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 |
|---|---|
| wanderlog-mcp dpolyakov04/wanderlog-mcp Enables Claude or any MCP-compatible agent to view and build complete Wanderlog trip itineraries through conversation. Supports adding places, notes, hotels, transit legs, car rentals, checklists, and expenses, plus searching places, guides | |
| demo-app-mcp-prestamo dponcedeleonf/demo-app-mcp-prestamo MCP server demo by Banco D that shows a loan application interactive widget across six steps, demonstrating three levels of agent visibility (full, result-only, and hidden) per MCP Apps (SEP-1865). It enables users to simulate a loan reques | |
| cookbook-brain dpro10/cookbook-brain An MCP server that gives AI agents persistent, file-based memory stored as plain markdown files in a local git repository, enabling agents to remember, recall, and build on information across sessions. | |
| WakaTime MCP Server dpshde/wakatime-mcp Provides access to WakaTime coding analytics data through MCP tools. Enables querying coding stats, activity summaries, project lists, and time tracking information from your WakaTime account. | |
| Seedance MCP dpspace2050/seedance-mcp Enables video generation using the Seedance 2.0 model through MCP, supporting both OpenAI and Volcengine API formats with tools for creating, monitoring, and downloading videos. | |
| tldraw-mcp dpunj/tldraw-mcp A minimal MCP server for AI-driven canvas manipulation and visualization using tldraw. It enables AI clients to programmatically create, update, and manage shapes, flowcharts, and frames on a live interactive canvas. | |
| meshcore-mcp dpup/meshcore-mcp A Model Context Protocol server that exposes a MeshCore node and the mesh reachable through it as a clean, high-signal interface for AI agents or tools. | |
| FogBugz MCP Server dpupek/fogbugz-mcp Enables interaction with FogBugz issue tracking system through its XML API, allowing users to search, create, update, and manage cases, comments, and attachments directly from their MCP client. | |
| astrotation dpush91/astrotation Visual feedback for AI coding agents on Astro sites, providing live annotations with source file:line, CSS selector, Tailwind classes, and computed styles. | |
| VRChat Project MCP dpwgc/vrchat-project-mcp A Unity editor MCP plugin that exposes 49 tools over HTTP for managing Unity projects and editing VRChat avatars, including expressions, parameters, and performance stats. | |
| gitlab-mcp-server dq042000/gitlab-mcp-server A TypeScript-based MCP server that enables code search, file reading, and project management via the GitLab API. | |
| grok-mcp dq52099/grok-mcp MCP server providing web search, news search, and X/Twitter search capabilities via HTTP or stdio. | |
| singular-mcp-server dqbuilds/singular-mcp-server Enables AI agents to read, control, and orchestrate Singular.live live broadcast graphics compositions, including filling control nodes, animating sub-compositions, and running a newsroom rundown-to-graphics workflow. | |
| Compresto MCP dqhieu/compresto-mcp A Model Context Protocol server that provides AI assistants with real-time data about Compresto's file compression app usage statistics, including total users, processed files, and total size reduced. | |
| Zip Hive Scaffold dqrshan/ziphive-scaffold MCP server for bulk-creating files and folders for any project, with built-in templates and custom scaffold support. | |
| glm4v-vision-mcp dqtx760/glm4v-vision-mcp MCP server that provides image analysis, OCR text extraction, and image description using the GLM-4V Flash model from Zhipu AI. | |
| DSH Subagent MCP dqtz5vpvj9-create/dsh-subagent-mcp Enables Codex to delegate coding tasks to a persistent DeepSeek Harness agent that can read repositories, edit files, and run tests, while letting users follow up, monitor progress, and interrupt the work. | |
| Roundtable AI dqureshi71/roundtable A local MCP server that lets a primary AI assistant delegate parts of a prompt to specialized sub-agent CLIs (Gemini, Claude, Codex, Cursor), which run in parallel against a shared context bundle. It then aggregates their findings into a si | |
| MCP ArchiMate Server dqxorg/mcp-archimate Enables AI assistants to read and write ArchiMate models stored in CoArchi XML format. Query elements, create relationships, design diagrams, and sync changes to Git through natural language. | |
| RCS X MCP Server dr-agentic/rcsx-mcp-server Lets AI assistants draft rich-card messages, preview them in an interactive iPhone widget, validate carrier support, and send RCS Business Messages from inside the chat. | |
| Instagram MCP Server dr-ashraf-s-mcp-labs/instagram-mcp user can control instagram account with claude web | |
| remotion-mcp-server dr-ashraf-s-mcp-labs/make-reels-with-claude Enables Claude to analyze reference videos (download, transcripts, frames) and generate new branded Instagram Reels/YouTube Shorts as React/TSX compositions, rendered to MP4 via Remotion. | |
| video-editor-mcp dr-ashraf-s-mcp-labs/video-editor-mcp An MCP server that gives Claude a conversational video-editing toolkit — trim, crop, color grade, caption, beat-sync, stabilize, and more — built on ffmpeg, faster-whisper, and yt-dlp, with optional DaVinci Resolve and CapCut integration. | |
| video-watcher-mcp dr-ashraf-s-mcp-labs/video-watcher-mcp An MCP server that lets Claude Desktop watch videos from YouTube, Instagram, Facebook, or direct URLs, extracting transcripts and key frames to summarize and answer questions about video content. | |
| tessera dr-code/tessera Provides persistent codebase memory for Claude Code, enabling semantic understanding of the project structure and action history across sessions to reduce redundant file reads. | |
