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 |
|---|---|
| MCP2Lambda danilop/mcp2lambda Enables AI models to interact with AWS Lambda functions via the MCP protocol, allowing access to private resources, real-time data, and custom computation in a secure environment. | |
| MCProxy danimalquackers/mcproxy An MCP server proxy that reduces context window bloat by stripping metadata and fetching schemas on-demand, while managing backend MCP servers across multiple transports. It also provides a web dashboard for monitoring and restarting backen | |
| ResearchMCP danimanas/researchmcp Enables AI-powered academic research by searching and retrieving research papers from OpenAlex database. Supports searching by keywords/topics and fetching full abstracts for detailed paper analysis. | |
| OHIP MCP Server danimh03/ohip-mcp A universal gateway for the Oracle Hospitality Interface Platform (OHIP) that enables AI assistants to execute authenticated API requests for hotel management tasks like reservations and inventory. It features automated OAuth 2.0 token mana | |
| sprinter danimoya/sprinter A self-hosted backlog tracker with priority scoring and an MCP server, enabling AI agents to autonomously pull, work on, and update tasks via JSON-RPC tools. | |
| xwiki-surgical-mcp danimoya/xwiki-surgical-mcp Enables LLMs to make section-level edits to a self-hosted XWiki instance by patching one section's body while reconstructing the full page for the single write call XWiki exposes, with version-conflict protection against concurrent changes. | |
| playwright-mcp-azure daninden/playwright-mcp-azure Enables MCP clients to remotely control a headless Chromium browser via Playwright, including navigation, clicking, typing, form filling, screenshots, and network request monitoring, over Streamable HTTP and deployable to Azure Container Ap | |
| HoYoLAB Genshin Battle Chronicle MCP Server danisec/hoyolab-mcp Enables models to query a user's Genshin Impact Battle Chronicle through read-only MCP tools, covering account statistics, characters, artifacts, Spiral Abyss, Imaginarium Theater, and exploration progress. It uses per-user encrypted HoYoLA | |
| IMDb MCP Server danish-mar/imdb-mcp Enables searching, discovering, and playing movies from IMDb via a Model Context Protocol server with a playback layer and monitoring dashboard. | |
| juno-mcp danish-mar/juno-mcp Enables LLMs to interact with MGMU Juno ERP, providing tools to fetch student profile, attendance, fees, schedule, results, and search students. | |
| kiwi-tcms-mcp danish54/kiwi-tcms-mcp-server An MCP server that exposes Kiwi TCMS as a set of AI-callable tools, enabling assistants to create and manage test plans, test cases, test runs, and executions directly from a conversation. | |
| mcp-devvm danisherror/mcp-devvm Enables an AI agent to perform real dev VM work—such as checking git status, switching branches, tailing logs, and restarting services—through typed operations that are re-validated and sandboxed by a daemon and require human approval befor | |
| swagger-mcp danishjsheikh/swagger-mcp swagger-mcp is a tool designed to scrape Swagger UI by extracting the swagger.json file and dynamically generating well-defined mcp tools at runtime. These tools can be utilized by the MCP client for further tool selection. | |
| mcp-site-analyst danishm/mcp-site-analyst An MCP server that provides Google Analytics and Search Console data as tools for AI assistants, enabling natural language queries for web analytics, SEO performance, and site insights. | |
| mcp-luz danisluz/mcp-luz Serves as a personal MCP hub for development, detecting the current stack and monorepo root, managing Docker Compose actions, querying Context7 documentation, and interacting with Nexus, while also forwarding tools from optional external MC | |
| PetPals KittyClaw MCP Server danissimode/beaverboardkanban-mcp Manages KittyClaw task board workflows for AI agents, providing a safe control plane without shell or git access. | |
| chatgpt-jules-mcp danissimode/catgpt_mcp_to_jules Secure MCP server allowing ChatGPT to manage Google Jules sessions through OpenAI Secure MCP Tunnel. | |
| Healthcare Clinic MCP Server daniyalafzal01/healthcare-mcp-server Exposes appointment scheduling and insurance claims data as MCP tools, allowing AI clients to query and update clinic records via a standard protocol. | |
| abacus daniyalmlk/abacus Provides option and portfolio analytics through validated numerical methods, exposing tools for pricing, Greeks, implied volatility, volatility surfaces, and American options via MCP. | |
| Supabase Storage MCP Server danizeap/supabase-mcp Enables creating storage buckets and uploading media files to Supabase Storage through natural language, with no delete or overwrite capabilities. | |
| MCP Gemini danjam/mcp-gemini An MCP server that lets AI assistants use Google's Gemini models. Generate text, analyze images, review code, and more — with support for multi-turn conversations and web-grounded answers. | |
| MCP Govee danjam/mcp-govee Enables AI assistants to control Govee smart devices, including lights, via natural language. Supports turning on/off, changing colors, adjusting brightness, and activating scenes through the Govee API or local network. | |
| MCP LaunchBox danjam/mcp-launchbox An MCP server that enables AI assistants to search and query your LaunchBox game library across all platforms including Steam, GOG, and emulators. It allows users to check ownership for bundles, view game metadata, find duplicates, and anal | |
| MCP Skeleton danjam/mcp-skeleton A starter template for building Model Context Protocol (MCP) servers with Node.js. It provides a foundational structure and an example tool to help developers quickly scaffold and deploy new MCP capabilities. | |
| mcp-synology danjam/mcp-synology Enables AI assistants to query a Synology NAS through MCP for system health, storage, network, packages, power, Cloud Sync, scheduled tasks, logs, notifications, and files, with read-only access by default and optional write permission for | |
