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 |
|---|---|
| SeekBridge chang-hai/seekbridge Enables DeepSeek-powered agents to control real Chrome tabs with semantic snapshots, tab groups, and local safety controls. | |
| proton-mail-ro chang-ryan/proton-mcp Provides read-only access to Proton Mail through the local Proton Bridge, enabling search, retrieval, and listing of messages, threads, folders, and attachments without any mutating capabilities. | |
| web-mcp chang-tong/web-mcp MCP server for multi-engine web search and web page fetching, supporting parallel search, content extraction, and optional LLM-powered search summarization and deep search. | |
| cocos-mcp-community chang0022/cocos-mcp-community Enables AI clients to inspect and operate the Cocos Creator project currently open, including scenes, nodes, assets, animations, and editor workflows via MCP. | |
| 丝路E投财务引擎 MCP 适配层 chang0911/slgj-finance-mcp-server Enables clients to access 21 cloud-hosted financial tools via a token-authenticated forwarding layer that relays tool calls to the Silkj E-Investment skill gateway. Supports stdio, Streamable HTTP, and hosted deployment modes without embedd | |
| tobid-mcp chang666-hash/tobid-mcp Search and analyze 14M+ Taiwan government tenders (since 1999, updated daily): full-text search, award records, vendor win-rate and rivalry reports, agency spending patterns with next-tender predictions, and bid price analysis. Free, no API | |
| udesa-mcp changazo/udesa-mcp Enables an AI agent to access a Moodle Campus Virtual account with the user's own credentials, reading course content, files, forums, notices, calendar, grades and quiz attempts for every enrolled course. Teachers, managers and course creat | |
| HUTB Simulator MCP Server changchujun/mcp- Enables AI interaction with embodied humans, autonomous vehicles, and drones through the HUTB simulator. Supports voice/chat control, weather conditions, perspective switching, and recording features. | |
| Changeflow MCP Server changeflowhq/changeflow-mcp Monitor any website and get AI-enriched change intelligence via MCP. Manage sources, search changes, and automate web monitoring from Claude, Harvey, or any MCP client. | |
| NoteMesh changenode/notemesh Connect to your Obsidian vault via Remote MCP. Works with Obsidian Sync or git. | |
| Changerawr MCP Server changerawr/mcp-server A Model Context Protocol server that enables AI assistants like Claude to manage changelogs, projects, and content through natural language interactions with Changerawr instances. | |
| projectpermit-mcp changhuliu/projectpermit-mcp Enables municipal permit preflight checks for construction and renovation projects, returning evidence-linked, rule-version-aware results without using an LLM. | |
| Maicraft changingself/maicraft-mcp-server Enables AI agents to play and interact with Minecraft servers through mineflayer, providing automated actions like mining, movement, crafting, and real-time game event monitoring. | |
| MCP CU Chat Server changjian-wang/mcp-cu-chat-server Renders Azure Content Understanding field schema as interactive table cards in VS Code Chat, enabling editing and persistence of field descriptions. | |
| voyager-mcp changjonathanc/voyager-mcp A Voyager-inspired MCP server that enables coding agents to build and immediately use CLI tools without restarting sessions. | |
| mcp-kr-g2b changoolee/mcp-kr-g2b Enables AI assistants to query and analyze Korean public procurement data from the Korea Public Procurement Service (G2B/Nuri) via 14 services and 156 operations, including bid announcements, contracts, prices, and statistics. | |
| kr-legislation-mcp changoolee/mcp-kr-legislation Integrates 132 tools from the Korean Ministry of Legislation OPEN API to provide comprehensive access to Korean legal documents, including statutes, precedents, treaties, administrative rules, and local ordinances. | |
| MCP OpenDART changoolee/mcp-opendart Enables AI assistants to access South Korea's financial disclosure system (OpenDART), allowing users to retrieve corporate financial reports, disclosure documents, shareholder information, and automatically extract and search financial stat | |
| bb-mcp changshenhan/bb-mcp Enables AI assistants to interact headlessly with the CUHK-SZ Blackboard instance, including downloading courseware, inspecting and submitting assignments, and reading announcements via automatic credential-based login. | |
| fbbp-mcp-rag-server changyufei222/fbbp-mcp-rag-server An MCP-compatible retrieval server that exposes your private FBBP knowledge base to agents and AI IDEs. | |
| Remote MCP Server (Authless) chaniji/remote-mcp-server-authless Enables deployment of MCP servers without authentication on Cloudflare Workers, allowing tools to be accessed remotely from clients like Claude Desktop or Cloudflare AI Playground via Server-Sent Events. | |
| Garmin MCP Server chanjiraphat/garmin_mcp_webapp Enables LLMs and MCP clients to securely access your Garmin Connect health and running data, including daily wellness metrics, activity details, training status, and race predictions, for personalized coaching and analysis. | |
| cadastral-mcp chanjong-ui/cadastral-mcp An MCP server for querying land use plans and exporting cadastral maps as DXF files using VWorld Open API from the Korean Ministry of Land, Infrastructure and Transport. | |
| ArchLang chanmeng666/archlang Floor plans as code. Compile, describe, lint, validate, score, repair, fix, finish, suggest and complete ArchLang (.arch) plans: a deterministic open-source DSL and compiler that renders floor plans to SVG, DXF or PDF with geometric validat | |
| femtech-radar chanmeng666/femtech-radar An MCP server that fetches, dedupes, and scores women's-health & FemTech research and industry news, designed to feed GitHub Agentic Workflows and an auto-updating Astro + RSS site. | |
