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 |
|---|---|
| websearch baozoulolw/searchhub Enables aggregated web searches across multiple providers with automatic failover, exposing search and source-listing tools via a streamable HTTP MCP endpoint secured by bearer token authentication. | |
| mcp-officecli-bridge bapakstack/mcp-officecli-bridge Streamable HTTP bridge that exposes OfficeCLI MCP tools (create, view, query, etc.) to Gemini Spark via a hosted server, deployable on Coolify. | |
| mcp-markdown-to-docx baptiste4321/mcp-markdown-to-docx Enables AI agents to convert Markdown into styled Word (.docx) documents, with control over fonts, colors, and layout via parameters. | |
| LinkedIn MCP Server baptitse-jn/linkedin_mcp A comprehensive Model Context Protocol server that enables AI assistants to interact with LinkedIn APIs for profile management, content creation, networking, messaging, and analytics. | |
| AI Optimizer MCP barackndenga/ai-task-optimizer-mcp A multi-task MCP server for AI code optimization and testing that integrates with VSCode/Cursor, CLI tools, and autonomous agents. It provides tools for running tests, generating code improvements, and managing objectives across different e | |
| Qoyod MCP Server baraeyah1989/qoyod-mcp-server Connects Claude to the Qoyod accounting system via its REST API, enabling natural language management of customers, invoices, vendors, journal entries, and other accounting resources through MCP tools. | |
| CMeIn MCP server barakburger/cmein-mcp Enables AI assistants to answer dating-profile photo questions from published articles with source links, read live pricing and policy pages, and, after account sign-in, check credits, review generations, find scenes, and request credit ret | |
| Lightroom MCP Elite baramesh/lightroom-mcp-elite Enables AI agents to control Adobe Lightroom Classic develop settings, manage presets and catalogs, and perform round-trip handoffs with Adobe Photoshop for advanced retouching. Provides native socket bridging for exposure, color grading, s | |
| Photoshop MCP Elite baramesh/photoshop-mcp-elite Enables AI agents to drive Adobe Photoshop on macOS through natural language, covering autonomous Adobe Firefly generative fill and object removal, Sensei AI sky and subject selection, non-destructive layer, adjustment, and text tooling, pl | |
| playwright-generate-mcp baramubarok/playwright-mcp Enables AI coding assistants to generate, score, run, and auto-heal Playwright E2E tests while enforcing domain-driven page object architecture and anti-flakiness rules. | |
| MediaWiki MCP Server baran1228/mediawiki-mcp-server Enables LLM clients to read, search, create, edit, and manage pages, files, categories, and revision history across any MediaWiki wiki, with OAuth-authenticated write operations and multi-wiki support. Extension packs add structured data an | |
| S&P 500 MCP Server baran1479/sp500-mcp-server Enables querying S&P 500 company fundamentals, annual financial metrics, historical price data, news sentiment, officers, and SEC filings from Supabase through MCP tools, with elicitation for resolving ambiguous company matches and embedded | |
| fcp-mcp-server baran47092/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro timelines from exported FCPXML — trimming, splitting, silence removal, markers, roles, keyframes, transcript-based editing, and cross-NLE export — with journaled, undoable writes | |
| Video Games MCP Server barandev/videogames-mcp-server Provides direct access to the RAWG gaming database, allowing users to search for games, retrieve detailed metadata, and explore genres within Claude. It streamlines game research by offering information on ratings, platforms, and release da | |
| Books & Film MCP Server baraninja/film-books-mcp A comprehensive MCP server for searching books, films, and scholarly publications across multiple APIs like Open Library, Google Books, TMDb, and Crossref, with advanced filtering and deduplication. | |
| Perplexity MCP Server barankrky/perplexity-mcp Exposes Perplexity AI's search and synthesis capabilities through MCP, enabling Claude Desktop and other MCP clients to search the web, synthesize sources, and get cited answers. | |
