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 |
|---|---|
| Monti APM MCP Server coding-pioneers/monti-apm-mcp Integrates Monti APM with the Model Context Protocol to provide AI assistants with access to Meteor application performance monitoring data. It enables users to monitor system metrics, analyze method execution traces, and track application | |
| Vibe MCP Server coding-professional/mcpserver_vibe Enterprise-grade MCP server for Vibe APIs, enabling AI agents to manage projects, repositories, buckets, and retrieve activity data. | |
| Korea Building Register MCP coding-realtor/building-register-mcp Provides 12 tools to query South Korean building register data, including title sheets, floor details, and official house prices via the data.go.kr API. It enables users to perform smart building lookups and region code searches using natur | |
| sap-sales-order-mcp coding-with-abbi/sap-sales-order-mcp MCP server for SAP S/4HANA Sales Order Management that enables natural language queries for sales orders, order details, and line items using SAP's public sandbox API. Built with offline testing, structured errors, and retry policies. | |
| butter-code-health codingbutter/code-health Enables AI assistants to analyze code health in TypeScript/JavaScript projects, providing tools to run analysis, start a dashboard, and get summaries. | |
| ElevenLabs Streaming MCP Server codingbutter/elevenlabs-streaming-mcp-server Enables streaming text-to-speech generation using ElevenLabs with real-time audio playback and voice listing. | |
| GitHub CLI MCP Server codingbutterbot/gh_cli_mcp An MCP server that wraps around the GitHub CLI tool, allowing AI assistants to interact with GitHub repositories through commands for pull requests, issues, and repository operations. | |
| DevRel MCP codingcatdev/devrel-mcp Enables users to submit, log, fetch, and analyze advocacy and community-program activities across Google GDE, Microsoft MVP, YouTube, Dev.to, Hashnode, GitHub, AWS, and other programs, with OAuth-secured and encrypted credential storage. | |
| dsh-plugin-xquant codingduan/dsh-plugin-xquant Integrates xquant's quantitative research MCP into DeepSeek Harness, enabling querying of factors, strategy logic, and historical data with research guidance for interpreting results. | |
| Context Bridge codinglone/mcp-context-bridge A unified context layer that connects your local data — repositories, documents, remote machines, and notes — to LLM interfaces through the Model Context Protocol (MCP). | |
| lowlevel-computer-use-mcp codingmachineedge/lowlevel-computer-use-mcp A low-level computer-use MCP server that exposes raw desktop control (mouse, keyboard, shell, windows, processes, screenshots, etc.) to MCP clients like Claude Code and Codex. | |
| english-tutor-mcp codingmasterlsw/interlanguage Enables English language practice by silently logging messages and providing reports on recurring grammar patterns without interrupting conversation. | |
| upilot codingriver/upilot Unity Editor automation bridge for AI agents and MCP clients, enabling inspection, control, and diagnostics of the Editor. | |
| DDEV MCP codingsasi/ddev-mcp Enables AI assistants to automate DDEV development environments, including project management, database operations, and executing commands for various CMS frameworks. | |
| DomainFinder MCP Server codingstark-dev/domainfinder-mcp Enables users to check domain name availability across 877 TLDs, generate intelligent suggestions, and retrieve WHOIS registration information. It supports bulk domain checks and cross-TLD searches through natural language interfaces. | |
| xmcp Application codingthailand/mcp-server-app A template MCP server created with create-xmcp-app that demonstrates structured organization of tools, prompts, and resources with automatic discovery from their respective directories. | |
| MCP JIRA Server codingthefuturewithai/mcp_jira A Model Context Protocol server that enables AI assistants to create and manage JIRA issues with rich markdown formatting and automatic conversion to Atlassian Document Format. | |
| MCP Mermaid Image Gen codingthefuturewithai/mcp_mermaid_image_gen An MCP server that generates diagrams from Mermaid code in multiple formats (PNG, PDF, SVG). | |
| Code Understanding MCP Server codingthefuturewithai/mcp-code-understanding An MCP server that analyzes local or remote GitHub repositories, providing intelligent code context and structure to AI coding assistants. | |
| Screenshot MCP Server codingthefuturewithai/screenshot_mcp_server Enables AI tools to capture and process screenshots of a user's screen, allowing AI assistants to see and analyze what the user is looking at through a simple MCP interface. | |
| VSC as MCP codingwithcalvin/vsc-mcpserver Enables AI assistants to leverage VS Code's language intelligence for code navigation, refactoring, and analysis via the MCP protocol. | |
| InnovationsHospitalitySearch MCP Server codingwithjoseph/innovationshospitalitysearch Enables authenticated publishing workflows for the Innovations Hospitality Search platform, allowing content management and opportunity publishing through natural language. | |
| YouTube MCP Server codingwithshahzaib/youtube-mcp-server Enables AI assistants to analyze YouTube channels, videos, transcripts, and content strategy through structured tool calls. | |
| TechMCP - PSG College of Technology MCP Server codit04/techmcp Enables AI assistants to access PSG College of Technology e-campus portal data including CA marks, attendance records, timetable schedules, and course information through natural language queries. | |
| codivupload-mcp codivion/codivupload-mcp Enables users to publish, schedule, and manage social media content across nine platforms including TikTok, Instagram, and X via the CodivUpload API. It also supports media management and the creation of YouTube live streams through natural | |
