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 |
|---|---|
| byob christophklein83/byob Lets AI coding tools drive the real Chrome browser you already have open, so they can read and act on logged-in pages with real clicks, typing, navigation, screenshots, and network or storage inspection. Everything runs locally over stdio w | |
| Stock Trade MCP Server christophl06646/stock-trade-finance-api Enables MCP-compatible clients to retrieve and work with Tiingo financial data, including stock prices, news, forex quotes, fundamentals, dividends, and splits through configurable tools. | |
| image-generator-mcp christophlabestin/image-generator-mcp Enables Claude to generate and edit images using OpenAI's GPT Image models, with automatic model selection and local file saving. | |
| youtube-mcp christophlanganke/youtube-mcp Enables AI assistants to fetch YouTube video transcripts and metadata without sign-in, and access signed-in users' own YouTube account data such as subscriptions, playlists, uploads, and caption tracks via OAuth 2.0. | |
| jmcomic-ai MCP Server christophlopez9228/jmcomic-ai Enables AI agents to search and browse albums, inspect comments and rankings, download albums or chapters, manage favorites, perform post-processing, and update configuration through standardized tools and resources. | |
| vscode-mcp christophmikhailov/vscode-mcp Enables MCP clients and AI coding agents to access a running editor's language-server data for real-time diagnostics, definitions, hover/signature/type information, references, and workspace-wide symbol renames without waiting for slow tsc/ | |
| HubSpot MCP Server christos6996/mcp-hubspot Enables AI assistants to access and manage CRM data by creating contacts and companies, retrieving activities and conversations, and performing semantic search over previously retrieved information with built-in vector storage and caching. | |
| SerpApi MCP Server christos73106/serpapi-mcp Enables running searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and other engines with automatic detection and formatting of answer boxes, organic results, news, images, and shopping data, plus weather and stock market looku | |
| DSH Crew christos82330/dsh-crew Enables Claude Code, Codex, Antigravity, and Grok to dispatch work to DeepSeek Harness agents that run as native subagents with live progress, tier policy and escalation, jobs-board tracking, and a multimodal bridge for vision and image gen | |
| ibkr-mcp christospappas/ibkr-mcp A read-only MCP server that connects to Interactive Brokers Gateway or TWS to expose account, contract, execution, and historical-data queries over stdio. | |
| codebadger christossilva46/codebadger Enables AI agents and LLMs to build, query, and analyze code property graphs from repositories, paths, or snippets for program and vulnerability analysis. Supports CPGQL queries, data-flow and taint tracing, program slicing, and vulnerabili | |
| LeetCode MCP Server christoswatanabe9424/leetcode-mcp-server Enables automated access to programming problems, solutions, contests, and user data across global and China sites, with optional authentication for user-specific features such as notes, lists, progress, and submissions. | |
| Instagram MCP Server christou5633/ig-mcp Enables AI applications to interact programmatically with Instagram Business accounts through the Graph API, including retrieving profile details, media posts, and engagement insights, as well as publishing images and videos. It also suppor | |
| DALL-E 3 MCP Server chrisurf/imagegen-mcp-d3 A Model Context Protocol server that provides OpenAI's DALL-E 3 image generation capabilities, allowing LLMs to generate high-quality images through a standardized interface. | |
| jira-mcp-server chrisurf/jira-mcp-server A read-only MCP server that provides AI agents structured access to Jira Cloud, enabling project listing, sprint overview, issue retrieval, and JQL search. | |
| Lotus MCP chrisvin-jabamani/lotus-mcp Enables creation of reusable browser automation skills through demonstration by recording user actions in a browser while narrating, then converting those workflows into executable skills that can be invoked through natural language. | |
