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 |
|---|---|
| X (Twitter) MCP Server dishant27/twitter-mcp Enables interaction with X (formerly Twitter), allowing for posting tweets, searching content, managing accounts, and organizing lists. | |
| deliverable-mcp diski7/deliverable-mcp Enables MCP clients to render Markdown to HTML, estimate page counts, verify document delivery constraints, and atomically ship documents through a zero-dependency JSON-RPC stdio server. | |
| Aider MCP Server disler/aider-mcp-server Allows Claude Code to offload AI coding tasks to Aider, reducing costs and enabling more control over which models handle specific coding tasks. | |
| Just Prompt disler/just-prompt A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama. | |
| numenews dismosgit/numenews Enables reading news numerologically by extracting numbers, computing gematria, finding resonance patterns via hybrid search in Qdrant, and generating daily numerology forecasts. | |
| QuillBot Local MCP disneik/quillbot-local-mcp Enables MCP clients to drive the QuillBot website through Playwright for text detection and humanization, returning literal service output once interface selectors are configured and validated. | |
| Flint Note disnet/flint-note-mcp Provides an agent-first note-taking system designed from the ground up for AI collaboration. Organizes your notes as a local vault of ordinary markdown files with semantic note types. | |
| cdp-mcp-server disoardi/cdp-mcp-server MCP server for Cloudera Manager and CDP cluster administration, enabling monitoring, configuration, and troubleshooting of Hadoop ecosystem services through natural language. | |
| Ceo MCP Media disomanceo/ceo-mcp-media Provides a durable MCP media pipeline for image, video, audio, and storyboard generation, with FFmpeg composition, provider routing, and resumable long-running jobs. | |
| Personal MCP Remote Agent disomanceo/personal-mcp-agent Safe MCP gateway that lets ChatGPT securely control a Windows Desktop Agent, enabling project file reads, git status/diff, and npm build/test within a designated workspace. | |
| Linode OAuth MCP Server displague/linode-oauth-mcp-server Turns the Linode API v4 OpenAPI specification into callable tools so users can search, inspect, and run Linode cloud operations from an MCP client. Requests only the OAuth scopes each operation needs, surfacing the sign-in link in chat when | |
| Plane MCP Server disrex-group/plane-mcp-server A Model Context Protocol (MCP) server that enables LLMs to interact with Plane.so, allowing them to manage projects and issues through Plane's API. Using this server, LLMs like Claude can directly interact with your project management workf | |
| Payload CMS MCP Server disruption-hub/payloadcmsmcp Enables management of Payload CMS projects through natural language commands, allowing developers to create, configure, and deploy content models with conversational AI. | |
| Polyprompt dissa12/polyprompt An MCP server that translates your coding prompts from your native language into a target language, enabling you to learn a new language through immersion and spaced repetition while building software. | |
| Roblox Executor MCP dissering/roblox-executor-mcp MCP server that allows AI agents to execute code, inspect scripts, spy on remotes, and interact with a running Roblox game client. | |
| a2a-x402-mcp-services disseveru/a2a-x402-mcp-services Enables agents to access production-grade paid MCP tools with real on-chain x402 v2 settlement, including EVM wallet risk scoring, payload normalization, and facilitator discovery, all discoverable via Bazaar-compatible metadata. | |
| Agent Commerce Suite disseveru/x402-mcp Production-grade suite of monetized tools for autonomous AI agent-to-agent commerce, enabling payments and task execution via x402 protocol and MCP. | |
| JLCEDA Codex MCP Bridge dissipative-atlas/jlceda-codex-mcp Bridges JLCPCB/Lichuang EDA Pro with MCP clients to export and analyze schematic/PCB DRC, netlists, and BOMs, enabling automated diagnostics and data queries. | |
| PWS MCP Server distortik/pws-mcp-server Enables AI assistants to interact with a Pro Wrestling Sim save, allowing natural language queries about roster, contracts, shows, and more, with read-only analysis and validated booking actions. | |
| Xava Labs MCP Template disturbing/mcp-live-code A template repository for bootstrapping Model Context Protocol (MCP) servers with WebSocket and SSE support, enabling real-time bidirectional communication and server-to-client streaming in Cloudflare Workers. | |
| Prover MCP Server disys-lab/skeptical-mcp-for-zksnarks Enables authenticated natural-language interaction with the CoSMeTIC zero-knowledge proof service by exposing tools to request proofs, check status, download proofs, and verify results, while managing job and session state. | |
| gimp-mcp diterex/gimp-mcp Enables scripted image editing with GIMP 3, including cropping, resizing, aspect-ratio fitting, dimension-spec validation, batch processing, and live control of a running GIMP instance. | |
| orcaslicer-mcp diterex/orcaslicer-mcp Enables AI assistants to work with OrcaSlicer code and perform slicing operations, such as reading files, checking Git status, and slicing 3D models to get print time and filament usage. | |
| youtube-research-mcp diterex/youtube-research-mcp Enables researching YouTube channels and videos by listing uploads, reading transcripts, extracting frames, and searching, without needing a YouTube API key. | |
| bookmark-atlas ditfetzt/bookmark-atlas Provides read-only retrieval and ranking of saved GitHub stars and X bookmarks from a local SQLite knowledge base, enabling agents to search, fetch details, find related entries, and surface best matches for a task. | |
