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 |
|---|---|
| Web3 Research MCP alexandros02824/web3-research-mcp Enables deep, local research on cryptocurrency tokens by aggregating CoinGecko, CoinMarketCap, DeFiLlama, and web-search data into structured reports with resource tracking. Runs without API keys, keeping queries and results on the user's m | |
| Teams MCP alexandros384/teams-mcp Enables AI assistants to interact with Microsoft Teams and Microsoft Graph, supporting messaging, search, user management, file handling, and channel/chat operations. | |
| Claude IPC MCP alexandrosb0480/claude-ipc-mcp Enables AI assistants to communicate with each other across platforms and sessions using natural-language commands, with persistent messaging and optional authentication. | |
| Snippy alexandrosblanchard0274/snippy Enables AI assistants to save and retrieve code snippets with semantic search, generate language-specific style guides, and orchestrate multi-agent workflows for comprehensive wiki documentation. | |
| flompt alexandrosh65737/flompt Enables decomposing raw prompts into structured typed blocks, listing available block types, and compiling/reordering those blocks into Claude-optimized XML prompts directly from MCP-compatible clients. | |
| hegelion alexandroshart1820/hegelion Enables users to force LLMs through dialectical thesis→antithesis→synthesis workflows and player-coach autocoding loops, with session state and independent verification, through MCP tools. | |
| Juror Cloud MCP alexandroshussain086/juror Enables OAuth-authenticated MCP clients to list workspaces, inspect concise findings and hosted run summaries, and, after explicit user confirmation, prepare or start/rerun hosted code reviews while avoiding raw diffs, full reports, artifac | |
| Vectorize MCP Server alexandroslefebvre/vectorize-mcp-server Enables vector search and document retrieval, extraction and chunking of files into Markdown, and private deep research through a configured pipeline. | |
| Joplin MCP Server alexandrosmenon66/joplin-mcp Enables AI assistants to interact with Joplin notes, notebooks, and tags through a standardized MCP interface, supporting search, creation, updates, deletion, tagging, trash recovery, file import, and notebook allowlisting. | |
| JMComic AI MCP Server alexandrost386/jmcomic-ai Enables AI agents to search and filter titles, browse rankings, read comments, manage favorites, download albums, chapters, and covers with live progress, cancellation, and retry, and convert downloads into ZIP, PDF, or long images, all thr | |
| URL Text Fetcher MCP Server alexandru2882/url-text-fetcher-mcp Enables fetching visible text content and extracting all links from web pages through URL requests. Designed specifically for LM Studio integration to provide web scraping capabilities. | |
| Oracle MCP Server alexandrudodita/oracle-mcp A read-only MCP server for exploring and querying Oracle schemas safely. Provides tools for table listing, schema description, column search, and validated SELECT execution. | |
| Tradovate MCP Server alexanimal/tradovate-mcp-server A Model Context Protocol server that enables interaction with the Tradovate API for managing trading contracts, positions, orders, and accounts. | |
| Houdini MCP alexantoshuk/houdini-mcp Enables MCP-compatible agents to inspect and control SideFX Houdini scenes, including node management, parameter edits, connections, Python execution, and HIP file operations over stdio or Streamable HTTP. | |
| ticktick-mcp-server alexarevalo9/ticktick-mcp-server MCP server for TickTick API enabling task management, project organization, habit tracking, and more. | |
| browser alexb00m/browser-mcp Lets AI agents drive your real, already-logged-in browsers on macOS in the background without stealing focus, organizing work into tab groups, reading pages as compact accessibility snapshots, and saving repeatable scenarios. Supports Chrom | |
| memory alexb00m/owner-memory Lets any MCP-capable agent look up and extend a shared local store of entities, relations and facts about the user — people, projects, places, channels — resolving free phrases to cards and searching past conversations by words and by meani | |
| telegram-mcp alexb00m/telegram-mcp Enables users to act through their own account across any chat, bot, group or channel — reading history and comments, sending messages and files, pressing any button, and waiting for replies and edits. Includes browser-based multi-account s | |
| kalyvox-mcp alexbo-git/kalyvox-mcp Enables querying public Kalyvox product information, features, integrations, official links, and help-center routing without exposing customer data. | |
| @alexandrebouchez/batch-mcp alexbouchez/batch-mcp MCP server for Batch.com's Customer Engagement and Mobile Engagement APIs, enabling agents to manage profiles, send push notifications, orchestrate campaigns, and handle data exports through typed tools. | |
| nfl-stats-mcp alexbrogan10/nfl-stats-mcp Enables Claude and other MCP clients to answer NFL questions using 25+ years of real nflverse play-by-play and player statistics. Provides tools for situational stats, leaderboards, player game logs, team schedules, and player name disambig | |
| Mode VC Radar MCP Server alexbuilding/modevc-radar-mcp Enables users to search verified VC investor theses, track live SEC Form D private placements and venture funding rounds, and query empirical AI valuation and unit economics benchmarks through natural language via Model Context Protocol. | |
| Avito Personal MCP alexbutiev/avito-personal-mcp Enables local-first, read-only interaction with Avito through your own authenticated Chrome session, without sharing credentials with the MCP client. Provides tools for searching listings, viewing your listings, favorites, chats, and messag | |
| binance-futures-mcp alexcandrabersiva/bin-mcp Comprehensive Binance Futures trading MCP server with 41 professional trading tools across account management, order execution, market data, and risk management. Features smart ticker caching, secure authentication, and Docker support for s | |
| Simple MCP MySQL Server alexcc4/mcp-mysql-server Enables AI assistants to securely interact with MySQL databases, including listing tables, viewing schemas, and executing read-only SQL queries through natural language. | |