| awesome-mcp-dev-stack-selector barankurtulusozan/awesome-mcp-dev-stack-selector A machine-readable FOSS registry and zero-latency MCP server for AI coding agents to search free and open-source software alternatives to commercial tools, with capabilities to find replacements, get app details, and search by query. | |
| MCP Deep Research baranwang/mcp-deep-research Enables web search and deep research capabilities through the Tavily API, allowing users to gather comprehensive information from the web with configurable search parameters and planning rounds. | |
| Trends Hub baranwang/mcp-trends-hub A MCP server that aggregates hot trends and rankings from various Chinese websites and platforms including Weibo, Zhihu, Bilibili, and more. | |
| mcp-tung-shing baranwang/mcp-tung-shing A Model Context Protocol plugin for Chinese Tung Shing (黄历/通勝/通胜) almanac calculations | |
| SPOKEAgent baranzinilab/spokeagent A structure-aware MCP server for querying the SPOKE biomedical knowledge graph, enabling entity resolution, schema introspection, path finding, and safe Cypher queries for biomedical knowledge inference. | |
| Plesk Extensions Guide MCP Server barateza/mcp-plesk-extension-guide Provides semantic search capabilities over the Plesk Extensions Guide documentation using Retrieval-Augmented Generation (RAG) and vector embeddings. It enables AI assistants to retrieve relevant technical information and answer natural lan | |
| obsidian-mcp barath-koottala/obsidian-mcp Enables Claude to read your Obsidian vault and retrieve outstanding tasks from daily notes by parsing checkboxes. | |
| Universal Web Data Extraction Platform barath2812/mcp Enables LLMs to extract content from websites using automated static and dynamic scraping engines with built-in anti-bot protections. It provides tools for web data retrieval and stores results in MongoDB with support for JSON and CSV expor | |
| flight-mcp baratharjun-b/travel_mcp Enables natural-language search, booking, and management of simulated flights using a local SQLite database through Claude Desktop. | |
| apple-health-shortcuts-mcp barbara-105/apple-health-shortcuts-mcp Exposes read-only Apple Health data (current status, sleep details, trends) to AI via a Cloudflare-deployed MCP server and iPhone Shortcuts. | |
| jev-browser-mcp barbara88985/jev-browser Enables LLM-driven browser automation in which the caller states one outcome per step and Jev (Typesafe System One) decides the target element, action, value, and whether the step is done, blocked, erroring, or irreversible, while Playwrigh | |
| opencode-mcp barbarabonnet6196/opencode-mcp Connects Claude, Cursor, VS Code, and other MCP clients to OpenCode's headless API, enabling users to ask questions, implement features, monitor background work, respond to questions and permissions, and review changes across projects. It p | |
| MiniMax-Coding-Plan-MCP barbarabutt3196/minimax-coding-plan-mcp Enables users to perform AI-powered web searches and analyze images through MCP clients, enhancing code development workflows. | |
| vivado-mcp barbarad07/vivado-mcp Enables AI agents such as Claude Code, Cursor, and Codex to safely drive a locally installed Xilinx Vivado through 32 MCP tools spanning GUI/Tcl/attach sessions, synthesis, implementation, timing and CDC analysis, XDC/IO validation, IP insp | |
| CVE-Search MCP Server barbarad19536/cve-search_mcp Enables querying the CVE-Search API to browse vendors and their products, retrieve vulnerabilities per vendor/product, fetch individual CVE details, and list the latest CVEs with CAPEC, CWE, and CPE expansions. Also exposes current database | |
| Email MCP Server barbaraharris2328/email-mcp Enables AI assistants to read, search, send, manage, schedule, and analyze email across multiple IMAP and SMTP accounts, with tools, prompts, and resources exposed over the Model Context Protocol. It also supports real-time inbox watching w | |
| PrismSRE barbaria888/prismsre PrismSRE is an AI-powered Kubernetes troubleshooting agent that uses Google's Gemini models and the Model Context Protocol to provide autonomous diagnostics and real-time insights for cluster issues. It features a glassmorphism dashboard an | |
| barbaros-mcp barbarkaragul-oss/barbaros-mcp Serves read-only public datasets over the Model Context Protocol, starting with the PrivacyMatrix dataset of AI app privacy practices. | |