| attach-cdp-mcp dr-sherbaz/attach-cdp Lets AI agents drive the Chromium browser you are already logged into by connecting an MCP client to its live tabs instead of launching a separate private profile. | |
| cml-mcp-server dr-stutters/cml-mcp-server Enables AI assistants to explore, build, run, and troubleshoot Cisco Modeling Labs (CML 2.x) network topologies, including lab construction from specs, console command execution, reachability testing, packet capture analysis, link impairmen | |
| cnc-mcp dr-stutters/cnc-mcp Enables AI agents to query and manage Cisco Crosswork Network Controller resources such as devices, credential profiles, providers, topology, tags, alarms, users, applications, and inventory jobs, with optional write operations for creating | |
| ise-mcp-server dr-stutters/ise-mcp-server Enables an assistant to troubleshoot Cisco ISE authentications and inspect or modify NADs, endpoints, users, policy, certificates, and TrustSec through the OpenAPI, ERS, and MnT REST surfaces. Supports authentication failure diagnosis, endp | |
| pentest-mcp-server dr-yato/pentest-mcp-server Enables authorized penetration testing and security assessments with CVE monitoring, vulnerability scanning, and reporting features. | |
| local-websearch-mcp dr34dl10n/websearch-mcp Small Python MCP server that provides web search and page fetching tools via DuckDuckGo, requiring no API key. | |
| Multi-Domain Booking MCP Server dr4g0n-h4ck3r/mcp_server Enables booking for movies, flights, trains, and buses with a 2-step confirmation flow and idempotency keys. | |
| OpenAlex Author Disambiguation MCP Server drabreu/alex-mcp Enables streamlined academic research and author disambiguation by providing AI agents with optimized access to the OpenAlex.org API. It supports searching for authors, resolving institutional affiliations, and retrieving scholarly works wi | |
| FRED API MCP Server dracepj/fred-mcp Enables searching and retrieving economic data from the Federal Reserve Economic Data (FRED) API, including time series, categories, releases, and popular indicators. | |
| ai-readme-manager draco-cheng/ai-readme-mcp A smart documentation system that helps AI assistants understand and follow your project's conventions by automatically discovering, routing, and managing AI_README.md guide files. | |
| YouTube Current Data MCP dracoform/chatgpt-youtube-mcp Enables ChatGPT to retrieve current YouTube metadata, channel uploads, search results, and transcripts via read-only MCP tools. | |
| pharmakon-mcp dracstuart/pharmakon-mcp Enables looking up drug and molecule data — identifiers such as InChIKey, SMILES, CAS, and ChEMBL IDs, plus measured and computed properties and drug information — across PubChem, ChEMBL, and Wikidata. Every returned value carries its cited | |
| DHIS2 MCP Server dradebo/dhis2-mcp Enables comprehensive interaction with DHIS2 health information systems through 40+ tools covering complete Web API functionality. Supports data management, tracker programs, analytics, and bulk operations for DHIS2 development and administ | |
| membank draekien-industries/membank LLM memory management system that stores corrections, preferences, decisions, and learnings in a local SQLite database with semantic search, exposed as an MCP server for automatic memory read/write by any MCP-compatible LLM harness. | |
| sleeper-mcp draffetseder/sleeper-mcp Enables AI models to manage and query fantasy sports leagues through the Sleeper API, supporting tasks like player lookups, league activity, and draft management. | |
| mytime-mcp dragan-mytime/mytime-mcp Remote MCP server for MY:TIME's competitive intelligence platform. Enables querying competitor e-commerce data, social metrics, and demand estimates via Claude, Power BI, and other tools. | |
| Storeshot MCP Server draggable/storeshot-mcp Enables MCP-compatible coding agents to read App Store and Google Play screenshot requirements, upload local images, generate complete store screenshot sets, track jobs, and download results into project or fastlane folders. | |
| Crawl4Claude dragomirweb/crawl4claude A comprehensive, domain-agnostic documentation scraping and AI integration toolkit. Scrape any documentation website, create structured databases, and integrate with Claude Desktop via MCP (Model Context Protocol) for seamless AI-powered do | |
| gitlab-mcp dragomirweb/gitlab-review-mcp An MCP server that enables AI agents to perform automated code reviews on GitLab merge requests, including fetching details, reading diffs, posting inline comments, managing labels, and approving or unapproving MRs. | |
| kospi-kosdaq dragon1086/kospi-kosdaq-stock-server An MCP server that provides KOSPI/KOSDAQ stock data using FastMCP. | |
| news-agent dragondoctor2033/newday Enables Claude to access fetched RSS news, event clusters, and archives to generate digests, watch for urgent alerts, and answer news-related queries via MCP tools. | |
| iceberg-mcp-server dragonejt/iceberg-mcp-server MCP Server for Apache Iceberg, enabling users to read, query, and manipulate data within Iceberg catalogs. | |
| opendata-mcp dragonheart8787/opendata-mcp Provides access to Taiwan open data including weather forecasts, earthquake reports, and air quality indices via natural language queries. | |
| tavily-rotator-mcp dragonheartcra/tavily-rotator-mcp Pools multiple Tavily API keys into a single local MCP server with round-robin rotation and automatic failover, exposing Tavily search, extract, crawl, map, and research tools to AI agents via stdio. | |
| MCP-ArcKnowledge dragonjump/mcp-arcknowledge With this you can you can easily manage and query your list of knowledge base(webhook endpoints). You can add new document sources by registering their URLs, and optionally provide a description and API key.
You can also list all the regis |
45,801–45,850 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.