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 |
|---|---|
| CSS Tutor MCP Server ebimopondei/css-tutor-mcp-server Provides personalized CSS learning updates by tracking known concepts in memory, fetching latest CSS news via Perplexity, and guiding users through new CSS features they haven't learned yet. | |
| crossref-mcp ebiyu/crossref-mcp Enables retrieval of academic literature metadata via DOI or search using the Crossref REST API. | |
| pb-mcp ebiyy/pb-mcp Enables interaction with the Productboard REST API, providing tools to manage features, notes, companies, objectives, initiatives, key results, releases, webhooks, users, products, and components. | |
| AI Material Cabinet MCP eblics/ai-cailiaogui-mcp Enables AI assistants like Cursor and Claude Desktop to access a local AI Material Cabinet for searching, reading/writing content, creating documents, and retrieving chunks via MCP. | |
| audio-transcription-mcp ebmarquez/audio-transcription-mcp MCP server for audio transcription with speaker diarization. Transcribes MP3/WAV files using Faster-Whisper and pyannote.audio, outputs markdown with speaker labels, timestamps, summaries, and action items. | |
| renfield-mcp-calendar ebongard/renfield-mcp-calendar Unified MCP server for calendar access connecting Exchange (EWS), Google Calendar, and CalDAV through a single MCP interface, enabling multi-calendar event management via natural language. | |
| renfield-mcp-filesystem ebongard/renfield-mcp-filesystem Watches local and SMB folders for settled new files and pushes them into the Renfield knowledge base and Paperless over REST; also provides interactive MCP tools for browsing and on-demand file ingestion. | |
| renfield-mcp-scanner ebongard/renfield-mcp-scanner Enables scanning stacks of documents from a USB scanner, correcting and routing each page into exactly one configured Renfield instance, with barcode separator sheets, durable staging, and human review for ambiguous routing decisions. | |
| @x-idra/mcp-server-searxng ebongard/renfield-mcp-searxng Enables privacy-focused meta searches across multiple search engines through SearXNG, with category, language, time-range, and safe-search controls, plus fallback instances. It correctly treats reachable instances with zero results as empty | |
| renfield-mcp-tracking ebongard/renfield-mcp-tracking Multi-carrier parcel tracking server that communicates directly with carrier APIs (DHL, UPS, FedEx, etc.) without third-party aggregators, providing normalized tracking status and events. | |
| PICO-8 MCP Server ebonura/pico8-mcp-server An MCP server for analyzing, manipulating, and documenting PICO-8 game carts using the shrinko8 toolkit. It enables users to count tokens, minify code, validate carts, and access API documentation through natural language commands. | |
| Content Fetcher MCP ebonylouis/content-fetcher-mcp2 Fetches and tracks content from YouTube channels, RSS feeds, and GitHub releases with persistence to identify new items across sessions. | |
| Slander MCP ebop14/slander_mcp An MCP server that retrieves and ranks humorous roasts, jokes, and memes about real or fictional characters from Twitter/X. It leverages LLMs for intelligent query generation and uses social engagement metrics to identify and rank high-qual | |
| flow-planner ebowman/bike-mapper Enables planning Dublin/Wicklow road-cycling routes through natural language in Claude Code, ranking loops, out-and-backs and one-way rides by expected stops, climb or flat preference, and length target. Exposes tools for route planning and | |
| RescueTime MCP Server ebowman/rescuetime-mcp Enables comprehensive access to RescueTime productivity data and features through the Model Context Protocol. Supports analytics retrieval, focus session management, highlights creation, and offline time tracking through natural language in | |
| Xcode MCP Server ebowwa/xcode-mcp Provides programmatic access to Xcode functionality, enabling AI assistants to create, build, test, and manage iOS/macOS projects directly. | |
