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 |
|---|---|
| Gemini Transcription MCP danielrosehill/gemini-transcription-mcp An MCP server for audio-to-text transcription using Google's Gemini API via OpenRouter, offering multiple tools for raw, cleaned, or formatted transcripts with support for local and remote deployment. | |
| K3B-MCP danielrosehill/k3b-mcp Enables burning optical media via the K3b CLI. Supports listing drives, burning data discs, and executing arbitrary k3bcli commands. | |
| MetaMCP Admin MCP danielrosehill/metamcp-admin-mcp Enables AI agents to administer MetaMCP instances by managing servers, namespaces, endpoints, and API keys across multiple deployments. Supports full CRUD operations, bulk server imports, cross-instance cloning, and granular tool management | |
| Miklat MCP danielrosehill/miklat-mcp An MCP server that helps AI agents find public shelters in Israel. Currently supports Jerusalem with 198 shelters. | |
| Daniel Rosehill's MCP Installer danielrosehill/my-mcp-installer Manages installation and configuration of MCP servers across multiple clients (Claude Code, Cursor, VS Code) from a personal GitHub registry, with support for API key management and bulk installations. | |
| Open Router Audio Transcription MCP danielrosehill/or-audio-transcription-mcp MCP server for audio transcription using OpenRouter models, supporting verbatim, cleaned, and custom transcription modes. | |
| Save-To-NAS MCP danielrosehill/save-to-nas-mcp Enables saving files and folders to a local NAS over NFS with automatic share discovery, smart mounting, and seamless file transfers. | |
| PostgreSQL MCP Server danielrsnell/postgres-mcp Provides read-only access to PostgreSQL databases, enabling LLMs to inspect database schemas and execute read-only SQL queries within a secure transaction context. | |
| Pingfusi daniels411/pingfusi Enables coding agents to publish work mid-task and route it to real human reviewers who pin comments to specific elements and return a verdict, so the agent can iterate until a person approves. | |
| BOSS 直聘 MCP Server daniels485/boss-zhipin-mcp Enables AI assistants to automate a recruiter's BOSS 直聘 workflow by driving an already-logged-in Chrome browser through the Model Context Protocol, so they can batch-search and deduplicate candidates, capture Canvas-rendered resumes as scre | |
| Italian Cities MCP Server danielsaban/mcp-server-crud-elasticsearch Provides CRUD tools for managing a database of Italian cities backed by Elasticsearch. It enables AI assistants to search, create, update, and delete city records through a standardized Model Context Protocol interface. | |
| U.S. Census Bureau Data API MCP danielsahin6719/us-census-bureau-data-api-mcp Connects AI assistants with official Census Bureau statistics, enabling dataset discovery, geography FIPS resolution, and aggregate data retrieval from the Census Data API and a local Postgres database. | |
| OSDU MCP Server danielscholl-osdu/osdu-mcp-server Enables AI assistants to interact with OSDU platform services including search, data management, and schema operations. | |
| Agile Team MCP Server danielscholl/agile-team-mcp-server Enables users to leverage a team of specialized AI agent personas like Business Analysts and Product Managers through a unified interface across multiple LLM providers. It streamlines agile development workflows by providing tools for model | |
| Backlog Manager MCP Server danielscholl/backlog-manager-mcp A task tracking and backlog management tool that enables AI assistants to create, organize, and track issues and tasks with status workflow through MCP protocol. | |
| mvn-mcp-server danielscholl/mvn-mcp-server Maven MCP Server enables AI assistants to manage Maven dependencies through natural language, including version checking, security scanning, and dependency analysis. | |
| obsidian-rag-mcp danielscholl/obsidian-rag-mcp Enables semantic search over an Obsidian vault using natural language, retrieving relevant notes and extracted conclusions. | |
| OSDU MCP Server danielscholl/osdu-mcp-server AI-powered access to OSDU subsurface data through natural language, enabling AI assistants to interact with the OSDU platform via conversational interfaces for search, schema management, records, and compliance. | |
| frappe-api-mcp danielsebastianc/frappe-api-mcp Enables interaction with Frappe and ERPNext sites through their REST API endpoints. It supports standard HTTP methods for performing CRUD operations and managing site data using natural language. | |
| NetWarden danielshaji1/home-network-mcp Enables AI assistants to discover, configure, harden, and troubleshoot multi-brand home and homelab networks through MCP, backed by declarative Terraform/OpenTofu orchestration. Includes safety guardrails, drift detection, snapshots, rollba | |
| beyondcompare-mcp danielsimonjr/beyondcompare-mcp Enables file comparison, folder diffing, 3-way merging, folder sync, and scripted automation through MCP. | |
| dropbox-mcp danielsimonjr/dropbox-mcp Dropbox MCP server to recover deleted files, list revisions, search content, and force-download cloud-only files via server-side API. | |
| Everything MCP Server danielsimonjr/everything-mcp Enables instant file and folder searching on Windows using Everything's blazing-fast search engine, supporting powerful search syntax including wildcards, regex, size filters, date filters, and comprehensive file information retrieval. | |
| fzf MCP Server danielsimonjr/fzf-mcp Enables fuzzy file searching, list filtering, and content searching using fzf's blazing-fast fuzzy matching algorithm. Self-contained with automatic fzf binary installation and cross-platform support. | |
| Math MCP Server danielsimonjr/math-mcp Provides secure mathematical computation capabilities including expression evaluation, symbolic math (derivatives, simplification), matrix operations, statistics, and unit conversion, with multi-tier acceleration through WebAssembly and Web | |
| Enhanced Knowledge Graph Memory Server danielsimonjr/memory-mcp An enhanced fork of the official MCP memory server that enables persistent knowledge graph storage with automatic timestamps, tags, importance levels, date range search, comprehensive statistics, and multi-format export (JSON, CSV, GraphML) | |
