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 |
|---|---|
| greybeard btotharye/greybeard An MCP server that provides AI-powered code review and architecture analysis, simulating the perspective of an experienced staff engineer. It integrates with IDEs to review diffs, design decisions, and tradeoffs through natural language. | |
| Local Search btroussel/semanticsearchmcp Enables AI assistants to perform offline semantic search over user-authorized code, documents, and images on macOS using EmbeddingGemma 2. | |
| Toolport btsouth/toolport One local gateway for all your MCP servers — shared by every AI coding
tool (Claude, Cursor, VS Code, Codex). Set up each server once; keys stay in the
OS keychain; lazy discovery keeps agent context small. Local-first, open source. | |
| conduit-openapi-mcp btsouth/toolport-openapi-mcp Turns any OpenAPI/Swagger spec into an MCP server, generating one tool per endpoint with zero code. | |
| npm-search-mcp-server btwiuse/npm-search-mcp-server MCP server for searching npm packages | |
| Langfuse MCP Server btyurin0868/langfuse-mcp Enables AI agents and MCP clients to query and debug traces, sessions, observations, and exceptions, plus access prompts, datasets, annotation queues, scores, and metrics from a local server. | |
| resend-mcp-server btyy6svgy6-netizen/resend-mcp-server Enables Claude to send emails via the Resend API using the send_email tool. | |
| Ghost Browser MCP bu3no77xl/ghost_browser_mcp Undetectable browser automation server for MCP-compatible AI agents, offering 225 tools across 32 sections to navigate, extract, clone pages, and bypass antibot systems like Cloudflare. | |
| zoho-bookkeeper-mcp bu5hm4nn/zoho-bookkeeper-mcp MCP server for Zoho Books integration, enabling AI agents to perform bookkeeping operations like managing journals, expenses, bills, invoices, and file attachments. | |
| minecraft-companion buaichilajiao/minecraft-companion Enables MCP clients such as AstrBot, Claude, Cursor, or custom scripts to control a Minecraft bot over SSE through 49 tools covering perception, movement, building, gathering, crafting, combat, farming, memory, social interaction, and auton | |
| Databricks MCP Server bubbii-noh/mcp Enables AI assistants like Claude to interact with Databricks workspaces through custom prompts and tools, with secure OAuth authentication for managing clusters, executing SQL queries, and accessing workspace resources. | |
| health-hub bubiji/health-hub Lets Claude Code, Codex, and other AI assistants query locally collected Apple Health data, build weekly reports, check sync status, and log workouts or meals by hand. | |
| swarm-search bubli-mubli/swarm-search Enables parallel research across multiple cheap AI worker models, splitting a question into sub-questions and synthesizing one sourced answer with references. | |
| MCP Prompt Optimizer bubobot-team/mcp-prompt-optimizer This MCP server provides research-backed prompt optimization tools and professional domain templates designed to improve AI performance through strategies like Tree of Thoughts and Medprompt. It enables users to analyze, auto-optimize, and | |
| singit bubon-ik/singit-agent-pay This MCP server enables AI agents to hold, capture, release, and refund USDC under human-set mandates with escrow lifecycle management, human-only dispute resolution, and full audit logging on Solana devnet. | |
| zget bubroz/zget MCP server for archiving media from 600+ sites (YouTube, TikTok, etc.) and managing a local library with search, metadata, and download tools. | |
| memos-mcp-server bubua12/memos-mcp-server Enables AI assistants to read and write Memos notes through a Personal Access Token, with task-oriented search, precise editing, todo and tag management, attachment handling, exports, prompts, and resources. It supports both local stdio and | |
| pve-mcp-server bubua12/pve-mcp-server Enables AI assistants to monitor and analyze Proxmox VE virtualization environments via the MCP protocol. | |
| Zabbix-MCP bucciamc-a11y/zabbix-mcp Enables agent harnesses to triage problems, query metrics, manage maintenance, and build or edit dashboards in Zabbix 7.4 with safeguards against accidental changes. | |
| Eraser Diagram Renderer buck-0x/eraser-io-mcp-server Enables rendering of diagrams (sequence, flowchart, ER, cloud architecture, etc.) using the Eraser.io API with customizable themes, backgrounds, and scaling options. Returns image URLs or base64-encoded content with built-in icon validation | |
| Bucketeer Docs Local MCP Server bucketeer-io/bucketeer-docs-local-mcp-server Enables AI assistants to search and retrieve content from Bucketeer's feature flag and experimentation documentation for accurate information. | |
| Bucketeer MCP Server bucketeer-io/bucketeer-mcp A Model Context Protocol server that enables management of feature flags in Bucketeer through CRUD operations including listing, creating, retrieving, updating, and archiving feature flags. | |
| Momentum buckg71/momentum-mcp A deterministic scoring engine for prioritizing workstreams across projects and clients, answering 'what should I work on right now?' with auditable rankings based on staleness, deadlines, revenue weight, and cascade risk. | |
| riksarkivet-mcp bucklo/riksarkivet-mcp Enables AI assistants to conduct Swedish genealogy research using the Swedish National Archives' public APIs, from identifying parishes and locating digitised church books to fetching and reading scanned pages with source citations. | |
| Gemini MCP Server bucksibi/gemini-mcp MCP server that enables Claude Code to interact with Google's Gemini API for code analysis, chat, and summarization tasks. | |