| Vikunja MCP danjamesmills/vikunja-mcp Enables managing Vikunja tasks and projects using natural language in Codex. | |
| Todo Markdown MCP Server danjdewhurst/todo-md-mcp An MCP server that allows AI assistants to manage todo lists stored in a simple markdown file, supporting creation, reading, updating, and deletion of todo items with persistent IDs. | |
| quebragalho-bridge danjour/quebragalho-bridge Exposes the Quebragalho pre-paid model gateway to MCP clients, letting coding agents like Claude Code, Codex, Cursor and OpenCode spawn separate repo-aware sub-agents that run on 17 frontier models, with background job tracking, routing tie | |
| Moviesda MCP Server danjraizen/mcpserver An MCP server for searching and managing Tamil movies from moviesda16.com using a local SQLite database. It enables users to search for movie titles, manually add listings, and automatically update the database through web scraping. | |
| evidence-lint dankaro-projects/evidence-lint Enables AI agents to run evidence QC gates mid-workflow—checking claims, sources, prose, and vault hygiene deterministically before research ships. | |
| Garmin Connect MCP Server dankeydevdave/garmin-connect-mcp-server Connects Garmin Connect data to MCP-compatible clients, providing access to fitness activities, health metrics, and training plans. It supports advanced features like headless 2FA and automated MFA retrieval to enable seamless health data i | |
| mcp-compliance-validator dankeydevdave/mcp-compliance-validator A comprehensive security validation system for MCP server implementations, providing enterprise-grade authentication, authorization, and protocol security checks. | |
| lambda_cloud_MCP dankit/lambda_cloud_mcp Enables agents to manage Lambda Cloud GPU instances over SSH, including executing commands, running background jobs, transferring files, and terminating instances, while also exposing UI-configured capacity alerts and auto-provisioning sett | |
| api-football-mcp-server dankniight/api-football-mcp-server Enables natural language querying of football/soccer data via the API-Football service, providing access to leagues, teams, players, fixtures, standings, and statistics. | |
| MCP Server Template danksai/mcp-server-python-mqngetev A minimal template for deploying Model Context Protocol servers on Render with Streamable HTTP transport, bearer token authentication, and an example hello tool. | |
| Bedtime Book Studio danmaps/bedtime-book-studio Enables turning a photo or character description plus a story idea into an interactive, mobile-friendly landscape children's picture book with Lift-the-Flap pages, built as a self-contained HTML file and served locally over Wi-Fi. | |
| adsb-mcp danmarce/adsb-mcp Enables users to query live local ADS-B flight data from their own receiver, listing aircraft overhead or near a point and finding aircraft by callsign, ICAO hex code, or registration. | |
| forge-mcp danmarce/forge-mcp Exposes a local Forge or AUTOMATIC1111 SDXL backend as typed image-generation tools, enabling any MCP client to generate and edit images through a deterministic, stateless interface with server-enforced SFW content. | |
| search-mcp danmarce/search-mcp Enables broad web search for current, time-sensitive information, returning short title, URL, and snippet results rather than full pages. It supports region and result-count parameters through a keyless multi-engine backend. | |
| weather-mcp danmarce/weather-mcp Provides Open-Meteo weather tools that return both structured forecast data for the model and a weather card (image link or text) for the user, plus geocoding of place names to coordinates. Requires no API key and works over stdio or stream | |
| Everything MCP Server danmarshall909/everythingmcp Provides lightning-fast filesystem search on Windows via the Everything SDK, with fallback to HTTP API. | |
| VectorClaw danmartinez78/vectorclaw Enables AI assistants to control Anki Vector robots locally via natural language, providing tools for speech, motion, perception, and interaction without cloud dependency. | |
| apache-atlas-mcp danmeon/apache-atlas-mcp Connects LLM agents to Apache Atlas for searching, tracing lineage, and managing metadata. Read-only by default, with optional write mode for creating entities and classifications. | |
| hatchet-mcp danmeon/hatchet-mcp An MCP server for Hatchet, the durable orchestration engine, enabling LLMs to inspect workflow definitions, runs, logs, and more, with optional mutating tools for triggering, canceling, and managing workflows. | |
| chaoxing-mcp danmo661/xuexitong-cli Read-only MCP server for Chaoxing (学习通) that logs into a user's account and exposes their class schedule, enrolled courses, course materials downloads, homework status, exam schedules and scores, chapter task-point progress, notices, and pe | |
| Sports Hub MCP Server danmorris27/mcp-sports-hub Aggregates 42 sports API providers into a single service exposing 410 tools for scores, stats, odds, esports, college sports, chess, motorsport, boxing, and more across 70+ sports. Each provider works independently, so you only need API key | |
| Nextcloud MCP Server danmorris27/nextcloud-mcp-server Enables AI assistants to interact with a Nextcloud instance through its APIs, covering notes, calendars, contacts, files, decks, recipes, tables, shares, news, mail, collectives, talk, and shopping lists with full CRUD operations. Supports | |
| Twitter MCP Server danmorris27/twitter-mcp Allows clients to post tweets and search Twitter through a Model Context Protocol interface. | |
| Banxico SIE MCP Server danmr8/mcp-banxico-sie Enables querying Mexico's central bank macroeconomic indicators — policy rate, TIIE 28/91, Cetes 28, and UDIS values — plus UDI-to-peso conversion and inflation variation calculations over date ranges. Use-case-oriented tools batch series r | |
| ows-mcp-wallet danmwihoti/ows-mcp-wallet Enables AI agents to check balances and send transactions across multiple blockchains with automatic spending limit protection and policy enforcement. |
42,151–42,200 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.