| Substack MCP Server danielsimonjr/substack-mcp Enables interaction with Substack publications through natural conversation, allowing users to create posts with cover images, publish notes, manage content, and retrieve profile information. | |
| UpMath MCP Server danielsimonjr/upmath-mcp Enables Claude Code to render LaTeX equations, TikZ diagrams, and documents into SVG or PNG formats via the UpMath API. It supports a wide range of TeX Live packages and syntax validation without requiring a local TeX installation. | |
| verify-mcp danielsimonjr/verify-mcp Enables AI coding agents to run the veriharness verification CLI as MCP tools, covering model probing, benchmark drivers and runners, scoring, grading, materialization, environment derivation, and reading run artifacts. It spawns the CLI an | |
| MCP Media Player danielsims/mcp-media-player Connects Home Assistant media players to Cursor, allowing automated control of playback (play/pause) based on agent activity for dopamine-driven development breaks. | |
| MCP Gateway danielsmag/aisafenet A FastAPI-based MCP gateway that aggregates multiple MCP servers, applies per-server tool allow/block policies, and re-exposes them as streamable HTTP MCP endpoints. It includes a local LLM safety guard for SQL/PII checks and a request hist | |
| ClawQL danielsmithdevelopment/clawql An MCP server for API discovery and execution with a token-efficient search -> execute workflow over OpenAPI, Google Discovery, and optional native GraphQL and gRPC sources. | |
| Lighthouse MCP danielsogl/lighthouse-mcp-server MCP server that enables AI agents to perform comprehensive web audits using Google Lighthouse with 13+ tools for performance, accessibility, SEO, and security analysis. | |
| CamoFox MCP danielsson10170/camofox-mcp Enables MCP-compatible AI agents to navigate, interact with, and automate the web through an anti-detection browser, with tools for tabs, search, extraction, downloads, sessions, and batch workflows. | |
| Financial Modeling Prep MCP Server danielsson18/financial-modeling-prep-mcp-server Enables AI assistants to access, search, and analyze financial data—including stocks, ETFs, crypto, forex, commodities, company fundamentals, earnings, and economic indicators—through a large catalog of flexible toolsets. | |
| Tapetide danielsson8401/nse-bse-indian-stock-market-data-mcp Lets AI assistants search, screen and analyze all 8,200+ NSE and BSE listed stocks with live quotes, quarterly financials, a 326-ratio screener, technical indicators, FII/DII flows, option chains and IV, corporate filings, IPOs and portfoli | |
| Filmladder MCP Server danielsteman/filmladder-mcp Provides movie listings, showtimes, and personalized recommendations for Amsterdam cinemas by scraping filmladder.nl, with support for filtering by date, cinema, rating, and preferred showtimes. | |
| crisp-mcp-server danielsuguimoto/crisp-mcp-server Enables MCP-compatible AI agents to query Crisp websites, operators, and conversations, post private notes, and manage conversation segments via the Crisp REST API on Cloudflare Workers. | |
| myanimelist-mcp-server danielsuguimoto/myanimelist-mcp-server Enables MCP-compatible clients to search and retrieve anime, manga, and forum data from the MyAnimeList API v2, including details, rankings, seasonal anime, and user lists via natural language tool calls. | |
| pandoc-mcp-server danielsuguimoto/pandoc-mcp-server Enables document conversion between formats using pandoc through MCP tools, supporting text and binary input/output, format listing, and version checks. | |
| pluggy-mcp danielsuguimoto/pluggy-mcp Enables managing Pluggy financial data products like accounts, transactions, investments, and loans through 25 MCP tools. | |
| Readonly Filesystem MCP Server danielsuguimoto/readonly-filesystem-mcp Node.js server implementing Model Context Protocol for secure read-only filesystem operations, allowing Claude to read files, list directories, search files, and get file metadata within specified directories. | |
| garmin-mcp danielsuri/garmin-mcp A local, single-user, read-only MCP server that gives Claude Code access to your Garmin health and training data, exposing tools for health snapshots, training status, run details, body metrics, and training analysis. | |
| garmin-unofficial-mcp danielsuri/garmin-unofficial-mcp A local, read-only MCP server that gives Claude access to your Garmin health and training data, exposing tools for health snapshots, training status, run details, body metrics, and training analysis. | |
| Expert Brain danielterra/expert-brain MCP server for a personal knowledge graph running on Cloudflare, enabling note-taking, task management, and cross-domain recall via Claude. | |
| albertheijn-mcp danieltyukov/albertheijn-mcp Enables AI assistants to shop the Dutch supermarket Albert Heijn: searching products with prices, nutrition and allergens, checking bonus deals, finding or importing recipes, and turning meal prep plans into baskets priced with the current | |
| IEEE Xplore MCP Server danieltyukov/ieee-mcp Allows users to search and retrieve academic papers, metadata, and citation counts from the IEEE Xplore digital library. It supports full-text search, author-specific queries, and publication tracking through the IEEE Xplore API. | |
| tudelft-mcp danieltyukov/tudelft-mcp Enables TU Delft students to access their Brightspace courses, OSIRIS records, MyTimetable schedule, and the Study Guide through any MCP client. It handles sign-in and requires confirmation before performing write actions. | |
| @showtime/mcp danielv14/showtime Enables browsing movie and TV show data from TMDB and OMDB through 24 MCP tools. | |
| health-mcp danielv27/health-mcp Provides a unified MCP interface to a personal health database, enabling AI agents to sync lifting workouts from Hevy, log food intake against a catalog, and run read-only SQL queries to cross-reference training and nutrition data. |
42,051–42,100 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.