| PowerPoint Automation MCP Server buckylee2019/powerpoint-automation-mcp Enables AI assistants to create, modify, and manage PowerPoint presentations programmatically using python-pptx. | |
| Desktop MCP budaesandrei/desktop-mcp Enables AI assistants to capture and analyze screen content across multi-monitor setups with smart image optimization. Provides screenshot capabilities and detailed monitor information for visual debugging, UI analysis, and desktop assistan | |
| linkedmcp buddhdev-harsh/linkedmcp linkedmcp | |
| household-agent buddhistrhythm/claw-household Enables AI-powered household management including inventory tracking, restock predictions, meal planning from available ingredients, and baby supply monitoring through natural language commands. | |
| FudanMailBox MCP buddykang/fudanmailbox_mcp Enables agents to manage a Fudan Cloud Mail (Tencent Enterprise Mail) account over IMAP/SMTP — browsing folders, listing and searching messages, reading content and downloading attachments, flagging, moving, archiving and deleting mail, man | |
| budgie budgie-app-solana/budgie-agent Enables agents to discover paid x402 resources, inspect the remaining USDC allowance, and make USDC payments on Solana for API calls from an on-chain delegated budget. | |
| AOCS-OmegaMCP budhasantosh010/aocs-omegamcp A quality-first multi-agent reasoning framework with fractal verification, adversarial red-teaming, and self-audit pipelines, providing deterministic MCP tools for complex analysis tasks. | |
| SanTech Content Engine MCP Server budhasantosh010/san-tech-yt-research-titles-scripts Enables YouTube competitor research, signal analysis, and transcript-aware pack building for content ideation and scriptwriting. | |
| mcp-comfyui budihartono/mcp-comfyui Bridges Claude Desktop to local and remote ComfyUI instances, enabling health checks, model listing, workflow queuing, status polling, and output retrieval. | |
| rs3-mcp buecherfresser/rs3-mcp MCP server that exposes RuneScape 3 data from the RuneMetrics, Grand Exchange, and RuneScape Wiki APIs, enabling natural language queries for player profiles, XP gains, quests, item prices, and wiki content. | |
| dongguk-rule-mcp buenosiempre-cmd/dongguk-rule-mcp Enables AI to search and retrieve regulations from Dongguk University's integrated rule management system. | |
| Remote MCP Server buerjia2012/remote-mcp Enables deployment of MCP servers on Cloudflare Workers without authentication, allowing users to create custom tools and connect them to AI clients like Claude Desktop or Cloudflare AI Playground. Provides a template for building remote MC | |
| arduino-mcp bufrai/arduino-mcp Enables AI agents to detect boards, manage cores and libraries, compile and upload sketches, and perform serial I/O through a local MCP server. | |
| upnote-mcp bug-breeder/upnote-mcp Enables AI agents to read and write UpNote notes locally via SQLite and URL schemes, supporting search, creation, editing, and organization. | |
| Cursor MCP Server buga-luga/cursor-mcp Facilitates integration with the Cursor code editor by enabling real-time code indexing, analysis, and bi-directional communication with Claude, supporting concurrent sessions and automatic reconnection. | |
| bagu-trainer bugan9527-tech/bagu-trainer Enables clients to monitor selected project code changes, match them to knowledge points, and generate contextual multiple-choice interview quiz questions from source text and working context. It exposes tools for listing knowledge points, | |
| T5Chem MCP Server bugatti742/t5chem Enables chemical reaction predictions (retrosynthesis, product, reagents), molecule validation, and property calculation through the Model Context Protocol, integrating with AI assistants. | |
| international-jobs-mcp bugeshic/international-jobs-mcp Enables searching and retrieving UN, NGO, and international organization job postings via the ReliefWeb API. | |
| mcpbin bugffet/mcpbin A testing server for MCP client implementations that provides tools for echoing data, error handling, timing operations, data generation, LLM sampling, and user elicitations. | |
| Cortex MCP Server bugg1n/cortex-mcp Cortex MCP provides AI agents with long-term portfolio memory by transforming project history and developer decisions into a structured, queryable knowledge graph. It enables assistants to maintain context across different repositories by e | |
| Loc Knowledge Graph Memory Server bughide010/smtest Enables Claude to remember information about users across chats using a persistent local knowledge graph that stores entities, relationships, and observations. | |
| CharCount Keeper bugoms/charcount-mcp Accurately counts characters, bytes, and manuscript paper based on Unicode grapheme clusters, and provides deterministic feedback to help AI meet exact length limits for self-introductions or school records. | |
| DayKeeper bugoms/daykeeper-mcp An MCP server that helps you remember special days and suggests personalized gifts and celebration messages based on relationships and budgets. | |
| Playground MCP bugoms/playground-mcp MCP server for Korean content mini-games, enabling AI agents to host and participate in quote guessing, word relay, actor relay, balance games, and daily challenges. | |
| audio-mcp bugorbn/audio-mcp Local MCP server for macOS that captures microphone input and/or system audio output into explicit, user-defined sessions and exposes the raw WAV audio to AI agents through MCP tools. |
35,951–36,000 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.