| Terminal Reader MCP chrisvin-jabamani/terminal-reader-mcp Enables Claude Desktop to read terminal command output by capturing commands prefixed with 'cap' to a log file. Eliminates the need to copy-paste terminal errors and output when asking Claude for help. | |
| qaLabMcp chrisvlj/qalabmcp A local MCP server providing 7 QA testing tools for client validation, test case generation, percentile calculation, HTTP error classification, SLA evaluation, API response validation, and customer lookup, intended for use with OpenCode or | |
| medlineplus-mcp chrisvo/medlineplus-mcp Provides tools to look up patient-friendly health education links from MedlinePlus Connect using clinical codes or medication names, enabling AI agents to retrieve trustworthy reference material without accessing private health records. | |
| local-mcp-toolbox chriswayneh/local-mcp-toolbox A secure, local-first MCP server for read-only inspection and troubleshooting of development environments, exposing narrow, typed, auditable capabilities for repository inspection, log summarization, Docker review, and security scanning wit | |
| TickTick MCP V2 chriswinsatlife/ticktick_mcp_v2 Enhanced TickTick task management server that provides rich functionality including task assignment, section management, comments, and batch operations with significantly improved performance through checkpoint sync. | |
| Screen Agent chriswu727/screen-agent Enables AI assistants to capture screenshots and control desktop input (mouse, keyboard) to see and interact with your screen. Features user-first safety controls including automatic pause on user activity and app allowlists to restrict int | |
| ServiceNow MCP Server chrisww2/now-mcp A Model Completion Protocol (MCP) server implementation for ServiceNow, allowing Claude to interact with ServiceNow instances. | |
| SAP-Commerce-MCP chriszhangrui/sap-commerce-mcp Enables AI assistants to directly control, automate, orchestrate, and self-heal Hybris/CCv2 environments and headless Spartacus storefronts through 27 JSON-RPC tools. Covers greenfield site provisioning, CMS scaffolding, B2B organization go | |
| Pencil2D Model Context Protocol (MCP) Server chriz-3656/pencil2d-mcp Enables AI agents to programmatically create, inspect, edit, validate, and headlessly render traditional 2D hand-drawn animation projects, including frames, layers, audio, camera keyframes, spritesheets, and video or GIF exports. | |
| Nova MFI – Mifos System Doctor MCP Server chrl3y/mifos-mcp-server Provides 50+ tools for audit, repair, notifications, GL posting, reporting, and complete Fineract administration — all accessible from any MCP-compatible AI client. | |
| McGill myCourses MCP Server chrldb/mcgill-mycourses-mcp Enables Claude Desktop to access your McGill University myCourses account, letting you ask about your courses and upcoming deadlines in plain language. | |
| pty-mcp chrlstopher-c/pty-mcp Enables end-to-end testing of CLI applications, REPLs, and TUIs by driving interactive pseudo-terminal sessions and reading clean rendered output through any MCP client. | |
| alipay-mcp-server chromatic0618/alipay-mcp-server An MCP server that exposes Alipay AI Pay capabilities to AI agents, enabling skill discovery, payment integration guides, and merchant onboarding workflows via Alipay's payment APIs. | |
| alio-mcp chromehearts79/alio-mcp Enables AI tools to search and read the internal regulations of 355 Korean public institutions by title or article text, compare them against the latest innovation guideline, and flag newer revisions. It also saves review results as Hangul | |
| Grey Hack MCP Server chromewillow/greyhack-mcp-server A Model Context Protocol server that enhances Grey Hack game development by providing GitHub code search, GreyScript validation, script generation, and Greybel-JS transpilation capabilities when used with Cursor IDE. | |
| MCP Forge chromewillow/mcp-forge A tool that generates MCP servers for Smithery with Cursor IDE integration, allowing users to quickly create servers from templates such as Basic, Web Search, or Database interactions. | |
| Chromia LSP MCP chromiaproject/chromia-lsp-mcp Enables AI assistants to query and analyze Rell code via Language Server Protocol features like hover information, completions, diagnostics, and code actions. Automatically manages the Rell LSP server and provides resource-based access with | |
