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 |
|---|---|
| @chartobserver/mcp-server bbusche/chartobserver-mcp An MCP server that lets an AI agent read your portfolio, place paper trades, and check the leaderboard on your ChartObserver account. | |
| FI-MCP bbusenius/fi-mcp Provides AI assistants with access to 30+ validated financial independence calculation functions, eliminating hallucinations by ensuring accurate calculations for retirement planning, CoastFI, investment returns, and other FI metrics. | |
| paper-search-mcp bbutlerau/paper-search-mcp Enables searching scholarly literature across CrossRef, ERIC, Semantic Scholar, and OpenAlex, and retrieving open-access PDFs via Unpaywall. | |
| Shopping List MCP Server bbwrl/shopping-list-mcp-server Enables AI assistants to manage a shared shopping list by adding, viewing, updating, and deleting products for different people via MCP tools. | |
| DealerFront bc1pzzfnxl/dealerfront Enables external AI agents to join, observe, and act in real-time Paris IRIS cartel battle royale games, using MCP tools to get state, plan moves, and communicate during matches. | |
| Pentest MCP bcampos29868/pentest-mcp Enables professional penetration testers to run reconnaissance, vulnerability scanning, brute-force checks, traffic capture, exploitation support, and report generation through a unified tool interface. Supports local and networked transpor | |
| MCP1 bcauley70/mcp1 A minimal MCP server that tells an interactive knock-knock joke suitable for children, supporting both local stdio and HTTP deployments. | |
| visual-understand-mcp bcdxc/visual-understand-mcp Provides image understanding capabilities to coding models without vision support by automatically invoking a vision model and returning text descriptions, enabling seamless context-aware coding with images. | |
| math-animation-mcp bcefghj/math-animation-mcp Enables creating 3Blue1Brown style math animations from text descriptions, PDFs, or images. Supports rendering educational videos for math and physics topics. | |
| webgrab-mcp bcefghj/webgrab MCP server for web content downloading supporting videos, articles, danmaku, comments, and copy protection bypass across 1700+ sites. | |
| kube-handrail bcfmtolgahan/kube-handrail Enables AI agents to perform safe, auditable Kubernetes write actions such as scaling, restarting and rolling back Deployments through a plan → policy-check → approve → apply → audit flow, with server-side guards, single-use plans and scope | |
| icon-mcp-server bcgbsh/icon-mcp-server Generates software and app icons locally as PNG, ICO, or ICNS files with customizable styles, shapes, gradients, text, and shadows, requiring no external APIs or network access. | |
| AgentTrust MCP bch1212/agenttrust-mcp Reputation infrastructure for the A2A economy, providing agent identity, trust scores, transaction history, and peer endorsements through twelve MCP tools. | |
| InjectShield bch1212/injectshield MCP server that provides tools to scan text and URLs for prompt injection attacks, protecting AI agents from adversarial inputs. | |
| cursor-browser-mcp bcharleson/cursor-browser-cli Enables AI agents to control Cursor IDE's built-in Browser Tab through a stdio MCP interface, providing accessibility snapshots with refs, click/type/fill, wait conditions, screenshots, and console/network inspection. | |
| gsc-agent-cli bcharleson/gsc-agent-cli Enables querying Google Search Console data, Core Web Vitals, and PageSpeed insights from the terminal or via MCP tools. | |
| Instantly MCP Server bcharleson/instantly-mcp Provides access to Instantly API v2 for email campaign and lead management functionality. | |
| Instantly MCP Server bcharleson/instantly-mcp-python Enables interaction with Instantly.ai email outreach platform through 31 tools across accounts, campaigns, leads, emails, and analytics. Supports both local and remote deployment with multi-tenant authentication. | |
| prospeo-cli bcharleson/prospeo-cli MCP server for the Prospeo API that provides person and company enrichment and search functionality, including email, mobile, job history, LinkedIn data, and company details. | |
| Slack MCP Server bcharleson/slack-agent-cli Enables AI assistants to interact with Slack workspaces through comprehensive channel management, messaging, direct messages, search functionality, and user management capabilities. | |
| smartlead-cli bcharleson/smartlead-cli MCP server for managing cold email campaigns, leads, email accounts, sequences, analytics, webhooks, and client sub-accounts via the Smartlead API. | |
| Cursor Sound MCP bcharleson/sound-mcp Plays sound effects when Cursor AI completes code generation, providing audio feedback for a more interactive coding experience. | |
| zoom-agent-cli bcharleson/zoom-agent-cli MCP server that provides 59 tools to manage Zoom meetings, recordings, users, webinars, reports, dashboard, chat, and groups via the Zoom API. | |
| CapCut MCP Server bchenner/capcut-mcp Enables AI coding agents to programmatically assemble vertical videos and manage local CapCut Desktop drafts, including AI background removal, audio mastering to -14 LUFS or Demucs vocal isolation, music auto-ducking, punch zooms, karaoke c | |
| VK Dating MCP bchkv/vk-dating-mcp An unofficial local stdio MCP server that uses a persistent Playwright browser profile to let MCP clients inspect VK Dating pages, manage chats and matches, preview or send and edit messages, react to content, and capture local snapshots. A | |
| alfredo bchong12/alfredo Enables MCP-compatible AI assistants to search and ask questions across a company's board, docs, canvas, and meeting transcripts, with citations, and to take actions like updating cards. | |