| react-analyzer-mcp codixor/react-analyzer-mcp A Docker-managed MCP server for analyzing React codebases and generating component documentation from mounted workspaces. It enables users to scan projects, analyze JSX/TSX strings directly, and generate Markdown docs while ensuring safe pa | |
| @cododel/yandex-wordstat-mcp cododel/yandex-wordstat-mcp MCP server for the Yandex Wordstat v2 API, enabling keyword search volume queries, regional distribution, and trends analysis via Wordstat tools. | |
| Facebook Ads Management Control Panel codprocess/facebook-ads-mcp A Node.js Express server that integrates with Facebook Marketing API to provide a platform for managing ad campaigns, analyzing performance, and receiving optimization recommendations. | |
| ai-governance-controls cody-aigov/ai-governance-mcp Provides AI governance controls as MCP tools for safety screening, risk classification, and red teaming of AI systems, returning structured governance reports. | |
| openfolio-ro-mcp cody1991/openfolio-ro-mcp Provides read-only access to OpenFolio data, enabling catalog, holdings, grid, and log queries without placing orders. | |
| DocsetMCP codybrom/docsetmcp Provides AI assistants with instant access to local Dash documentation docsets and cheatsheets, enabling offline documentation searches across 165+ programming languages, frameworks, and developer tools directly within conversations. | |
| ms-graph-mcp codybuilder-dev/ms-graph-mcp A modular Model Context Protocol server for Microsoft Graph and Microsoft 365, enabling users to manage Teams, mail, calendar, To Do, contacts, and Outlook settings through natural language. | |
| MCP File Server codyde/mcp-file-tool Enables AI models to perform file system operations (reading, creating, and listing files) on a local file system through a standardized Model Context Protocol interface. | |
| MCP Firecrawl Server codyde/mcp-firecrawl-tool A server that provides tools to scrape websites and extract structured data from them using Firecrawl's APIs, supporting both basic website scraping in multiple formats and custom schema-based data extraction. | |
| Sentry MCP Server codyde/mcp-sentry-ts A Model Context Protocol server that enables AI assistants to interact with Sentry for error tracking and monitoring, allowing retrieval and analysis of error data, project management, and performance monitoring through the Sentry API. | |
| Defuddle MCP Server codysandahl/defuddle-mcp Fetches webpages and returns clean, structured Markdown with metadata (title, author, publish date, description, domain, word count). | |
| broca-machina codyslater/broca-machina Gives any text-based AI a voice and ears inside a Discord voice channel by transcribing speech, relaying to an LLM/agent, and speaking replies back. | |
| AXT-MCP codyterry24-dev/axt-mcp A Model Context Protocol service registry and connector framework that enables seamless integration with multiple services and models through a standardized API interface. Provides an extensible architecture for custom service adapters, API | |
| Schelling Protocol codyz123/schelling-protocol Universal coordination hub for AI agents. Find collaborators, negotiate terms, form contracts, and build reputation through an MCP interface. Supports natural language search across agent networks. | |
| Deskbrid coe0718/deskbrid Linux desktop HAL for AI agents. One daemon, one socket, every desktop action. GNOME, KDE, Hyprland, X11. Ships in one command. | |
| mcp-slim coefficient-work/mcp-doctor Optimizes MCP tool menus from OpenAPI specs by grouping operations by tag and trimming schemas to reduce token usage, improving agent tool-selection accuracy. | |
| antigravity-browser-bridge coelhobugado/antigravity-browser-bridge Enables MCP-compatible agents to securely control the user's already authenticated Chrome browser via explicit tab authorization and DOM-based actions. | |
| Personal Notes Assistant coeusyk/personal-notes-assistant MCP server that indexes your Obsidian notes into a Milvus vector database and enables querying them via a local or OpenAI LLM, with real-time synchronization. | |
| qb-mcp-server coevin/qb-mcp-server Enables MCP clients to query and manage a Qbee-managed device fleet, offering read tools for device status, files, CVEs, and changes, plus confirmation-gated write operations for configuration, file management, membership, and IAM. | |
| AI Skills MCP Server coff33ninja/ai-skills-mcp Compiles skill definitions and serves them to AI agents via MCP, enabling tools for context packing, dependency resolution, and skill searching. | |
| MCP Vision Server coffe-d/mcp-vision-server Enables Claude Code to describe images and extract text using Kimi/Moonshot vision API. Supports local image files with customizable prompts. | |
| MCP GlitchTip coffebar/mcp-glitchtip Integrates GlitchTip error monitoring with AI assistants, enabling them to fetch, analyze, and debug issues from your GlitchTip instance. | |
| mcp-pageshot coffee-fuelled-code/mcp-pageshot Paste a URL to see exactly how it renders as a social card on Twitter, LinkedIn, Facebook, and Slack. Generate custom OG images from templates. | |
| mcp-shiplegal coffee-fuelled-code/mcp-shiplegal Answer a few questions. Get clean, jurisdiction-aware privacy policies and terms of service. | |
| HL7 v2.5.1 → FHIR R4 Mapping MCP Server coffeemilktea/hl7-v2-fhir-mcp-server Enables users to look up how specific v2 fields, datatypes, and table codes translate to R4, and to convert whole ORM, ADT, and ORU messages into transaction Bundles with explicit warnings for unmapped values. |
39,851–39,900 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.