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 |
|---|---|
| YouTube Knowledge MCP efikuta/youtube-knowledge-mcp Transforms YouTube into a queryable knowledge source with search, video details, transcript analysis, and AI-powered tools for summaries, learning paths, and knowledge graphs. Features quota-aware API access with caching and optional OpenAI | |
| mysql-mcp-plugin efilkucf/mysql-mcp-plugin Provides MySQL access with configurable per-connection capabilities, enabling secure read-only or writable database operations through Claude Code and other MCP clients. | |
| wakatime-mcp efirvida/wakatime-mcp Exposes WakaTime Summaries API tools over stdio, enabling daily and today's coding activity summaries via MCP. | |
| multiple-gmail efk44/multiple-gmail Connects several Gmail and Google Workspace accounts to MCP-capable AI apps so they can search, read, draft, send, reply, and label mail across one account or all of them at once. Runs locally on Windows with encrypted on-disk credentials, | |
| eForest Agent Skills eforest-finance/eforest-agent-skills This MCP server enables aelf blockchain interactions for token creation and NFT trading, including symbol market operations and comprehensive NFT workflows. | |
| octobrowser-mcp eforus-overseer/octobrowser-mcp Enables AI assistants to control Octo Browser antidetect profiles and drive real browsers over Playwright/CDP, covering profile lifecycle, navigation, interaction, tab management, and one-time profiles through 37 MCP tools. | |
| ArmaVita Meta Ads MCP efraintorres/armavita-meta-ads-mcp A local Model Context Protocol server that enables interaction with the Meta Marketing API to manage ad accounts, campaigns, and creatives. It provides tools for targeting research, insight reporting, and campaign management through local M | |
| armavita-originality-ai-mcp efraintorres/armavita-originality-ai-mcp Local-first MCP server for Originality.ai workflows, including AI detection, plagiarism checks, readability, SEO scans, and scan-result retrieval for content teams. | |
| armavita-quo-mcp efraintorres/armavita-quo-mcp Local-first MCP server for Quo/OpenPhone automation across messaging, calls, contacts, users, phone numbers, and webhooks via a clean stdio tool surface. | |
| festo-codesys-mcp efranceschetti/festo-codesys-mcp An MCP server that turns AI assistants into competent Festo/CODESYS PLC engineers by grounding them in curated, manufacturer-accurate knowledge and forcing every artifact through a machine-checked validation pipeline for CODESYS import. | |
| Weather-MCP efrat-fr/weather-mcp An MCP server that provides weather forecast tools for Israel (via Playwright web scraping) and the USA (via NWS API), enabling LLM agents to answer weather queries in natural language. | |
| NOMA efww/noma A read-only MCP gateway foundation for Korean public data, exposing bounded public-data capabilities to MCP clients with explicit provider isolation and honest status. | |
| fastapi-mcp-todo egafossojm/fastapi-mcp-todo FastAPI Todo API with an MCP server for managing todos, deployable to Render, AWS App Runner, or ECS. | |
| eGain MCP Server egain/egain-mcp-server Enables AI clients to interact with eGain Knowledge, supporting portal browsing, article reading, knowledge search, and AI-powered answers through MCP. | |
| MCP RAG Server egara/mcp-rag Connects to a PostgreSQL database (pgvector) to perform semantic retrieval via the search_documents tool, returning raw document snippets for LLM synthesis. | |
| Warp SQL Server MCP egarcia74/warp-sql-server-mcp Enables secure database operations on SQL Server instances through a three-tier safety system, supporting schema exploration, query execution, performance analysis, and data export with configurable security levels from read-only to full de | |
| lb-mcp-ui-proxy egargale/lb-mcp-ui-proxy An MCP proxy server that enriches Longbridge's financial API with UI-enhanced tools. It transforms JSON responses into interactive dashboards such as stock cards, candlestick charts, and portfolio views for any MCP host. | |
| Love Live! Illustration Prompt Generator egawata/odai-lovelive-mcp-server Generates creative illustration prompts featuring characters from the Love Live! franchise (μ's, Aqours, Nijigasaki, Liella!, Hasunosora, and Ikizurai) with randomized settings including characters, locations, times, actions, and items. | |
| MCP MySQL egcooper/mcp-database Enables AI assistants to connect to MySQL databases, execute read-only queries, list tables, and describe table schemas via MCP. | |
| Google Drive MCP egcooper/mcp-google MCP server for managing Google Drive documents from Cursor, enabling file operations like list, search, download, upload, update, create folders, and delete. | |
| SEO Research MCP egebese/dataseo-mcp Enables AI coding assistants to perform SEO research tasks including backlink analysis, keyword research, traffic estimation, and keyword difficulty analysis using Ahrefs data directly within IDEs. | |
| wharfy egebilge/wharfy MCP server for managing local dev ports on macOS. It enables AI agents to inspect listening ports, identify owning processes and parent chains, kill processes safely, wait for ports, and report LAN exposure. | |
| yek-mcp egecakir1/yek-mcp Enables natural language querying of the Turkish Manuscript Institution's catalog of 674,000+ manuscripts, allowing AI-assisted browsing and discovery. | |
| Kokkai Minutes MCP Agent egegungordu/kokkaikaigiroku-mcp Provides a structured interface to the Japanese National Diet Library's parliamentary proceedings API, allowing AI models to search and retrieve Diet meeting records and speeches. | |