| chromia-mcp chromindscan/chromia-mcp Enables AI to interact with Chromia Wallet for sending $CHR transactions. | |
| FastMCP Google Docs Manager chronis10/gemini-docs-mcp Enables interaction with Google Docs through a FastMCP server, allowing users to list, read, and create documents. It leverages the Google Docs and Drive APIs to provide seamless document management via Gemini-CLI. | |
| FastMCP Gmail Reader Server chronis10/gemini-email-mcp Enables users to manage Gmail by fetching recent emails with pagination and creating new or reply drafts via the Gmail API. It provides a seamless interface for interacting with email content and drafting responses within Gemini-CLI. | |
| NyxID chronoaiproject/nyxid Agent Connectivity Gateway — turn any authenticated API into an MCP Server. Self-hosted reverse proxy with OAuth 2.0/OIDC credential injection, per-agent isolation,
NAT traversal for localhost services, and REST-to-MCP auto-wrap from OpenAP | |
| pravo-mcp chronovault/pravo-mcp Enables searching Russian federal laws, presidential decrees, and other official acts on publication.pravo.gov.ru, retrieving document cards, dictionaries, publication statistics, and links to official PDFs directly from Claude and other MC | |
| ErgStats chrsep/ergstats Enables AI agents to read a Concept2 Logbook account through MCP, covering training summaries, personal bests, workout lists, splits, intervals, stroke data and profile details. Access is read-only via an API key created after signing in wi | |
| Todoist MCP Server chrusic/todoist-mcp-server-extended Integrates Claude with Todoist for natural language task management, supporting project and section organization, task creation, updating, completion, and deletion using everyday language. | |
| easyJOB MCP Server chrustek-studio/easyjob-mcp-server An MCP server for the easyJOB REST API that manages OAuth tokens and provides tools for user lookup, job search, time tracking, and generic entity CRUD operations. | |
| MCP Server Starter (TypeScript) chry8822/workout-mcp A minimal, production-ready TypeScript template for building Model Context Protocol servers with auto-loading architecture for tools, resources, and prompts, supporting both stdio and HTTP transports. | |
| ThreadShelf MCP Server chrystianschutz/threadshelf Enables semantic search and retrieval of archived AI conversations from multiple providers via the MCP protocol, allowing thread continuation and integration with MCP-capable tools. | |
| Gemini Notebook by Chryzalide (agy-gemini-notebook-plugin) chryzalide/agy-gemini-notebook-plugin Connect Google Antigravity 2, VS Code, Cursor and Claude Code to Gemini Notebooks (formerly NotebookLM, both personal and Google Cloud Enterprise). Exposes 21 MCP tools for workspace notebook binding, grounded Q&A with citations, Fast and D | |
| apple-reminders-mcp chs2147/apple-reminders-mcp Enables Claude to read and search Apple Reminders tasks on macOS, including lists, incomplete/completed items, and keyword search, all locally without modifying data. | |
| obsidian-local-mcp chs2147/obsidian-local-mcp Enables Claude to create, read, update, and search notes in a local Obsidian vault, with automatic YAML frontmatter and folder management. | |
| omlx-mcp chsh/omlx-mcp Enables Claude or any MCP client to run prompts against a local oMLX instance through its OpenAI-compatible API, with asynchronous jobs, thinking control, result polling, cancellation, and a battery guard. | |
| i18n-file-replace-mcp cht-codeini/i18n-file-replace-mcp Enables MCP clients to replace hardcoded text in source files with i18n resource keys, with support for previewing changes, profiles, resource sets, and machine translation. | |
| glm-vision-mcp chu-nian/glm-vision-mcp Adds image understanding to any MCP-compatible AI client via free Zhipu vision models. Enables agents to analyze local images or URL images by answering natural language questions. | |
| Claude Code Orchestrator MCP chu459/claude-code-orchestrator-skill Enables Codex to orchestrate multi-agent coding by routing tasks to local Claude Code workers via CCSwitch, managing cost and model selection for planning, execution, and review. |
38,801–38,850 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.