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 |
|---|---|
| competitor_analyzer-mcp-server bjmashele/competitor_analyzer-mcp-server Enables competitive analysis by validating companies, identifying sectors and top competitors, and generating comparative reports with actionable insights. | |
| Mermaid-Grammer-Inspector bjmhe-archived/mermaid-grammer-inspector-mcp A Model Context Protocol (MCP) server for validating Mermaid diagram syntax and providing comprehensive grammar checking capabilities | |
| bonk-mcp MCP Server bjoernbonk/letsbonk_mcp_server Implements Solana blockchain functionality for the LetsBonk launchpad, enabling users to launch and trade tokens on letsbonk.fun. | |
| eventor-mcp bjorges/eventor-mcp Exposes the Norwegian/Swedish orienteering federation's Eventor REST API as typed tools, letting an MCP client query events, clubs, entries and competitors, and optionally publish start and result lists, without ever seeing the user's API k | |
| tmw-mcp bjorn/tmw-mcp Enables MCP-capable AI agents to play The Mana World by logging in, moving around, fighting, trading, and talking to NPCs in real time. | |
| Google Ads MCP Server bjorndavidhansen/google-ads-mcp-server Enables Claude Desktop to access and manage Google Ads data, including campaigns, ad groups, keywords, budgets, and visualizations, through natural language interactions. | |
| WordPress MCP Proxy bjornfix/wordpress-mcp-proxy Enables interaction with multiple WordPress sites through a proxy that connects to the MCP Expose Abilities plugin. Allows discovering and executing WordPress abilities across configured sites with secure authentication. | |
| piherder-mcp bjorngluck/piherder-mcp Enables AI agents such as Cursor, Claude, and Codex to read and manage a PiHerder instance through its bearer token API, including server inventory, jobs, and host files. | |
| SmartThings MCP Server bjornhovd/samsung-smartthings-mcp Enables control and monitoring of SmartThings smart home devices through natural language, supporting switches, sensors, refrigerators, and other IoT devices with real-time status queries and command execution. | |
| Crawl4AI MCP Server bjornmelin/crawl4ai-mcp-server High-performance server enabling AI assistants to access web scraping, crawling, and deep research capabilities through Model Context Protocol. | |
| Grammarly MCP Server bjornmelin/grammarly-mcp Automates Grammarly's web interface to check AI detection and plagiarism scores, then uses Claude to iteratively rewrite text until it meets target thresholds for humanized content. | |
| Qdrant Neo4j Crawl4AI MCP Server bjornmelin/qdrant-neo4j-crawl4ai-mcp Enables autonomous orchestration of vector search, knowledge graph queries, and web crawling through a single MCP interface, providing agentic RAG capabilities for AI assistants. | |
| statsbudget-mcp bjornwalther/swedish-budget-mcp Provides structured access to Swedish national budget data, including allocations, tax revenue, and fiscal data. Enables queries on budget overviews, expenditure areas, revenue timeseries, and voting results via MCP tools. | |
| yt-transcript-mcp bjornwalther/yt-transcript YouTube transcripts as token-efficient AI context. One fetch, cached. No yt-dlp, no API keys, no system dependencies. ~50 KB per video, instant re-reads from local cache. | |
| Squarespace MCP Server bjswing/squarespace-mcp-2026-complete A comprehensive MCP server that enables AI assistants to interact with Squarespace sites, providing 67 tools for website management, e-commerce, content creation, and analytics. | |
| Query Counter MCP Server bjulius/querycountermcp Logs LLM interactions to local CSV or Markdown files with automatic categorization for detailed tracking. It provides an interactive HTML dashboard to visualize query volume, model usage, and category distribution. | |
| treasury-mcp bjunjo/treasury-mcp An MCP server that enables AI agents to query real-time Bitcoin network intelligence and corporate treasury data, including company holdings and SEC filings. It combines 49 core Bitcoin tools with specialized functions for tracking publicly | |
| MCP Template Server bjw101102/mcp-template A Python starter template for building MCP servers with client connection management and Jupyter notebook integration. Provides a structured foundation for adding custom tools, prompts, and workflows to create AI-powered applications. | |
| cloud-browser-mcp bk927/cloud-browser-mcp Enables a single user to let ChatGPT read and control a dedicated Chromium browser running on their own server, with tab, navigation, and browser-action tools plus manual approval safeguards. | |
| douyin-mcp bk927/douyin-mcp Enables Douyin public search, video and comment reading, authorized creator video management, analytics, uploads, publishing, and comment replies/deletion via official APIs and optional browser reads. | |
| QQ MCP bk927/qq-mcp Enables interaction with QQ through official bot APIs or personal accounts bridged via NapCat/OneBot v11, including status checks, target listing, bounded context retrieval, and plain-text sending to allowlisted conversations. | |
| SkillDock bk927/skilldock Enables agents to install compatible SKILL.md skills from Git repositories or local directories into a persistent registry, then discover them through search, progressive loading, and asset reads. It exposes only user-selected hot skills as | |
| X Research MCP bk927/x-mcp Enables read-only research on public X data through tools for posts, threads, profiles, search, trends, collections, and saved-result analysis using free public APIs and optional sessions. | |
| YouTube MCP AIO bk927/youtube-research-mcp Enables read-only research on YouTube by exposing video metadata, transcripts, comments, search, channels, playlists, and trending data through four task-oriented tools. | |
