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 |
|---|---|
| Google Workspace MCP Server davidpak/ada-mcp-servers Enables AI assistants to manage Google Calendar events and Gmail emails through natural language. Supports creating/listing calendar events with smart color coding, sending/reading emails, and advanced search capabilities across both servic | |
| systems-thinking-mcp davidpanter/systems-thinking Provides systems thinking models as composable analysis lenses for architecture, infrastructure, DevOps, incident analysis, and technical decision-making. | |
| pushinglimits-mcp davidpetras92-sys/pushing-limits-mcp Enables local retrieval of Pushing Limits Club training data, including planned and actual workouts, TSS, CTL/ATL/TSB, weekly summaries, and thresholds, without needing a browser. It provides these metrics to Claude Desktop via stdio. | |
| telegram-mcp davidphc/telegram-mcp-bot An MCP server that connects to a Telegram group chat, persists messages to a local SQLite database, and exposes tools to search, retrieve, and send messages via SSE. | |
| ProxmoxMCP-Plus davidpius95/guildserver-proxmox-mcpserver Enhanced MCP server for managing Proxmox virtualization platforms with complete VM lifecycle management, LXC container support, and OpenAPI integration. Enables natural language VM creation, power management, and comprehensive cluster monit | |
| qa-mcp davidpoza/qa-mcp Automates generation of QA artifacts such as API tests, E2E tests, and documentation exports. It supports REST Assured, Cypress, and Excel/Word document generation. | |
| Casper Agentic Portfolio Copilot davidpraise0x/casper-agentic-portfolio-copilot AI-driven portfolio dashboard and MCP server for the Casper blockchain, enabling wallet monitoring, validator staking analysis, RWA compliance checks, and on-chain transaction generation. | |
| luckjingle-mcp davidray/iocane Enables Claude or any MCP client to design and print text and images to Bluetooth thermal label printers, including scanning, configuring, and managing multiple printers. | |
| Peek davidray/peek Enables an AI agent to capture a photo via a live camera preview, returning the image to the agent and saving it locally. | |
| FlowLens MCP davidrezende470/flowlens-mcp-server It gives coding agents full browser context from recorded browser flows for in-depth debugging and regression testing, allowing them to inspect user actions, network activity, console logs, storage, DOM events, and screen recordings without | |
| mcp4openapi davidruzicka/mcp4openapi Turn any OpenAPI specification into a smaller, LLM-friendly MCP server. Enables interaction with REST APIs through MCP tools using profiles to reduce complexity. | |
| Mini-ERP MCP davidsandez/mcp-erp Enables language models to discover and use standardized ERP tools and resources, such as querying stock, viewing products and clients, and registering sales with human confirmation for destructive actions. | |
| mcp-insee-entreprises davidscanu/mcp-insee-entreprises MCP server to query the INSEE SIRENE API and search for French companies, supporting searches by SIREN, SIRET, and advanced filters like name, location, and activity. | |
| easy-crypt-mcp davidscode404/easy-crypt-mcp Enables AI agents to load, inspect, test, and repair machine-checked cryptographic proof files by wrapping EasyCrypt's batch CLI in six tools that report open goals and diagnostics. Agents can try tactic snippets on temporary copies, then c | |
| CIA Diagnose davidscoreal/cia-diagnose Expert business diagnosis engine that analyzes companies across 11 dimensions and returns a Revenue Leak Score with prioritized, triple-option recommendations. | |
| ChatGPT Inbox Community davidsegade/chatgpt-inbox-community Enables compatible MCP clients to list authorized Obsidian folders, create new Markdown notes, and check delivery receipts through a paired relay. | |
| MCP Tool Server davidshtian/mcp-on-aws-bedrock Facilitates interaction with AWS Bedrock-enabled tools by implementing Anthropic's Model Context Protocol for seamless tool integration and communication. | |
| mcp_boe davidsilvente-dev/mcp-servers-demo Enables AI assistants to query the BOE's daily gazette summary and search recent summaries for provisions whose titles contain given words, returning titles, sections, departments and links. Runs locally over stdio or as a stateless HTTP MC | |
| bizmachine-mcp davidsimoes/bizmachine-mcp Access Czech and Slovak company data (financials, contacts, risks, ownership) via BizMachine API, enabling natural-language lookups by name, domain, or ICO. | |
| Grok Chrome Bridge davidsolheim/grok-chrome-bridge Enables Grok Build to attach to the user's active Chrome profile via MCP, leveraging the profile's tabs, cookies, and logins instead of launching an isolated browser. | |
| todoie davidstor/todoie Enables natural language task management: capture, edit, complete, and search tasks with duplicate detection and citation-backed answers. | |
| MCP Local Filesystem Server davidsusairaj/file_system_mcp An MCP server that provides secure access to local file system operations. | |
| MCP Market davidsyahshi/mcp-market Enables users to mint, browse, buy, sell, and list NFTs, and to manage a $MCP balance funded with USDC or USDT on Solana, all through natural-language chat inside Claude or ChatGPT. Includes deposit address issuance, on-demand deposit check | |
| solana-mcp-server davidsyahshi/solana-mcp-server Enables AI agents to query Solana balances, SPL and Token-2022 holdings, transaction summaries, and recent activity, and to dry-run SOL transfers through read-only tools. It validates inputs and never signs or broadcasts transactions. | |
| ffd-mcp davidtauriello/ffd-mcp Parses SEC EDGAR Exhibit 107 XBRL fee disclosures from registration statements and returns structured fee data through the Model Context Protocol. No API keys required. | |
| xule-mcp davidtauriello/xule-mcp Provides reference and pre-flight linting for XBRL Query and Rules Language (XULE), helping LLMs write syntactically sound rules with tools for object model lookup, function catalog, filter syntax, and boilerplate snippets. | |