| apple-health-semantic-mcp barbaroso/apple-health-semantic-mcp Query Apple Health export data with an LLM via a semantic layer that avoids common data traps, enabling accurate natural-language queries about health metrics. Optionally imports CPAP therapy data for correlation. | |
| OSCAR MCP Server barbaroso/oscar-mcp A read-only MCP server that allows AI assistants to analyze CPAP/BiPAP therapy data from OSCAR by querying its local SQLite database, with privacy protections and tools for summarizing and investigating sleep therapy metrics. | |
| jev-browser-mcp barbieri50751/jev-browser Enables browser automation in which a planning LLM states one outcome at a time while a Typesafe System One model decides which element, action, and value to use, with Playwright carrying it out. Exposes tools for opening pages, driving mul | |
| aipulsegeorgia barbosa520/awesome-ai-pulse-georgia Enables Claude Code, Cursor, Codex, and any MCP-compatible client to search, list, and retrieve entries from a curated collection of 378 AI agent frameworks, developer tools, and automation repositories using natural language, with category | |
| Civil3D MCP Server barbosaihan/civil3d-mcp Enables AI assistants to interact with Autodesk Civil 3D, allowing them to retrieve project data, create/modify/delete drawing elements, and execute code to automate Civil 3D operations. | |
| rankforge barbudda/rankforge-cli Enables AI coding assistants to audit a site's technical SEO and AI-search readiness — including localhost dev servers — and retrieve rule explanations, fix templates, and generated llms.txt files so the assistant can edit the repo to resol | |
| Directus MCP Server barc1999/directus-mcp-server Enables AI tools to connect to a Directus API and read collection items, retrieve the current user, and discover available collections and fields. | |
| garmin-mcp barcia/garmin-mcp Gives MCP clients read-only access to Garmin Connect data through Garmin's official Personal API, exposing daily metrics, sleep, activities, body composition, and related wellness endpoints via OAuth-protected remote tools. | |
| Resolve Claude MCP barckley75/resolve-claude-mcp Connects DaVinci Resolve Studio to Claude AI via the Model Context Protocol, enabling natural language control over video editing, color grading, Fusion compositing, AI features, and more. | |
| fpgaZeroMCP bard0-design/fpgazeromcp Provides AI assistants with a complete FPGA toolchain for HDL linting, simulation, synthesis, and place-and-route across various hardware targets. It features a GitHub-backed IP core registry that enables users to search for and import MIT- | |
| anytype-mcp-remote bardaxx/anytype-mcp-remote Enables MCP clients that support remote servers, such as ChatGPT, to securely search, fetch, list, and optionally create or update objects in a self-hosted Anytype space over HTTPS. | |
| claude-worker-delegation bardylaw/claude-worker-delegation Enables Claude Code to offload bulk tasks to cheap OpenRouter worker models via tiered model selection, parallel batch execution, daily budget caps, and cost logging. | |
| BareMCP barecommerce-core/baremcp Enables AI assistants to manage BareCommerceCore e-commerce stores through 46 tools covering products, orders, customers, categories, pages, media, webhooks, and analytics. Uses secure OAuth authentication without requiring API keys in chat | |
| watashi-db bareforge/watashi-db Provides a local, persistent context database for AI tools via MCP, enabling them to recall user preferences, decisions, and experiences across sessions. It is fully local with optional sync, and works with any MCP client. | |
| Bellink MCP Server barflotek/bellink-mcp Connects AI assistants to over 30 business tools like Gmail, Slack, and Airtable through a single unified interface. It enables users to perform actions across multiple platforms using natural language without managing individual API integr | |
| ai-memory-mcp bargisula/ai-memory-mcp Provides AI coding agents with a local, Markdown-first shared memory, enabling them to record decisions, failures, progress, and handoffs and retrieve them across sessions via MCP tools. |
32,951–33,000 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.