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 |
|---|---|
| hep-index bsmart-hep/hep-index Serves AI agents live, non-RAG access to registered HEP codebases through MCP tools for regex search, symbol lookup, and file reading across C++, Python, Fortran, and Mathematica sources. | |
| Chain of Draft Thinking bsmi021/mcp-chain-of-draft-server Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured appro | |
| Congress.gov API MCP Server bsmi021/mcp-congress_gov_server Enables querying U.S. legislative data from Congress.gov API using MCP resources for direct lookups and tools for searching and retrieving related data. | |
| MCP Conversation Server bsmi021/mcp-conversation-server A Model Context Protocol server implementation that provides a standardized interface for applications to interact with OpenRouter's language models through a unified conversation management system. | |
| MCP File Context Server bsmi021/mcp-file-context-server A Model Context Protocol server that enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities. | |
| File Operations MCP Server bsmi021/mcp-file-operations-server A Model Context Protocol server that enables enhanced file system operations including reading, writing, copying, moving files with streaming capabilities, directory management, file watching, and change tracking. | |
| Filesystem MCP Server bsmi021/mcp-filesystem-server A Model Context Protocol server that provides file system operations, analysis, and manipulation capabilities through a standardized tool interface. | |
| MCP Gemini Server bsmi021/mcp-gemini-server A dedicated server that wraps Google's Gemini AI models in a Model Context Protocol (MCP) interface, allowing other LLMs and MCP-compatible systems to access Gemini's capabilities like content generation, function calling, chat, and file ha | |
| Gemini TTS MCP Server bsmi021/mcp-gemini-tts Provides text-to-speech capabilities using Google's Gemini TTS API with support for multiple voices, automatic chunking of long text, multi-speaker dialogue, and audio playback via Windows Media Player. | |
| mcp-memory-bank bsmi021/mcp-memory-bank Enables persistent memory management using ChromaDB vector store, with Docker support for easy deployment. | |
| Mistral Codestral MCP Server bsmi021/mcp-mistral-codestral Provides code completion, bug fixing, and test generation for multiple programming languages, integrating with the Mistral Codestral API to enhance code development processes. | |
| Node Omnibus MCP Server bsmi021/mcp-node-omnibus-server A comprehensive Model Context Protocol server that provides advanced Node.js development tooling for automating project creation, component generation, package management, and documentation with AI-powered assistance. | |
| npm-docs-server bsmi021/mcp-npm_docs-server Fetches metadata and README documentation for NPM packages, with local caching via SQLite for improved performance. | |
| MCP Python Executor bsmi021/mcp-python-executor Executes Python code with safety constraints and manages Python packages through the Model Context Protocol. | |
| MCP Webscan Server bsmi021/mcp-server-webscan Enables web content scanning and analysis by fetching, analyzing, and extracting information from web pages using tools like page fetching, link extraction, site crawling, and more. | |
| MCP Task Manager Server bsmi021/mcp-task-manager-server A local Model Context Protocol server providing backend tools for AI agents to manage projects and tasks with persistent storage in SQLite, enabling structured tracking of project tasks with dependencies, priorities, and statuses. | |
| sticky-notes-server bsmi021/sticky-notes-server A MCP server for managing sticky notes with CRUD operations, search, tags, conversations, and a React UI. | |
| mdslides-mcp-server bsmnyk/mdslides-mcp-server An MCP server for generating HTML presentation slides from Markdown content using the mkslides library, enabling integration with tools like Claude in VSCode to create and manage presentations. | |
| ghidra-mcp bsoman3/binary-diffing-workshop-mcp-server-and-agent-container Enables AI agents to analyze and diff binaries by driving Ghidra headless or inside its GUI, exposing native reverse-engineering tools such as listing functions and segments, searching strings, decompiling, disassembling, and following cros | |
| Sushimaster bsosik1/sushimaster-mcp MCP server for finding deals in food delivery apps (Wolt and Glovo). Enables AI agents to search restaurants and dishes, compare prices, ratings, and delivery options, and get recommendations with direct links. | |
| FPL Strategy MCP bsovs/fpl-strategy-mcp Enables rules-aware Fantasy Premier League decision-making by evaluating your squad, transfer options, chips, and signals to return legal hold, transfer, and chip recommendations with reasoning, risk, and outlook. | |
| mcp-weatherapi bsparks/mcp-weatherapi Provides weather data tools using the WeatherAPI.com service, including current conditions, forecasts, location search, astronomy, and air quality. | |
| Pufferfish-MCP bspoones/pufferfish-mcp Enables AI assistants to control Coral/Pufferfish game panels by managing power, console commands, files, backups, SFTP transfers, and server listings across multiple panels via the Coral client API. | |
| Cogni-Docs bsreeram08/cogni-docs Enables AI assistants to search and query documentation with flexible backend configurations (ChromaDB, Xenova embeddings) and supports multiple chunking strategies via an MCP server. | |
| Git Repo Browser MCP bsreeram08/git-commands-mcp A Node.js implementation that enables browsing Git repositories through the Model Context Protocol, providing features like displaying directory structures, reading files, searching code, comparing branches, and viewing commit history. | |
