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 |
|---|---|
| ClickUp MCP Server chisanan232/clickup-mcp-server Enables AI applications to interact with ClickUp's project management API through the MCP protocol, supporting resources like Teams, Spaces, Goals, and Key Results. | |
| Slack MCP Server chisanan232/slack-mcp-server A strong MCP server for Slack integration, providing standardized access to Slack's API features through both MCP tools and webhook processing. | |
| figma-mcp chisanucha-suwan/figma-mcp Read-only Figma MCP server that enables design-to-code workflows by talking to the Figma REST API with a personal access token, for use with Claude Code and GitHub Copilot. | |
| Serpentine3D MCP Server chisomobanzi/serpentine3d Enables AI to view the Serpentine3D viewport, create NURBS geometry, and execute commands, integrating AI directly into the modelling workflow. | |
| visor-mcp chisomobanzi/visor Enables Claude Code to see and control a Meta Quest headset via ADB, providing tools for screenshots, logs, performance monitoring, app management, and more. | |
| web3-matrix-onboard chisonkon/web3-social-onboarding Enables AI agents to automate Web3 social account onboarding for Twitter, Discord, and Gmail by scanning local fingerprint browsers, parsing account data, generating 2FA codes, and submitting or monitoring batch onboarding tasks. | |
| GNS3 MCP Server chistokhinsv/gns3-mcp Enables control of GNS3 network lab automation, including projects, nodes, consoles, and SSH, through Claude Desktop or any MCP-compatible client. | |
| swagger-connect-mcp chitanta628/swagger-mcp Enables AI coding agents to discover and use Swagger/OpenAPI operations, schemas, and endpoints from configured sources, with optional API request execution and environment-based authentication. | |
| Google MCP Server chitragohad/chitra-mcp-server A Python FastAPI server that exposes Google Docs and Gmail tools with terminal-based approval before each action. Allows appending to Google Docs and creating Gmail drafts. | |
| MCP Outlook Scheduler chitsingh/mcp-outlook Enables AI assistants to intelligently schedule meetings by checking Microsoft Outlook calendars, finding available time slots across multiple participants, and automatically booking meetings with Teams integration. Uses Microsoft Graph API | |
| ChittyMCP chittyos/chittymcp A consolidated Model Context Protocol server for the ChittyOS ecosystem, offering modular tools for evidence intake, legal, infrastructure, and synchronization domains with chain execution. | |
| DeskSense chituqaq/desksense-mcp A read-only Windows MCP server that gives AI assistants awareness of the current PC state, including open applications, focus, idle status, and system metrics. | |
| Slack Notifications MCP Server chiuchau-inc/mcp-slack-notifications Enables sending customizable Slack notifications from Claude, supporting rich formatting, task completion alerts, and priority levels for development workflows. | |
| minecraft-admin-mcp chius-me/minecraft-admin-mcp A lightweight, self-hosted MCP server that provides a small set of administration tools for a single Minecraft Java Edition server, including whitelist management, broadcasting, kicking, backups, and monitoring, with secure RCON-based opera | |
| GLM-4.6V-Flash MCP Server chiyan11/glm-4.6v-flash-mcp A Model Context Protocol server that wraps the free GLM-4.6V-Flash vision model, enabling text-only LLM clients like Codex, Cursor, and Claude Desktop to analyze images, videos, and files (PDF/TXT) through standard MCP tools. | |
| 250game MCP chiyukiruon/250game-mcp Enables AI agents to join 250game-server rooms as ordinary players over native WebSocket without modifying the game server, supporting room setup, card play and manipulation, scoring, and turn-based decisions while filtering hidden informat | |
| express-recon-mcp chiz0me/express-recon Enables scanning Express.js route surfaces for inventory and audit, classifying routes as public/authenticated. | |
| bmw-ediabas chiziminc/bmw-mcp Enables an AI assistant to read diagnostic data from BMW vehicle control units through EDIABAS, including checking connectivity, listing ECUs and jobs, describing jobs, reading faults, and running read-only jobs. | |
| Vercel AI SDK MCP Server chiziuwaga/vercel-ai-sdk-mcp-project Exposes Vercel AI SDK Core capabilities (generateObject, generateText, streamText, UI generation) to AI development environments like Cursor, designed to work in orchestration with other MCP servers for multi-step AI workflows. | |
| antirea.defense_mcp chldbwnstm/anti-rea Enables agents to locate core logic and surrounding clues, generate approved protection plans, apply obfuscation and virtualization through supported engines, and verify behavior and relative speed after protection. It helps defend binaries | |
| VisualizeBetter chldbwnstm/visualizebetter An MCP-native workspace where AI pushes discoveries into a live GPU-rendered graph, preserving project structure and findings across sessions. | |
| android-mcp-server chldu2000/android-mcp-server Enables Android device control via ADB and scrcpy, including device management, app management, file operations, shell commands, input simulation, screen mirroring, and UI element inspection. | |
| PostgreSQL MCP AI Explorer chlee10/postgresql_mcp A Model Context Protocol server that enables natural language data exploration and visualization for PostgreSQL databases. It allows users to convert questions into SQL queries and interact with data through a Streamlit web interface featur | |
| ExcaliDash MCP chlee1001/excalidash-mcp Enables MCP clients to list, select, create, summarize, and edit ExcaliDash (Excalidraw) drawings through the Drawing Agent API, supporting both stdio and Streamable HTTP transport. | |
| Home Assistant MCP Control chllhc-svg/home-assistant-mcp Enables control of external Home Assistant devices via an MCP control layer and frontend system page. | |