| Cin7 Core MCP ebragas/cin7-mcp Enables Claude users to query stock levels and purchase orders in a Cin7 Core account through read-only GET requests, including product availability, locations, on-order quantities, supplier due dates, and purchase order details. | |
| Recruit CRM MCP ebragas/recruitcrm-mcp MCP server for Recruit CRM, enabling AI assistants to search candidates, view jobs, and manage recruiting workflows. | |
| MCP Conta Azul ebrahimpleite/mcp-contaazul Enables AI assistants to interact with Conta Azul Financial APIs to manage accounts, balances, and transactions through natural language. It features specialized tools for tracking cash flow, processing payables and receivables, and generat | |
| obsidian-brainstorm ebrainiac/obsidian-brainstorm-mcp Connects Claude Desktop to an Obsidian vault, enabling reading, searching, capturing ideas, and managing notes through natural language. | |
| McPortfolio ebrandler/mcportfolio Enables LLM-driven portfolio optimization using natural language, providing tools for mean-variance, HRP, Black-Litterman, and other optimization methods. | |
| cursor-mcp ebrindley/cursor-mcp Enables delegating coding tasks to Cursor Cloud Agents from Claude Code, Codex, or Grok, with scoped repository access, progress monitoring, follow-ups, and result reporting. | |
| Affinity MCP Server ebuberpg-prog/affinity-codex-plugin Connects Codex to Affinity's native local MCP server through a local SSE-to-stdio bridge, enabling document inspection, vector and photo editing, page layout work, native previews, and reusable scripts without any cloud server or API key. I | |
| Cavalry MCP Server ebuberpg-prog/cavalry-codex-plugin Enables Codex to inspect compositions, build procedural motion graphics, execute scripts, and develop reusable tools through the application's local MCP tools. | |
| Vault as MCP ebullient/obsidian-vault-mcp An Obsidian plugin that runs an MCP server, enabling external LLM tools to read, search, create, and modify notes in your vault via HTTP or stdio transport. | |
| mcpy ebursztein/mcpy Enables AI agents to fetch web pages as markdown or HTML, grep them for patterns, search the web, news, images, videos, shopping, jobs and places, and look up scholarly papers — over MCP or REST. It self-hosts on Cloudflare Workers with a p | |
| sprinty ebursztein/sprinty A disciplined-sprint MCP server for AI coding agents, providing structured sprint management with immutable append-only ledger, programmatic close-gates, and live dashboard. | |
| tapetide-mcp ebutt9584/nse-bse-indian-stock-market-data-mcp Enables AI assistants like Claude, ChatGPT, Cursor and VS Code Copilot to search, screen and analyze 8,200+ NSE and BSE listed stocks using 55 tools covering live quotes, quarterly financials, a 326-ratio screener, technical indicators, FII | |
| Chunky MCP ebwinters/chunky-mcp An MCP server that manages chunking and reading of large responses, allowing tools to handle oversized data that would otherwise fail. | |
| EDCB MCP Server ebycow/edcb-mcpserver Enables LLMs to control EDCB, a broadcast recording software, allowing program information retrieval and reservation management. | |
| codemode-mcp-gateway ec-9624/codemode-mcp-gateway Exposes a single execute tool so agents can discover, inspect schemas for, and compose calls to connected upstream MCP servers by writing JavaScript that runs in a fresh sandboxed QuickJS VM. Results from combined tool calls are returned as | |
| MCP Multi-Agent Orchestration Server ec49ca/nlp-project-contract-comparison Orchestrates multiple AI agents to process complex queries by intelligently splitting tasks, executing them in parallel, and synthesizing results using local Ollama LLM inference. | |
| TezosX MCP ecadlabs/tezosx-mcp Provides Tezos wallet management and blockchain interaction tools for AI agents, including support for the x402 payment protocol. It enables tasks like sending XTZ, checking balances, and managing automated payments for services like NFT mi | |
| Enhanced Gemini MCP Server ecampossoria/gemini-mcp-enhanced Leverages Google's Gemini AI with a 1M token context window for comprehensive codebase analysis, enabling intelligent code search, architecture analysis, and targeted improvement suggestions. | |