| Context Memory MCP Server dithilli/context-memory-mcp Tracks mistakes and solutions from past Claude sessions to avoid repeating failed approaches. | |
| FontLab MCP Server dithilli/fontlab-mcp-server Enables AI assistants to interact with FontLab for font design and manipulation, including querying font metadata, creating/modifying glyphs, applying transformations, and exporting fonts. | |
| 聚水潭个人连接器 ditingchenming-sys/jst-personal-connector Enables local MCP clients and business systems to log in with a user's own Jushuitan account, explore pages, and run general read-only queries while keeping login state local and independent per client. | |
| MCP微信公众号爬虫 ditingdapeng/mcpwechatofficialaccounts 基于MCP架构的微信公众号文章爬虫系统，支持AI智能体通过Selenium自动抓取微信公众号文章内容和图片，实现文章内容的智能分析。 | |
| rekall ditrixnew/rekall Enables Codex agents in VS Code to compact accumulated conversation context at checkpoints while preserving a verified written handoff, and to automatically continue the authorized task once after compaction. | |
| outlook-mcp ditto-404/outlook-mcp MCP server that connects to Windows Classic Outlook to automate email organization, search, and reply draft creation without sending emails. | |
| weblab dittofleet/weblab Enables AI agents to drive real Chromium, WebKit, or Firefox browsers — opening named sessions, running ordered steps like clicks, typing, and assertions, and reading back text, console/network logs, and screenshots — so web apps can be tes | |
| jenkins-mcp dittops/jenkins-job-mcp MCP server that triggers Jenkins automation jobs and returns their results, with an action registry, parameter validation, and credential redaction. | |
| Oreo Pudding div0ky/oreo-pudding Enables LLM clients to interact with Apple Calendar (iCloud) via CalDAV, supporting listing calendars, retrieving, creating, updating, and moving events. | |
| deepseek-vision-mcp div7ne/deepseek-vision-mcp Adds image understanding to text-only coding agents via two tools: describe_image for detailed descriptions and describe_ui for structured UI reports. | |
| React Native Expo MCP divagnz/mcp-react-native-expo An MCP server for React Native development with Expo, offering automated code remediation, refactoring, testing, and analysis tools to accelerate development and enforce best practices. | |
| google-scholar-labs-ajg-mcp divenire990/google-scholar-labs-ajg-mcp MCP server for AI agents to search Google Scholar Labs and filter results by AJG 2024 journal ratings, using local browser sessions and safe CAPTCHA handoff. | |
| Home Assistant MCP Server diverdown1964/homeassistant-mcp Enables control and monitoring of Home Assistant smart home devices through MCP, allowing users to list entities, check device states, and call services to control lights, switches, sensors, and other connected devices. | |
| Mnemozine diverofdark/mnemozine Mnemozine is a self-hosted unified conversational memory layer that ingests conversations from AI tools, distills them into a temporal knowledge graph, and serves that memory to agents via a single MCP server. | |
| ClickUp MCP Server diversioteam/clickup-mcp Enables AI assistants to interact with ClickUp's task management API for core project workflows, supporting operations like task creation, updates, search, assignment, and team analytics through natural language. | |
| gemini-mcp diversioteam/gemini-cli-mcp A Model Context Protocol server that wraps the Gemini CLI, enabling AI assistants to send prompts, research topics, analyze code, and summarize content using Gemini. | |
| 1C MCP Proxy diversus23/itmcp Proxies MCP protocol to JSON-RPC for 1C:Enterprise IT management system, enabling AI agents to manage tasks, projects, knowledge base, and files. | |
| terminal-bridge-mcp dividduang/terminal-bridge-mcp An MCP server that bridges AI assistants to real terminal sessions, enabling creation, management, and interaction with persistent PTY processes for running commands, monitoring output, and debugging. | |
| burrowser dividehex/burrowser Enables AI agents to use isolated, persistent Chromium profiles with real WebAuthn passkeys, and provides Playwright MCP tools for browser automation with exclusive per-agent access. | |
| SlangLane Dictionary dividendflow-dev/slanglane-mcp Enables users to look up, search, decode, compare, and explore contemporary internet English, texting shorthand, regional expressions, and clearly labeled non-graphic adult vocabulary through a remote, zero-auth Streamable HTTP endpoint. | |
| figcraft divikwu/figcraft Enables AI-powered design operations in Figma, including UI creation, design review, token sync, linting, auditing, and auto-fix through natural language commands. | |
| opus-advisor-mcp divinci-ai/opus-advisor-mcp An MCP server that enables Claude Code to consult Opus as a strategic advisor during tasks, allowing users to escalate complex decisions to Opus using their existing Claude Code subscription without needing API keys. | |
| bible-cli divine-creative-ministries/bible-cli Offline command-line toolkit for biblical study, allowing AI agents to access original-language texts, perform morphological searches, cross-references, and more, with all results traceable to queries. | |
| Divine API Indian Astrology MCP divineapi/mcp-indian-astrology The MCP server for Divine API's Indian Astrology services, allowing AI assistants to query Vedic astrology data such as Panchang, Kundli, and matchmaking through natural language. | |
| Android MCP Server divinedev-dotcom/android_mcp Enables AI agents to fully control Android devices through over 30 tools for app management, UI automation, and vision-based analysis via ADB. It supports multi-device management, action recording, and smart execution strategies ranging fro |
44,901–44,950 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.