| apple-health-shortcuts-mcp chloe622-mail/apple-health-shortcuts-mcp Exposes Apple Health data as three read-only MCP tools (now, detail, trends) for AI to query health metrics, sleep, and trends via HTTP. | |
| Apple Health Shortcuts MCP chloe622-mail/apple-health-shortcuts-mcp1 This MCP server exposes read-only Apple Health data to AI assistants via three tools (health_now, health_detail, health_trends), deployable to Cloudflare with a one-click button and no coding required. | |
| apple-health-shortcuts-mcp chloe622-mail/apple-health-shortcuts-mcp2 Enables AI assistants to read Apple Health data through three tools: current stats, detailed metrics, and trends. Deployable to Cloudflare with a one-click phone setup, exposing only read-only access. | |
| Korea Ground-Truth MCP chloepark85/kr-groundtruth-mcp Enables AI agents to verify Korean ground-truth data through MCP and REST, including business registration, addresses, corporations, apartment trade prices, and statutes, metered with prepaid credits. | |
| mcp-server-isaaclab chloepilonv/mcp-server-isaaclab Enables Claude to control NVIDIA Isaac Lab for RL training, environment management, and policy evaluation on a remote GPU instance via SSH tunnel. | |
| semantic-runtime chloride233/semantic-runtime Enables MCP clients to serve and query semantic models, providing tools for entity descriptions, metric lookups, context resolution, and operation validation for AI agents. | |
| blendy-blender-mcp chlxyz/blendy Enables AI assistants to control and query Blender scenes through local MCP, allowing operations like retrieving scene information with objects and materials. | |
| Planka MCP Server chmald/planka-mcp Enables AI assistants to interact with Planka, a real-time Kanban board application, for managing projects, boards, lists, cards, and more. | |
| arc-cdp-mcp chmodami/arc-cdp-mcp Enables Claude Code to control the Arc browser over CDP, including navigation, clicking, form filling, screenshots, and reading console and network traffic. | |
| jayrah chmouel/jayrah Enables AI assistants to interact with Jira via CLI/TUI, supporting issue browsing, creation, comments, status changes, and custom fields. | |
| pg-semantic-mcp chncaesar/db-semantic-mcp A read-only PostgreSQL MCP server for AI coding agents that exposes database schema and sample data as tools, with LLM-powered semantic search enriched by a user-authored semantic layer. | |
| gm-data-bridge chngm/local-mcp-service Enables local programs to push text and images to AI assistants via HTTP and retrieve AI-generated responses, acting as a local data bridge between your code and MCP-capable AI tools. | |
| Web Search MCP chngrkvc/web-search-mcp Provides eight tools for web search, content extraction, screenshots, PDFs, JavaScript execution, crawling, and Wayback Machine snapshots and archiving. | |
| mcp-file-servers chniapxs/mcp-file-servers Enables file operations (PDF, Office, images, archives, media) through natural language, with tools for reading, writing, converting, and analyzing files locally. | |
| mcp-gitlab-workflow chntif/mcp-gitlab-workflow An MCP server for issue-driven GitLab development, automating requirement analysis, issue creation, branching, coding, merge requests, and issue updates. | |
| padlet-mcp-server cho-0820/padlet-mcp-server Enables Claude to read posts, create new posts, and add comments on Padlet boards through natural language. | |
| Charlotte cho232/charlotte Enables AI agents to browse and interact with web pages through compact, structured representations — landmarks, headings, forms, and typed interactive elements — rather than full accessibility-tree dumps, with three detail levels so agents | |
| IDA Pro MCP Server cho4010/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis tasks, including executing Python scripts, retrieving binary metadata, searching values, text, and byte sequences, and obtaining disassembly. | |
| mcp-server-atlassian-bitbucket cho5620/mcp-server-atlassian-bitbucket Enables AI assistants to interact with Bitbucket Cloud workspaces, repositories, pull requests, branches, commits, and code through MCP tools for reading, creating, updating, deleting, commenting, searching, and cloning. | |
| MCP GitHub Project Manager cho8432/mcp-github-project-manager Turns GitHub Projects v2 into an agentic project management layer where AI coding agents register, atomically claim and track tasks, heartbeat, review each other's work, and operate within token budgets, all backed by GitHub-native storage | |
| Multi-Service MCP Platform choas/try-mcp Provides a unified MCP interface to multiple utility services including transportation info, mindful sentences, weather forecasts, emoji oracle, timestamps, fortune cookies, and lucky numbers. | |
| Mixtape choasli165-ui/mixtape Enables Claude to search SoundCloud, curate and build playlists from a described mood or moment, and control playback by playing, skipping and liking songs. It also exposes the local desktop player's library and queue so requests like "make | |
| casper-network-mcp choaterboater/casper-network-mcp Enables an AI assistant to search, inspect and run vendor API operations for HPE Aruba Networking Central, Juniper Mist and HPE Aruba Networking ClearPass through four tools covering tool discovery, read-only execution, full invocation with | |
| Wicked API - Agent First API Services choaticpixels/wickedapi_mcp Real-time crypto, stock, and prediction-market data for agents — prices, indicators, funding rates, DeFi TVL, macro calendar, and an AI momentum score. Configure one Base wallet key and it just works. No signup, no dashboard, no subscriptio | |
| cpp-mcp chocek-rb/cpp-mcp Enables AI coding assistants to search for and retrieve authoritative C and C++ documentation from cppreference.com, returning sanitized, paginated Markdown content. |
38,501–38,550 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.