| Sync Licensing MCP Server ecarcamo/mcp-local-redes A local MCP server for music sync-licensing that enables searching tracks, checking rights clearance, calculating license costs, generating contracts, and registering usage via JSON-RPC 2.0. | |
| eCash MCP Server ecashprotocol/ecash-mcp-server Enables AI agents to interact with the eCash ecosystem on Base mainnet, providing tools for mining, wallet operations, job marketplace, and reputation management. | |
| baserCMS MCP Server ecatchup/basercms-mcp Model Context Protocol server implementation for operating baserCMS that enables GitHub Copilot and other agent modes to interact with baserCMS through its API. | |
| Ecclium MCP für ChurchTools ecclium/mcp-churchtools Enables AI assistants to read and, where permitted, write data in ChurchTools, schedule recurring tasks like weekly service rosters, and review or revert changes for security and transparency. | |
| LeetCode MCP Server ece14435/leetcode-mcp-server Enables automated access to LeetCode problems, contests, solutions, and user profiles across both leetcode.com and leetcode.cn, with optional session-cookie authentication for private notes, progress tracking, and code execution or submissi | |
| Excalidraw Architect MCP ece6192/excalidraw-architect-mcp Turns structural descriptions of systems, processes, data models, and charts into auto-laid-out, hand-drawn .excalidraw files across 25 diagram types, with natural-language revision and SVG/PNG export. Runs fully offline in Cursor, Claude C | |
| SandBase CLI ecec291/cli It connects supported AI clients to over 2,000 models and APIs, enabling discovery, inspection, execution, OAuth sign-in, and rollback. | |
| Stock MCP ececho/stock-mcp Enables AI agents and backends to query A-share, US equity, ETF, index, and crypto market data with technical indicators, fundamentals, money flow, news search, and SEC/A-share filings through MCP tools. Also exposes CSV/JSON code-export en | |
| Glance ececoleman49191/glance An MCP server that gives Claude Code a real browser, letting it navigate pages, click and type, capture inline screenshots, inspect console and network activity, and run multi-step test scenarios with visual regression checks. It enables en | |
| Currency Exchange MCP Server ecedalpolat/mcp-exchange Enables real-time currency exchange rate queries between any two currencies using ExchangeRate API, with automatic triggering by AI models through the MCP protocol. | |
| Bitbucket MCP eceleroy3460/bitbucket-mcp Enables AI assistants to list and retrieve repositories, inspect repository details, and fetch or create pull requests through Bitbucket Cloud and Server APIs. | |
| Deep Code Reasoning MCP Server ecelewis617/deep-code-reasoning-mcp Enables Claude Code to hand off complex code analysis to Google Gemini, supporting huge-context trace and log correlation, execution-flow tracing, cross-service impact analysis, performance bottleneck detection, and hypothesis-driven debugg | |
| S&P 500 MCP Server ecelewis72566/sp500-mcp-server Enables querying S&P 500 company data from Supabase, including fundamentals, annual financial metrics, historical OHLCV prices, news with sentiment filtering, officers and compensation, and SEC filing history with type and date filters. Shi | |
| Turbular ecely035/turbular Enables LLM agents to connect to multiple database types, retrieve normalized schemas, and execute optimized SQL queries through a unified API. | |
| Financial Modeling Prep MCP Server ecemendoza702/financial-modeling-prep-mcp-server Enables AI assistants to access and analyze financial data, stock information, company fundamentals, and market insights through 250+ tools spanning stocks, ETFs, crypto, forex, commodities, and economics. Supports dynamic, static, or full | |
| Korean DART MCP eceparker727/korean-dart-mcp Enables AI assistants to query Korean DART disclosure data through 15 tools, covering filings, financials, ownership, XBRL, and document conversion. It also supports Buffett-style analyst frames for insider signals, accounting risk, and qua |
46,801–46,850 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.