| EuroLeague Analytics MCP egemeny13/euroleague-analytics MCP server for querying validated EuroLeague and EuroCup basketball analytics, including possession-based metrics, four factors, and lineup-level on/off data reconstructed from play-by-play events. | |
| zoho-sprints-mcp egenius01/zoho-sprints-mcp Enables MCP-compatible clients to manage Zoho Sprints projects, sprints, items, statuses, and comments via the Zoho Sprints REST API. | |
| Xiumi Connector egg-0831/xiumi-connector Enables AI agents and CLI users to search and inspect Xiumi public-account templates, copy editable templates into their own account, recolor and replace images/text, manage drafts, validate structures, publish previews, and snapshot/restor | |
| stargate-mcp eggfriedrice24/stargate-mcp Integrates Asana, GitHub, and Slack into MCP-compatible clients like Claude and Cursor, enabling task management, messaging, and project management through natural language. | |
| lms-mcp eggs-gd/lms-mcp Enables controlling a Lyrion Music Server through MCP tools for playback control, library search, and queue management. | |
| LexiPilot eggydx/lexipilot Connects Momo vocabulary-learning data to ChatGPT via MCP, enabling study progress checks, today's word review, fuzzy or forgotten word drills, and personalized quizzes. | |
| deepseek-search-mcp eggylan/deepseek-search-mcp Enables MCP clients to run web searches and fetch web page contents through DeepSeek's Search and Fetch APIs, returning structured JSON results with configurable tool names and multiple transport options. | |
| webmcp-polyfill eggyshrimp/webmcp-polyfill Enables browsers to act as MCP servers by relaying tools, resources, and prompts to AI agents via a WebSocket-to-stdio bridge. | |
| engineer-your-data eghuzefa/engineer-your-data-mcp Enables data engineers and BI professionals to perform data pipeline development, quality assurance, visualization, and API integration locally with AI assistance. | |
| linkedin-mcp egig/linkedin-mcp A local MCP server that lets Claude log in to LinkedIn and publish image posts to your personal profile feed, backed by LinkedIn's REST Images API and Posts API. | |
| agent-browser egistr/agent-headless-browser Enables AI agents to drive a persistent Chrome session that stays signed in to your own Google account, with tools for navigation, snapshots, clicking, typing, keystrokes, screenshots, JavaScript evaluation, and lifecycle or re-login contro | |
| linkedin-mcp egistr/linkedin-mcp Enables LinkedIn API integration for managing profiles, posts, feed, connections, and sending messages through MCP-compatible clients. | |
| Web Asset Studio egistr/web-asset-studio An MCP server that turns images generated in a logged-in ChatGPT web session into consistent, game-ready assets: it composes style-bible prompts, ingests browser downloads, removes backgrounds, pixelates to a true grid, outlines, slices gri | |
| MCP Spec Generator egitiaec/mcp-spec-generator Converts user story documents (from Notion, Google Docs, PDFs, etc.) into structured spec.md files following the SPEC_KIT_TEMPLATE format, ready for development teams. | |
| Jelly Memo Local MCP Server egm7126/jelly-memo-public-drop A local MCP server that enables AI tools to find and propose changes to Jelly Memo notes, running only on 127.0.0.1:8765 with optional pairing token for security. | |
| Starbase MCP egmermarketing/starbase-mcp Enables interaction with Starbase OS CRM through natural language, allowing users to manage contacts, tags, and forms. | |
| Build Runner MCP Server egn88/build-runner-mcp Provides structured build, compile, and test operations with parsed output to reduce token usage and improve readability. | |
| Refactor MCP egn88/refactor-mcp A Model Context Protocol (MCP) server for automated refactoring of Java and TypeScript/JavaScript codebases. | |
| mcp-tools egnaro9/mcp-tools Provides five safe tools (calc, search, model_drift, compare_runs, grade_answer) for arithmetic, keyword search, model drift monitoring, eval comparison, and answer grading against sources, all implemented directly from the MCP spec with ze | |
| Egnyte MCP Server egnyte/egnyte-mcp-server Enables AI agents to search for and retrieve documents from Egnyte by name, using Egnyte's public APIs and Python SDK, integrating enterprise content into AI workflows. | |
| SimpleCodeMCP egoetmann/simplecodemcp Indexes internal code libraries and exposes them via MCP for AI agents to provide context-aware assistance on company-internal libraries. | |
| kd2-rules-mcp egordoronchenko/kd-rules-mcp Enables MCP clients to parse, build, edit, and validate 1C Data Conversion 2 exchange rules (ПравилаОбмена 2.01, registration and correspondent rules) against configuration metadata, including matching hints, XML round-trip editing, reverse | |
| ichi egorfedorov/ichi A persistent character and memory layer for coding agents over MCP. It remembers user interactions, reinforces standards, and provides emotional continuity across sessions. | |
| spine-mcp egorfedorov/spine-mcp MCP server for creating Spine 2D animations from cut-up characters, generating runtime skeletons, packed atlases, and editable Spine projects. | |
| browser-guard-mcp egoring/browser-guard-mcp Enables AI agents to automate browsers through Playwright behind multi-layer safety guards, restricting navigation to allowed domains, defaulting to read-only actions, and recording all behavior in audit logs. | |
| judge-mcp egoring/judge-mcp Enables LLM-as-judge text quality evaluation via MCP, scoring original-revised pairs with multi-axis weighted rubrics, testing scorer models against labeled golden sets, and cross-validating agreement between two scorers. |
47,201–47,250 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.