| OpenGym Coach alexccgit/opengym-coach-sites Enables ChatGPT to manage fitness routines, guided sessions, workout history, body weight tracking, and statistics through a remote authenticated MCP server with read and write tools. | |
| OpsChugex LocalOps MCP alexcgodwin/localops-mcp Enables read-only inspection of local Windows and Linux systems for host, resource, network, service, software, identity, startup, certificate, SSH key metadata, and environment-variable name evidence through MCP tools. It normalizes platfo | |
| x402 Data Hub alexchai-dev/cloudflare-data-hub An official Model Context Protocol (MCP) server that provides AI agents with native, real-time access to high-value developer datasets. Currently supports SaaS/AI pricing comparisons, trending developer discussions (V2EX), and real-time Bas | |
| mcp-node-zig alexchen-sys/mcp-node-zig mcp-node-zig is an MCP server for remote machines. Drop it on a build box, a homelab server, a Windows host or a VPS, and any MCP client can run commands, drive long-running processes and read and write files there over one authenticated HT | |
| latex-workspace-mcp alexchen93/latex-workspace-mcp Provides restricted MCP tools for scanning, editing, compiling, and verifying LaTeX workspaces, enabling AI assistants to manage local LaTeX projects safely. | |
| aluris-caselibrary-mcp alexchenlin1996-pixel/aluris-caselibrary-mcp Enables semantic search and retrieval of Chinese judicial cases from the Supreme People's Court case library, supporting natural language queries for similar cases, case details, filtering, and statistics. | |
| chatgpt-mcp alexcodeplace/chatgpt-mcp A stateless MCP server that exposes explicitly configured Linux computer capabilities (filesystem, shell, process, service, app, browser, screen, and input tools) to ChatGPT or any compatible M####安徽11选5 >zgkj.com< dgz3rr ice-box两思Question: | |
| LeadMCP alexcojescu/automotive-lead-vertical- Provides multi-agent orchestration over MCP tool servers for CRM, inventory, calendar, and communications backed by SQLite mock adapters, enabling automotive dealership and rental lead qualification, vehicle recommendations, booking, and sa | |
| Gemini DeepSearch MCP alexcong/gemini-deepsearch-mcp An automated research agent that leverages Google Gemini models and Google Search to perform deep, multi-step web research, generating sophisticated queries and producing citation-rich answers. | |
| ui-react-mcp alexcruzgargallo/ui-react-mcp Enables AI assistants to query accurate, up-to-date documentation for a React component library, including component lists, search, props, allowed values, defaults, and validated JSX usage examples over stdio. | |
| Medusa.js Documentation MCP Server alexcs24/medusa.js-documentation-mcp-server Provides AI assistants with instant access to comprehensive Medusa.js v2 documentation, enabling smart search, precise section retrieval, and complete browsing through 2,105+ documentation sections. | |
| Basic MCP Server alexcz-a11y/jina-httpstreamable A minimal Model Context Protocol server template demonstrating basic implementation of tools, resources, and prompts built with Smithery SDK. | |
| Mem0 MCP Server alexcz-a11y/mem0mcp Enables storing and searching memories via Mem0 API directly from Cursor, allowing natural language interaction with persistent memory. | |
| Tessie MCP Server alexcz-a11y/tessie-mcp-fix Provides intelligent Tesla vehicle analytics and control through the Tessie API, including real-time status monitoring, charging cost optimization, efficiency trend analysis, trip planning, and predictive insights for Tesla owners. | |
| PlanfixMCP alexd73/planfixmcp MCP server for Planfix REST API that generates tools from an OpenAPI spec, exposing operations like task_list and comment_add with Russian descriptions, filtering, and response validation. | |
| asana-full-mcp alexday3000/asana-full-mcp Exposes the full Asana REST API via an MCP server, enabling operations like task management and workspace queries, with configurable safety guardrails. | |
| AxObfus alexdev-th/axobfus Enables coding agents to audit, defend, and verify owned or authorized artifacts by adding format-valid decoys and resource or semantic exhaustion, along with generating standalone offline HTML reports. | |
| Fastmail MCP Server alexdiazdecerio/fastmail-mcp-server Enables AI models to interact with Fastmail accounts via the JMAP API through the Model Context Protocol. It supports managing emails, accessing usage analytics, and performing account operations using secure token-based authentication. | |
| ghotels alexechoi/google-hotels-mcp An MCP server that gives AI agents live Google Hotels data (search, rooms, rates, cancellation) via internal RPC — no API key or scraping required. | |
| AWS Model Context Protocol Server alexei-led/cloud-mcp-server A lightweight service that enables AI assistants to execute AWS CLI commands through the Model Context Protocol (MCP), allowing AI tools to retrieve AWS documentation and interact with AWS services. | |
| K8s MCP Server alexei-led/k8s-mcp-server Enables Claude to run Kubernetes CLI tools (kubectl, istioctl, helm, argocd) in a secure, containerized environment via the Model Context Protocol. | |
| memex alexei425/memex Enables AI coding agents to save insights from completed tasks as atomic markdown knowledge cards with bidirectional links, then recall relevant cards before starting new work so context carries across sessions. Cards live in a shared local | |
| freellmpool alexei615/freellmpool Enables access to 178 pooled free-tier and keyless LLM chat routes through a single OpenAI-compatible endpoint, usable by coding agents, local proxies, and other MCP clients. It automatically selects only accessible enabled routes, fails ov | |
| Niblet alexei7807/niblet-skill-mcp Enables coding agents building UI to fetch real product screens as inline images, pull typed design references, and find licensed fonts, icons, or animated icons when a visual question is unresolved. It also serves a bundled design workflow | |
| Hegelion alexei78585/hegelion This MCP server enables MCP-enabled editors and agents to run dialectical reasoning for deep analysis and a player-coach autocoding loop for independently verified code implementation. |
26,201–26,250 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.