| bws-mcp bchoor/bws-mcp Enables remote management of Bitwarden Secrets Manager secrets through a Cloudflare Worker, supporting list, get, put, and delete operations within allowlisted projects. | |
| MCP-Memory-LanceDB-Pro bcornish1797/mcp-memory-lancedb-pro A full-featured long-term memory system for Claude Code that persistently stores and retrieves preferences, decisions, and project context across sessions using hybrid search and LLM-powered extraction. | |
| backtester-mcp bcosm/backtester-mcp Local-first backtesting engine with built-in overfitting detection (PBO, deflated Sharpe, bootstrap CI, walk-forward) and a native MCP server for AI agents to validate trading strategies. | |
| MCP Gestão de Tarefas bcosta19/mcp-gestao-tarefas Integra agentes de desenvolvimento ao sistema Gestão de Tarefas, permitindo gerenciar projetos, demandas, sprints e tarefas com suporte a fila offline e sincronização posterior. | |
| HubSpot Email MCP Server bcousin93/hubspot-email-mcp Enables Claude Code to create HubSpot marketing email drafts from Markdown and Word documents with automatic image handling and brand guidelines. | |
| Xbox Controller MCP Server bcperry/controller_mcp An MCP server that provides Xbox controller emulation capabilities, allowing users to programmatically control buttons, analog sticks, and triggers through an API interface. | |
| imap-mcp bcrisp4/imap-mcp Enables an AI agent to search and read a single IMAP mailbox through a local, read-only index and write Markdown drafts without ever sending mail. | |
| vilsem-mcp bcsnpc/vilsem-mcp Enables agents to connect to Power BI semantic models, preview custom ECharts-based visuals with model data, and insert and validate them in existing local PBIR reports. | |
| Bybit MCP Server bcusack/bybit-py-mcp A comprehensive MCP server providing full access to Bybit's v5 API for real-time market data, trading operations, and account management. It enables AI assistants to execute trades, manage positions, and monitor wallet balances with built-i | |
| Foundry Claude Bridge bcw3075/foundry-claude-bridge Lets Claude act inside a Foundry VTT world through OAuth-secured MCP over HTTPS, reading and sending chat, rolling dice, looking up actors, scenes, tokens, combat and journals, moving tokens, and driving the Lythara Survey Sheet map module. | |
| Google Workspace MCP Connector bd01010/chatgpt-workspace-connector A ChatGPT custom connector that enables users to access, create, and manage Google Workspace files (Drive, Docs, Sheets, Slides) directly through ChatGPT using OAuth 2.0 authentication. | |
| ODV MCP bd4xda/oceandataview-mcp-server Connects MCP-compatible AI assistants to Ocean Data View, enabling inspection of collections and saved views, export of scientific data, and rendering of bounded views to images while leaving original collections unopened. | |
| estudio-aprendizagem bdasilvasouza905-dotcom/estudio-aprendizagem Enables ChatGPT to deliver interactive educational exercises with server-side session management, answer validation, justifications, and learning summaries via MCP. | |
| Exely Hotel Booking MCP Assistant bdata0/exely_mcp Enables hotel booking operations through the Exely Distribution API via natural language interactions. Integrates with LLMs and Telegram bots for seamless hotel search, booking, and management functionality. | |
| io.github.bdbais/routeai bdbais/routeai Enables Claude Code to offload small coding tasks to local Ollama machines and free or paid AI providers, choosing the cheapest available option while enforcing quotas, budgets, and Claude's final review. | |
| GitHub Portfolio MCP Server bdbrown4/github-portfolio-mcp-server Enables AI agents to query a GitHub user's public profile, repositories, language breakdowns, and README content | |
| bdc-doc-mcp bdc-assist/bdc-doc-mcp Provides a documentation search MCP tool (search_docs) that enables AI agents to retrieve relevant chunks from BDC documentation using semantic embeddings and keyword search, with filtering by document type and date. | |
| Redis Graph MCP Server bdc-assist/dug-mcp Enables LLMs and AI agents to search a biomedical knowledge graph for concepts and study variables, traverse semantic relationships, and look up BioData Catalyst PIC-SURE paths for cohort building. | |
| Windsurf AI Interceptor bddda/windsurf-mcp An MCP server that automates the continuation of AI tasks by intercepting tool calls and injecting user instructions directly back into the execution flow. It eliminates the need for manual 'continue' prompts, enabling an uninterrupted and | |
| maya_mcp bdeda/maya_mcp A Model Context Protocol server that enables AI assistants to interact with active Autodesk Maya sessions using the maya.cmds API. It allows users to manage scene objects, control selections, and perform common 3D operations through natural | |
| zotero-mcp bdejager621/zotero-mcp Enables AI assistants to search a Zotero library, retrieve item metadata, and access full-text PDF contents through MCP tools. | |
| flake-verbs bdelanghe/flake-verbs Enables analyzing Nix flakes to identify which inputs are actually used and to detect locked-input drift, including unportable or orphaned inputs, through MCP tools. | |
| Sonarr & Radarr MCP Server bdfrost/mcp-servarr Enables interaction with Sonarr and Radarr APIs to query media libraries, check recent additions, view upcoming releases, manage download queues, and perform searches for TV shows and movies through natural language. | |
| c64-kb bdgscotland/c64-kb Enables AI agents and developers to query a structured Commodore 64 knowledge base over MCP, combining semantic search and knowledge graph traversal for hardware references, techniques, recipes, pitfalls, timing budgets, and compatibility c |
33,301–33,350 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.