| marketplace-mcp bssoft2b/marketplace-mcp Enables AI agents to read and work with Wildberries, Ozon, and Yandex Market seller accounts through typed tools, multi-account support, unified data schemas, rate limiting, audit, and encrypted credential storage. | |
| aspro-mcp bssth/aspro-mcp Enables LLMs to interact with the Aspro.Cloud REST API through self-describing tools for discovering and calling modules, entities, and methods. | |
| telegram-mcp bssth/telegram-mcp Enables MCP clients to operate a Telegram account as a userbot, providing tools for reading and sending messages, searching chats and contacts, managing media, and performing other account actions via MTProto with a locally encrypted sessio | |
| Loom Transcript MCP bstyler/loom-transcript-mcp Enables users to fetch transcripts and comments from public Loom video URLs. It provides tools to retrieve video text data and discussion threads directly through the Model Context Protocol. | |
| @bsv/mcp bsv-blockchain/bsv-ai-toolkit Provides tools and prompts for Bitcoin SV development, enabling code search, BRC lookup, and function definition search within locally cloned BSV repositories. | |
| @bsv/simple MCP Server bsv-blockchain/simple-mcp Provides AI agents with knowledge and code generation tools for building BSV blockchain applications using @bsv/simple. | |
| AI Agent Template MCP Server bswa006/mcp-context-manager An MCP server that enhances AI agents' coding capabilities by providing zero hallucinations, improved code quality, security-first approach, high test coverage, and efficient context management. | |
| AIS Revizor bswvladimir-beep/ais-revizor A local-first MCP server that gives AI coding agents runtime visibility and AI-managed debug logging. It replaces blind print() debugging by turning runtime execution into causal chains, allowing agents to instantly locate bugs by finding m | |
| AlpineDataWorks Intelligence Server btabiado/adw-mcp Agent-ready economic, market & geo-health intelligence — 163 MCP tools, 155 driver-backed indices. | |
| boxes-mcp btafoya/boxes-mcp Enables management of GNOME Boxes virtual machines through libvirt/virsh with lifecycle and snapshot operations. | |
| Android Source Explorer MCP Server btakahashi51/android-source-explorer-mcp Enables AI tools to explore AOSP internals and Jetpack/AndroidX libraries by providing on-demand source code search, class and method lookup, inheritance and reference navigation, and optional LSP-powered cross-file features. | |
| TradingView MCP btanaji/tradingview-mcp Provides real-time market data, technical analysis, screeners, and backtesting for stocks, crypto, forex, and futures to AI assistants via MCP. | |
| Smart MCP btangonan/smart_mcp A global framework for creating reusable command shortcuts and slash commands that work across any directory. It enables systematic code refactoring, debugging, and auditing through a hierarchical configuration system with global defaults a | |
| Codebase MCP Bridge btawaifi/codebase-mcp-bridge Enables LLM clients to search, read, and patch a trusted source repository with rollback-safe edits, Git operations, and allowlisted validation over stdio or OAuth-protected HTTP. Keeps secrets and arbitrary shell access out of reach while | |
| btcmatic-mcp-server btcmatic-com/btcmatic-mcp-server MCP server that gives autonomous agents pay-per-call Bitcoin context (self-custody radar, fee percentiles, price change windows, condition frequencies) paid in sats over Lightning via L402 invoices, with no account or API key required. | |
| famistudio-mcp btdt/famistudio-mcp Enables creating, inspecting, validating, and rendering NES FamiStudio .fms projects from plain JSON without a GUI. | |
| OCR Beans btechbrasil/ocr-beans Enables AI agents to extract text from Brazilian court case PDFs and images fully offline, checking legibility, OCR-ing only the pages with corrupted fonts, and returning page-level text labelled as native text or OCR with sheet numbers rea | |
| TypeSpec MCP Server bterlson/typespec-mcp Enables building MCP servers using TypeSpec, with tools for learning, scaffolding projects, and compiling TypeSpec to generate server assets. | |
| mcp-annuities-server btholath/mcp-annuities-server Enables retrieval of annuity client data, payout calculations, and portfolio analysis, with prompt templates for generating client reviews, summaries, and reports. | |
| Sugar bthompson7085/sugar Enables AI coding agents to save and recall persistent project and cross-project context across sessions through semantic search over a local SQLite store, with no external API keys required. Optionally exposes a task queue so agents can pi | |
| Owlyn MCP btitkin/owlynmcp Time-aware work sessions for AI agents. | |
| searxNcrawl btljnvtzfi/searxncrawl Enables AI agents to run parallel web searches through SearXNG and/or You.com and crawl individual pages or entire sites into clean, deduplicated Markdown or JSON, including authenticated and documentation-focused crawls. | |
| Granola MCP Server btn0s/granola-mcp Provides access to Granola notes, meeting transcripts, calendar events, and document panels through the Granola API, enabling search and retrieval of meeting-related content. | |
| Jokes MCP Server btomartelli/jokesmcp Fetches jokes from multiple APIs including Chuck Norris, Dad jokes, and Yo Mama jokes, providing humor-focused content through standardized MCP tools. | |
| OpenInsider MCP btopn/openinsider-mcp An MCP server that exposes 16 free investment-research signals (insider trades, SEC filings, short data, and live quotes) to any MCP-compatible LLM. |
35,901–35,950 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.