| Claude Server MCP davidteren/claude-server Provides sophisticated context management for Claude, enabling persistent context across sessions, project-specific organization, and conversation continuity. | |
| MCP Play Sound Server davidteren/play-sound-mcp-server Provides audio playback functionality for AI agents, allowing them to play notification sounds when coding tasks are completed. | |
| signet davidtorcivia/signet A self-hosted MCP server for the Pebble Index 01 ring that lets you press the ring to capture voice notes, search journals and the web, and execute tools on your own infrastructure rather than someone else's cloud. | |
| WhatsApp Channel davidv539/whatsapp-claude-plugin Enables driving a Claude Code session from WhatsApp over a linked device or the official Cloud API, with bidirectional messaging, full media support, local voice-note transcription, per-group personalities, and context recovery after restar | |
| Code Knowledge MCP Server davidvc/code-knowledge-mcptool Provides a project memory bank and RAG context provider for enhanced code understanding and management through vector embeddings, integrated with RooCode and Cline. | |
| Jokes MCP Server davidvenanciodp/jokesmcp Enables Microsoft Copilot Studio agents to fetch and deliver jokes on demand through the Model Context Protocol. It is published as a Power Platform custom connector, so access benefits from enterprise security, governance, and real-time da | |
| Hacker News MCP Server davidvgilmore/hn-mcp-server Enables AI assistants to fetch top, new, best, Ask HN, Show HN, and job stories, as well as specific posts, comments, and user information from Hacker News through the Model Context Protocol. | |
| gmail-mcp davidvinu/gmail-mcp Enables AI assistants to read and draft emails across multiple Gmail accounts at once, with strict safeguards that prevent sending, deleting, or modifying mailbox settings. | |
| mail-mcp davidvornholt/pim An IMAP helper for Thunderbird workflows that allows searching, reading, and creating/updating/deleting drafts with HTML and attachments via MCP or CLI, but cannot send emails. | |
| AI Work Hub MCP Server davidvuy/ai-work-hub A local-first MCP server that lets AI assistants search and retrieve context from indexed projects, Git state, decisions, and tasks without sending data to the cloud. | |
| EasyAirClaim MCP Server davidvv/claimplane-mcp This MCP server provides tools for developers to query, create, and manage test data for the EasyAirClaim application, including customers and flight delay claims. It is intended for development and testing only, with full database access a | |
| Recall davidwang04041/recall Enables Claude and other AI agents to persistently store and retrieve decisions, patterns, and knowledge across sessions, surviving context limits, restarts, and compaction. It supports self-hosted Redis/Valkey or managed cloud deployment w | |
| Cerebras Code MCP Server davidweatherall/cerebras-code-mcp Enables planning with Claude Code and high-speed code generation using Cerebras, avoiding API limits while producing quality code with visual diffs. | |
| Cloudflare Playwright MCP davidwhitelabeledca/playwright-mcp-pumpjack An MCP server that enables AI assistants to perform web automation tasks such as navigation, clicking, and taking screenshots by running Playwright on Cloudflare Workers. It allows models to interact with the web through a set of browser co | |
| local-web-mcp davidwlindholm/local-web-mcp Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures. | |
| notion-local-ops-mcp davidwuwu001/notion-local-ops-mcp Enables a Notion MCP Agent to work as a local coding agent by exposing local files, shell, git, and patch-style editing over MCP, plus delegated long-running tasks via local Codex or Claude. It also supports managing local MCP services and | |
| malaysia-payroll-mcp davidyapcc/malaysia-payroll-mcp Enables calculating Malaysian statutory payroll deductions—EPF, SOCSO, EIS and MTD/PCB—for a resident employee's fixed monthly salary, citing the official rate table or rule behind each figure. | |
| Caltrain MCP Server davidyen1124/caltrain-mcp A Model Context Protocol server that provides real-time Caltrain schedule information, allowing AI assistants to look up train departures between any stations and access station information using GTFS data. | |
| clinicaltrialsgov-mcp-server davidyilmaz194/clinicaltrialsgov-mcp-server Enables searching 600K+ ClinicalTrials.gov studies with field-specific, status, phase, and geographic filters, retrieving full study records and posted results, discovering valid field names and values, and matching patient profiles to recr | |
| CNKI Search MCP Server davidyuan666/cnkisearchmcp An MCP server for searching Chinese academic papers and core journal information across multiple free platforms like Baidu Scholar and the National Center for Philosophy and Social Sciences. It enables users to retrieve metadata for social | |
| Multi-Agent MCP davidzong1/mult-agent-mcp Creates and manages multi-agent teams of AI coding assistants (Claude Code, Codex CLI) that collaborate in tmux terminal sessions. Enables a leader agent to assign sub-tasks to team members for coordinated development. | |
| @roompanda/mcp daviesevan-svg/roompanda-mcp Enables AI agents to search availability, price rooms, and make real bookings via the Roompanda API, scoped to a single property by the API key. | |
| Fanside AI davieslennox0/fanside-ai Enables agents and humans to pay per question over x402 and receive plain-language answers about on-chain activity, priced by complexity before execution. Each paid request runs a live subgraph round trip to search, validate, generate and e | |
| bim-agent daviidro/bim-agent MCP server that enables one-click BIM audits by chaining IFC statistics, validation, and quantity takeoff workflows through natural language queries. |
42,801–42,850 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.