| espanso-mcp bkaes/espanso-mcp An MCP server for managing Espanso text expansion configurations, enabling AI assistants to create, update, delete, and list shortcuts with cross-platform support. | |
| Recall bkarabacak65/recall Enables Claude and other AI agents to store and retrieve decisions, patterns, and knowledge persistently across sessions and context compaction, either self-hosted on Redis/Valkey or through a managed SaaS. | |
| Ryft MCP bkawk/ryft-mcp A Model Context Protocol server that enables interaction with the Ryft API to manage financial resources such as payment sessions, customers, and subscriptions. It supports comprehensive operations including payouts, disputes, and account-s | |
| MCP Google Multi-Account Server bkbaheti/google-multi-account-mcp Enables natural language interaction with multiple Google accounts (Gmail, Drive, Calendar) from MCP-compatible clients like Claude. | |
| AgentBTC MCP Server bkblocksolutions-rgb/agentbtc-mcp Enables AI agents to perform Bitcoin and Lightning Network payments using a non-custodial, zero-trust architecture. It provides 13 tools for wallet management, invoice creation, and payment processing while keeping node credentials local to | |
| AgenticBTC MCP bkblocksolutions-rgb/agenticbtc-mcp Connects AI agents to Bitcoin payment rails with owner-defined spending policies and limits. | |
| Business MCP Server bke1302/business-mcp-server Enables AI to query a business database for customers, orders, and revenue using natural language through safe, well-defined tools. | |
| Plex Bridge bkhouser/plex-bridge Enables MCP clients to search selected Plex movie and TV libraries and access personal ratings, viewing history, and watched/resume state with explicit data caveats. Provides factual library context and optional taste summaries for assistan | |
| monarch-mcp bkichler/monarch-mcp MCP server that bridges Claude to Monarch Money for personal-finance analysis and lightweight edits. | |
| iphoto bklassen3434/photos-mcp Enables searching, inspecting, viewing, and refreshing a locally indexed folder of iCloud Photos downloaded with icloudpd, using metadata, GPS, place names, Apple Vision labels, and OCR without storing Apple ID credentials. | |
| weixin-mcp bkmashiro/weixin-mcp Enables AI assistants to send and receive WeChat messages through the official ClawBot API, supporting text, images, files, and videos. | |
| glados-voice-mcp bkmeneguello/glados-voice-mcp Enables AI agents to generate and play GLaDOS-style text-to-speech through a shared local daemon, with one-voice-at-a-time coordination plus status and stop controls. | |
| Bredouille MCP bknnnnn/bredouille-mcp Enables MCP clients such as Claude and ChatGPT to answer questions about French mushroom growing conditions from Bredouille's published index: per-species conditions and best days for a 1 km cell, the drivers behind an index value, commune | |
| Camera MCP bkosciow/mcp_camera Enables capturing live images from a USB camera and checking camera health via natural language. | |
| Chess MCP Server bkoseda/mcpchesssampleserver Enables chess gameplay and interaction through MCP protocol. Allows users to play chess games, make moves, and manage chess sessions through natural language commands. | |
| Todoist MCP Server bkotos/todoist-mcp Provides Todoist task management capabilities to AI assistants through the Model Context Protocol. Enables users to interact with their Todoist projects and tasks directly through Claude Desktop using natural language commands. | |
| ramen-mcp-bridge bkraad47/ramen-mcp-bridge A stdio MCP server that forwards JSON-RPC to a Ramen worker's ramen.v1.Mcp/Call over gRPC, letting stdio-only MCP clients reach Ramen's tools. Supports local plaintext and cloud TLS targets, with every flag also configurable via environment | |
| clipferry bkrdmrcioglu/clipferry Shared clipboard across Mac and Windows. Get the latest clip (optionally only from another machine), search clipboard history across devices and list paired devices; passwords and API keys are withheld unless allowed. | |
| openmemory-mcp bkrdmrcioglu/openmemory-mcp Self-hosted shared memory for AI coding tools: any MCP client can save, search (Postgres + pgvector) and recall project knowledge. Includes a web UI and Docker Compose setup. | |
| claude-mcp-config-manager bkristesiashvili/mcp-config-manager Provides an inline UI in Claude Desktop to view, add, remove, and update MCP server entries in claude_desktop_config.json, with automatic backup and app restart. | |
| SignalRank MCP bksampadi/signalrank-mcp Enables MCP-compatible clients to search SignalRank with dense, BM25, or hybrid retrieval and receive ranked evidence with provenance. | |
| vera_mcp_service bkslab/vera_mcp_service MCP Tools Server that bridges the Agent Service with data services, currently enabling knowledge base search via the kb_search tool. | |
| starlight-mcp bkspace/starlight-mcp MCP server for Astro/Starlight docs sites, providing search, get, and list tools for documentation content. | |
| Hermes Atlas MCP Server bkuri/hermes-atlas-mcp Enables AI agents to search, browse, and recommend tools from the Hermes Agent ecosystem directory with zero configuration. | |
| Jesse MCP Server bkuri/jesse-mcp An MCP server that exposes the Jesse algorithmic trading framework's capabilities to LLM agents for backtesting, optimization, and risk analysis. It provides 32 specialized tools for managing trading strategies and performing comprehensive | |
| gsap-mcp bl00dclot/gsap-mcp A static code generation server for GSAP animations. It provides 18 tools to generate tween, timeline, easing, plugin effects (ScrollTrigger, SplitText, MorphSVG, etc.), and developer utilities without any GSAP runtime dependency. |
34,501–34,550 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.