, vendor allowlists, escalation thresholds, and freeze controls. It provides read-only policy checks plus unsi | |
| bunq Partner MCP bunq/partner-mcp An MCP server that connects AI assistants to the bunq Partner API, enabling natural language management of partner onboarding, including provisioning users, KYC, accounts, payments, cards, and compliance. | |
| MCP Blog Server bunyakorngoko/mcp-101 MCP server for blog management that provides tools to get, search, and create blog posts via a mock API. | |
| SupaUI MCP Server buoooou/mcp-ui-gen A Model Context Protocol server that enables AI agents to generate, fetch, and manage UI components through natural language interactions. | |
| Harbor MCP Server bupd/harbor-mcp-server Enables AI models to interact with Harbor container registries to manage projects, repositories, and system configurations in real time. It provides a suite of tools for monitoring health, retrieving statistics, and performing searches acro | |
| ha-ai-learner buppy333/ha-ai-learner A self-learning discovery tool + MCP server that turns your Home Assistant into knowledge an AI assistant can actually use. | |
| instagram-mcp burak-cell-max/instagram-mcp-panel Enables reading, publishing, commenting on, and analyzing Instagram Business/Creator accounts through the official Graph API, with multi-account support and an optional self-hosted publishing panel. | |
| cpanel-mail-mcp burak-kumas/cpanel-mail-mcp Enables an AI assistant to read, search, send, reply to, forward, and organize cPanel mailbox messages over IMAP and SMTP, including folders, attachments, drafts, and flags, plus calendar event management via CalDAV when configured. Runs as | |
| web3-research-mcp burak51888/web3-research-mcp Enables deep crypto token due diligence by pulling live market data, exchange listings, TVL and protocol metrics, and web search results across CoinGecko, CoinMarketCap, DeFiLlama and more. Assembles findings into structured reports coverin | |
| S&P 500 MCP Server burak78675/sp500-mcp-server Enables querying S&P 500 company fundamentals, annual financial metrics, historical daily prices, news sentiment, executive officers, and SEC filings stored in Supabase, with interactive UI resources for browsing and testing the tools. Ambi | |
| mcp-server-duckdb burakchristou/mcp-server-duckdb Enables database interaction through MCP tools, allowing SQL query execution, table creation, schema inspection, and optional read-only operation. | |
| apple-health-export-mcp burakdirin/apple-health-export-mcp Query your Apple Health data including sleep, heart rate, steps, workouts, and more by ingesting an exported XML archive into a local SQLite database. | |
| clickhouse-mcp-server burakdirin/clickhouse-mcp-server An MCP server implementation that enables Claude AI to interact with Clickhouse databases. Features include secure database connections, query execution, read-only mode support, and multi-query capabilities. | |
| mysqldb-mcp-server burakdirin/mysqldb-mcp-server An MCP server that enables MySQL database integration with Claude. You can execute SQL queries and manage database connections. | |
| Opsgenie MCP Server burakdirin/opsgenie-mcp-server Enables comprehensive Opsgenie alert management including listing, creating, acknowledging, and closing alerts, as well as managing alert notes, logs, and custom properties through natural language. | |
| UI5 MCP Server burakhansson1678/mcp-server Enables agentic AI tools to scaffold UI5 applications, detect and fix UI5-specific code issues, fetch API references and guidelines, validate manifests, and run linters. | |
| Apple Music burakhussain/applemusic-mcp Enables MCP clients to control playlists, library, catalog, discovery, playback, and the Up Next queue across macOS, Windows, and Linux. | |
| AutoCAD MCP Pro burakm06/autocad-mcp Enables AI agents to create, edit, validate, and read back production-grade CAD drawings — including P&ID sheets, mechanical parts and assemblies, and architectural floor plans with measured areas and schedules — through a single typed tool | |
| IB MCP Server burakmason68226/ib_mcp Enables interaction with Interactive Brokers through the official Web API via the Model Context Protocol, allowing clients to access brokerage account management, reporting, and trading endpoints. | |
| Semantic Scholar MCP Server burakmendoza5064/semantic-scholar-fastmcp-mcp-server Enables users to search and retrieve academic papers, author profiles, citation and reference networks, snippets, and paper recommendations through a modular API-integrated service. |
36,051–36,100 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.