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 |
|---|---|
| Bloghunch MCP Server bloghunch/mcp-server Connects AI assistants to Bloghunch publications for automating content creation, analytics, and distribution. | |
| javis-zalo blogminhquy/javis-zalo Enables an MCP client to work with a personal Zalo account, reading messages and history, searching threads, viewing media, marking chats read and sending messages to individual or group conversations. It runs locally over stdio or an authe | |
| Remote MCP Server Authless blokpardi/remote-mcp-server-authless A deployable server on Cloudflare Workers that provides Model Context Protocol tools without requiring authentication, allowing easy integration with AI models like Claude Desktop and the Cloudflare AI Playground. | |
| G-Guest MCP server blondedevrules/g-guest-mcp Book a table, an appointment or a place in a class at a real local business. Live availability, instant confirmation, no account and no API key. Eight tools: search, fetch, get_business, check_availability, create_booking, check_booking, ca | |
| memlink blondu2024/memlink Enables encrypted synchronization of Claude Code memory files between a PC and mobile or other MCP clients, allowing memory search, retrieval, writing, and listing from anywhere even when the PC is off. | |
| nes-lter-mcp blongworth/nes-lter-mcp Enables natural language querying of oceanographic data from the NES-LTER API, including CTD profiles, cruise datasets, and station information. | |
| fetch-rendered-page-mcp blono/fetch-rendered-page-mcp MCP server that fetches and renders dynamic web pages (SPA) using Chromium, returning content as Markdown or text. It uses lightweight HTTP first with automatic fallback to a browser for JS-heavy sites, and includes SSRF protection, login s | |
| Error Collector MCP bloockchaindev/error-collector-mcp An open-source MCP server that collects errors from browser console and terminal, then uses OpenRouter's free AI models to generate summaries for AI agents. | |
| mech-cad-design-mcp bloodreaper005/cad-agent Enables coding agents to turn mechanical requirements into validated FreeCAD models with deterministic sizing from published standards, standard-part provenance, and automatic geometry validation. | |
| gmail-mcp bloody-regina/personal-gmail-mcp Enables connecting Gmail to MCP clients, allowing search, read, send, reply-all, forward, attachments, drafts, labels, and thread management across multiple Google accounts at once via a self-hosted Cloudflare Worker. | |
| gmail-mcp bloody-regina/personal-gmail-mcp-bloodyregina Enables AI assistants to manage Gmail accounts, including searching, reading, sending, replying, forwarding, attachments, labels, and drafts across multiple mailboxes on a self-hosted Cloudflare Worker. | |
| QiyueAstro MCP Server bloodymarygg/qiyue-mcp MCP server for Eastern and Western divination, enabling tarot, Lenormand, I Ching, Meihua, Qi Men, BaZi, Zi Wei Dou Shu, Xiao Liu Ren and Da Liu Ren readings via the free QiyueAstro public API. | |
| saft-mcp bloomidea/saft-mcp An MCP server that enables AI assistants to parse, validate, and analyze Portuguese SAF-T tax files, providing tools for querying invoices, customers, products, VAT breakdowns, and anomaly detection. | |
| lore-mcp-server blooming-cherry/lore-mcp-server Enables MCP clients to search and ask questions about Arknights world lore through hybrid retrieval and retrieval-augmented generation, with source annotations on generated answers. | |
| toolbox-mcp blooming-cherry/test_mcp Enables AI hosts to call deterministic tools such as echo, add, reverse, read/write files, and a C++-implemented two_sum via the MCP stdio interface. | |
| Fingerstyle Tab MCP Server blooper20/fingerstyle-tab-mcp An AI-powered MCP server that converts guitar audio recordings into high-quality fingerstyle tablature. | |
| bloorecall-mcp blooshoo/bloorecall Enables coding agents to search local notes by meaning and keyword using BM25 plus local Ollama embeddings, returning ranked paths and snippets verified against disk. | |
| Here Now ER MCP blottosicei/here-now-er-mcp An MCP server that provides real-time emergency room availability, open hospitals, pharmacies, and drug information for Korean users, especially useful during non-business hours. | |
| jevpilot bloudhood/jevpilot Gives agents an autonomous browser that takes a single goal-level call and drives a real Chrome step by step, returning a verified result or a concrete question instead of guessing. It keeps passwords out of prompts, requires approval befor | |
| intelligence-hub blpancholi/mcp_test A Multi-Domain Private Intelligence Hub that routes user queries to the best local Ollama model and uses a local vector DB (ChromaDB) for RAG. Everything runs on your machine. | |
| tardigrade-shield blu5morpheus/tardigrade-shield Model-agnostic cybersecurity MCP server for CMMC 2.0 compliance workflows with air-gapped Ollama mode. | |
| bluereacher-mcp blue-reacher/bluereacher-mcp Enables AI agents to send iMessages, check delivery status, read conversations, and verify iMessage capability over a dedicated line. | |
| observability-mcp blue-sky-exist/observability-mcp MCP server for querying observability data from Elasticsearch, SkyWalking, and Prometheus/VictoriaMetrics, enabling AI models to search logs, traces, and metrics across environments. | |
| Harmonic MCP Server blue-yard/harmonic-mcp-server Provides access to Harmonic.ai's API for searching and retrieving detailed information about companies and professionals. Supports company searches by domain or query, people searches, saved search results, and employee listings with pagina | |