| Google Jobs MCP Server chanmeng666/server-google-jobs A Model Context Protocol server that provides Google Jobs search capabilities through SerpAPI integration, featuring multi-language support, flexible search parameters, and rich job details. | |
| mimo-vision channel-carl/mimo-vision Provides Claude Code with visual capabilities by analyzing local images via Xiaomi MiMo-V2.5, enabling image analysis, comparison, and UI inspection to guide frontend development. | |
| memocean-mcp channellabai/memocean Local-first AI Memory MCP server for AI agents to search and manage knowledge stored in Obsidian vaults, optimized for CJK languages with zero AI dependency. | |
| devflow-mcp channen2/dev-mcp An MCP server that automates developer workflows across GitHub, Jira, and Slack, enabling PR/code review automation, CI checks, and team notifications. | |
| MCP Knowledge Assistant channico/mcp-knowledge-assistant A read-only MCP server that enables AI clients to search a knowledge base and retrieve complete source documents via narrow search and fetch tools. | |
| StudyPilot MCP Server chanoir999/studypilot Exposes course documents as searchable resources and provides tools for reading, study task management, and source-grounded quiz prompts. Supports hybrid retrieval and integration with DeepSeek-based agents. | |
| Lazada MCP chanoktrue/lazada-mcp A read-only MCP server for Lazada Open Platform that provides access to orders, transactions, fee breakdowns, and per-SKU profit analysis. | |
| Zynx Supabase MCP Server chanonwankaew-ui/zynx-supabase-mcp Real TypeScript MCP server for connecting Zynx agents to Supabase through safe, allowlisted tools. | |
| MCP File Upload Sample chanrute/mcp-file-upload-sample Enables uploading files to MinIO (S3 compatible) via MCP tools. Supports Base64 file upload and optional curl command generation. | |
| Light DevOps MCP Server chansanya/forgedeck Enables AI agents to query build/deploy status and request operations on a self-hosted Docker/Compose deployment platform, with Observer and Operator skills and approval-based write actions. | |
| OneSignal MCP Server chansearrington/onesignal-mcp Enables AI assistants to manage OneSignal push notifications, email, SMS, and user management through natural language. Supports multi-channel messaging, segmentation, templates, analytics, and iOS Live Activities with 50+ tools for complet | |
| ImageForge MCP chanshawoh/imageforge-mcp Enables image generation and editing through OpenAI's gpt-image-2 model, supporting text-to-image, reference-guided generation, and editing with local files or URLs. | |
| yudao-pilot-mcp chanshawoh/yudao-pilot-mcp Workspace-aware MCP server for the yudao/ruoyi-vue-pro ecosystem that helps AI coding tools identify backend, frontend, and database configurations so generated code lands in the right project structure. | |
| Bizplay MCP Server chansokheang/mcp_server_portal Enables AI agents to use corporate card and expense functions, including balance checks, transaction listing, receipt compliance, expense reporting, and approval workflows, by calling existing REST APIs through a governed gateway with ident | |
| WorkOS AuthKit MCP Server chantasticstream/workos-authkit-mcp An example MCP server that integrates WorkOS AuthKit to enable secure remote client authentication and organization-centric user management. It allows developers to control access to specific tools based on user permissions and roles within | |
| MiMo Multimodal Understanding MCP Server chanthmiao/mimo-multimodal-understanding-mcp Integrates Xiaomi MiMo's multimodal API to enable understanding of images, audio, and video through natural language prompts. | |
| Knowledge MCP chanthr/internal-mcp Exposes your Google Drive, Slack, GitHub, and Railway to MCP clients with semantic search, per-user permissions, and optional OAuth, allowing natural-language access to your private data and infrastructure. | |
| Safe DB Gateway chantichalla/database-mcp Enables AI agents to query PostgreSQL databases securely with read-only defaults, PII masking, rate limiting, and human-approved, expiring mutation tokens. | |
| mcp-town-explorer chanys/mcp-town-explorer A demo MCP server for exploring Massachusetts town data (housing, schools, crime, distance to Boston) via tools and resources, designed to teach MCP architecture with dual-host setup. | |
| claude-consult-mcp chao-shiun/claude-consult-mcp Enables OpenAI Codex to consult Claude Code for co-analysis, adversarial second opinions, and read-only file review over the Model Context Protocol, with Claude remaining advisory and unable to modify files. | |
| Slack Gitlab Digest Model Context Protocol MCP Server chaodonghu/slack-gitlab-test-model-context-protocol-server Summarizes Slack activity and GitLab merge requests with OpenAI to help generate daily standups, weekly reports, or quarterly check-ins. | |
| gemini-cli-bridge chaodongzhang/gemini_cli_bridge Exposes the local Gemini CLI as an MCP stdio server, providing tools for prompting, web search, file operations, and MCP management, enabling AI clients like Codex CLI and Claude Code to interact with Gemini. | |
| MCSManager MCP Server chaofanx/mcsmanager-mcp Enables management of Minecraft servers through the MCSManager API. Supports executing server commands, checking player status, retrieving server information, and controlling game settings like weather. | |
| netdiag-mcp chaojiwudipaozi/netdiag-mcp Enables AI agents to drive switches, servers, and consoles over SSH or serial Console through 28 MCP tools, auto-detecting vendors, paging through long output, and cleaning raw byte streams into readable text. Provides structured diagnostic | |
| Agent Bridge chaojixiaoyezi/agent-bridge MCP server that bridges multiple AI agents for unified local chat, supporting private messages, chat rooms, role queues, and broadcast with fixed identities and rate limiting. |
37,901–37,950 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.