| deep_researcher blue007-arc/deep-researcher-agent-mcp Enables users to run autonomous multi-stage deep research directly from MCP-compatible clients, producing cited, publication-quality technical reports from web searches and unstructured data. | |
| Spec-Tools-MCP blue03183/spec-tools-mcp Centralized MCP server for spec-driven AI agent workflows, enabling isolated feature management, task tracking, and implementation with handoff and archiving capabilities across multiple projects and developers. | |
| siyuan-mcp-server blueblueeyes/siyuan-mcp-server Enables AI models to interact with SiYuan Note systems, allowing management of notebooks, documents, blocks, files, and more through natural language. | |
| Valorant MCP Server bluebot-609/valorant-mcp-server Provides Valorant game data through the Model Context Protocol, including player details, match history, MMR, leaderboards, and game content using the HenrikDev API. | |
| lighthouse-mcp bluebridge-e/lighthouse-mcp MCP server for managing Tencent Cloud Lighthouse servers, enabling natural language control of instances, firewall rules, monitoring, and more. | |
| api-mcp-server bluechenchenchen/api-mcp-server Fetches and parses Swagger/OpenAPI documentation from URLs, cleans and optimizes it to reduce token consumption, and provides standardized API descriptions to intelligent IDEs for suggestions, auto-completion, and code generation. | |
| dsh-computer-use bluechonk/dsh-computer-use Enables agent-native desktop control by driving mouse, keyboard, and interface elements through accessibility-first semantic operations, with fallback to screen coordinates when accessibility cannot reach a target. | |
| stitch-mcp-stdio bluedevilcollectibles/stitch-mcp-stdio Stable stdio MCP server for Google Stitch AI UI design tool, eliminating the proxy subprocess to prevent crashes. Provides tools to manage projects, screens, design systems, and generate UI designs. | |
| MEDAS MCP bluedragondc/medas_mcp Enables querying TÜİK (Turkish Statistical Institute) indicators via 92 topics and 400+ indicators, with cached metadata for fast responses and optional live download of real Excel reports through a Playwright-powered ZK Widget API. | |
| agent-web-search-mcp blueewhitee/agent-web-search-mcp Enables MCP-compatible agents to perform web searches via the agent-web-search engine, returning ranked results with sources. | |
| belex MCP Server blueforce/belex-mcp Provides AI assistants with citable access to Bernese laws (BSG) and administrative court rulings (Verwaltungsgericht Bern) via search, retrieval by number, and article extraction. | |
| Vybsly MCP bluefusionlab/vybsly-mcp MCP server for Vybsly AI-first search API, providing full-content web search with 24M+ pages, encyclopedia federation, strict-mode filters, and real-time data tools. Enables natural language search, content extraction, and access to live da | |
| code-failures-mcp blueif16/code-failures-mcp MCP server that indexes a knowledge base of past bugs and fixes, making them searchable via BM25 from Claude Code or any MCP client. | |
| doltap-mcp bluekds/doltap-wiki Enables AI agents to search, read, create, patch, lint, and synchronize a shared Markdown+git knowledge base across multiple machines and sessions, with confidence metadata and protocol resources. | |
| Meta-MCP Server blueman82/mcp-exec A Model Context Protocol server that wraps multiple backend servers for token-efficient tool discovery via lazy loading. It enables AI models to browse available servers and fetch specific tool schemas on-demand, significantly reducing init | |
| Recall blueman82/recall Provides long-term memory storage for AI assistants with semantic search, enabling persistent storage of preferences, decisions, and context with relationship tracking between memories. | |
| blue-matador-mcp-server bluematador/blue-matador-mcp-server Enables natural language management of Bluematador monitoring, including cloud integrations, alerts, notifications, and team management. | |
| subagent-mcp bluemonkey262/subagent-mcp Enables delegating work from a Claude Code session to resumable, approval-aware child agents across Claude Code, Codex, OpenCode, Antigravity, and Cursor, with tools for spawning, messaging, stopping, and reviewing events. | |
| vangard-daz-mcp bluemoonfoundry/daz-mcp-server MCP server that enables Claude to control DAZ Studio for scene manipulation, morph discovery, animation, and rendering. | |
| CRAG-MCP bluemot/crag-mcp A Model Context Protocol server that builds and queries a config-aware code graph with support for conditional compilation (#ifdef) filtering, enabling context-aware code analysis across different build configurations. | |
| TaskMesh MCP Server blueneon-tech-pvt-ltd/task-mesh-mcp Enables AI IDEs to interact with TaskMesh task management and time tracking APIs through secure, scoped access tokens. | |
| bluente-translate bluente/bluente-translate-mcp-server Translate your documents with formatting intact in 2 minutes | |
| bluepages-mcp bluepagesdoteth/bluepages-mcp Enables looking up Ethereum address mappings to Twitter/X and Farcaster identities, with tools for checking and retrieving identity data. | |
| TradingView MCP Jackson bluepandanyc/tradingview-mcp-jackson- Enables Claude to control and read from the TradingView Desktop app, providing automated morning briefs, chart analysis, Pine Script development, and replay mode. | |
| shared-memory bluepiecom/dsh-reef Enables multiple DSH plugin/session agents to share trust-labeled Markdown memory and query on-demand cross-plugin digests, with write access isolated per channel so untrusted third-party content cannot become instructions. | |
| Meshy AI MCP Server blueplanet0628/meshy-ai-mcp Enables to generate 3D models from text and images, apply textures, and remesh models using the Meshy AI API. |
34,751–34,800 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.