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 |
|---|---|
| Marriott MCP emrgim/marriott-mcp Enables AI agents to read Marriott Bonvoy account details, stays, trips, and hotel availability, and to create, modify, or cancel reservations through a real Chrome session, with all writes gated on explicit human confirmation. | |
| raptio-mcp emsnicket/raptio-mcp Enables MCP clients to monitor KegLand RAPT fermentation chambers and RaptPill hydrometers via the RAPT.io API, and to control temperature, PID settings, and profiles when mutating operations are explicitly enabled. | |
| Cold Mail Agent MCP emsoumik/cold-mail-agent-mcp Provides context-aware cold outreach guidance for AI clients via a single tool, cold_email_guidance, helping draft personalized and effective emails. | |
| Natural Voice MCP emsoumik/natural-voice-mcp Provides writing guidance and mechanical lint checks to help AI clients draft or rewrite content in a specific natural voice. | |
| carry emtcmca/carry Enables syncing a context pack between Claude Code and Claude mobile via a remote MCP server, allowing users to push instructions from their repo and read them on mobile. | |
| evren-mcp emuzinun/evren-mcp Connects Claude Code to the EVREN Yapay Zeka Platform, enabling users to list datasets, estimate training costs with time-limited offers, start only approved training jobs, and retrieve results, metrics, and credit usage under per-job and d | |
| windows-debug-mcp emyk/windows-mcp Read-only MCP server for diagnosing Windows crashes, stability, and gaming performance by reading event logs, crash dumps, hardware inventory, performance counters, and registry settings. | |
| server-anthropic emzimmer/server-anthropic Provides access to Anthropic's AI models through the Model Context Protocol, enabling listing models and sending messages to Claude via a standardized interface. | |
| Mozilla Readability Parser MCP Server emzimmer/server-moz-readability Extracts and transforms webpage content into clean, LLM-optimized Markdown. Returns article title, main content, excerpt, byline and site name. Uses Mozilla's Readability algorithm to remove ads, navigation, footers and non-essential elemen | |
| WordPress MCP Server emzimmer/server-wp-mcp Enables AI assistants to interact with WordPress sites through the WordPress REST API. Supports multiple WordPress sites with secure authentication, enabling content management, post operations, and site configuration through natural langua | |
| MCP Access OAuth Server ena-turcotte6/mcp-access-oauth A Cloudflare Workers-based MCP server that enables secure remote connections using built-in OAuth authentication via Cloudflare Access. It provides identity-based access control for MCP tools and supports persistent state management through | |
| CVEstate enabled404/cvestate Enables vulnerability lookup and triage across NVD, EPSS, CISA KEV, OSV, and many other sources, while tracking an estate's exposure changes from SBOMs and lockfiles through snapshots and prioritized diffs. | |
| gobbler-mcp enablement-engineering/gobbler Converts YouTube videos, audio, documents, and web pages to clean markdown with YAML frontmatter, providing AI assistants with structured content via the MCP protocol. | |
| Agentic RAG MCP enached134-ctrl/agentic-rag-mcp A multi-agent Retrieval-Augmented Generation system exposed as an MCP server. Ask a question and a LangGraph pipeline plans the retrieval, pulls evidence from a pgvector knowledge base, optionally augments it with live web research, drafts | |
| mcp-toolkit-server enachimuthu/mcp-toolkit-server Enables everyday utilities like calculation, text analysis, encoding, hashing, UUID generation, datetime lookup, and note management through MCP tools, resources, and prompts. | |
| AIDA MCP Server enaconsucr/aida2026-mcp-agents Exposes three Model Context Protocol tools — World Bank REST indicators, OECD SDMX statistics, and a local corpus of 60,278 Google Play reviews of the EDUS digital-health app — plus a data schema resource. Enables LLM agents to retrieve and | |
| Enapter MCP Server enapter/mcp-server MCP server providing tools for AI-agents to interact with Enapter EMS. | |
| MCP Brave Search Server enbock/mcp-server Enables web search using the Brave Search API, with configurable query and result count. | |
| memoryd enboxorg/memoryd User-owned AI memory layer exposing persistent memory, task graph, and semantic search via MCP server, with data stored on DWN under user control. | |
| vue-ts-lsp enc0ded/vue-ts-lsp-mcp Self-contained MCP server providing type-aware code intelligence for TypeScript, JavaScript, and Vue files, exposing tools like hover, definition, references, and diagnostics to Claude Code without requiring global language server installat | |
| Vps-mcp enchanted-dev-stack/vps-mcp Enables a ChatGPT Web conversation to act as a coding agent on a VPS, with project-bound chats, Git worktree isolation, live activity streaming, structured questions, and file/image exchange via MCP. | |
| cyclops enchanter-ai/cyclops A security MCP proxy that monitors and blocks data exfiltration between AI agents and their tools by detecting toxic flows (untrusted → sensitive → egress) deterministically with zero LLM calls in the decision path. | |
| Lippy-Agent MCP Server enchawk/lippy-agent Enables monitoring of website changes through contracts, with automatic extraction, semantic diffing, and healing, triggering alerts and actions via email, Slack, or Telegram. | |
| KAP MCP Tools enciyo/kap-tr-mcp A Model Control Protocol server that provides access to Turkey's Public Disclosure Platform (KAP) data, including company information, financial reports, market announcements, and sector information. | |
| MCP STDIO Webhook Server encoded-evolution/mcp_webhook_python_zed A lightweight MCP server that accepts event envelopes, maps them to configurable tools, and supports STDIO transport with Docker deployment. | |
| lookup-holiday encodi/lookup-holiday Real public/bank/school holiday lookup for 206 countries via a rule-based calendar engine (moveable holidays like Easter computed astronomically, not guessed). Priced per call via x402/USDC on Base. | |
| simulate-monte-carlo encodi/simulate-monte-carlo Real Monte Carlo simulation of a compound event or conditional probability. Named random variables, a safe expression interpreter, seedable for reproducibility. Priced per call via x402/USDC on Base. | |
| Sonora MCP encodi/sonora-mcp Enables AI assistants to query Spotify for what is currently playing and to search tracks, albums, artists and playlists, with optional opt-in play/pause control. It authenticates via OAuth PKCE without a client secret, requesting least-pri | |
| validar-codigo-medico encodi/validar-codigo-medico MCP server that validates medical codes (ICD-10-CM with official descriptions, CPT structural checks) via a single tool, with x402 billing. | |
| validar-semver encodi/validar-semver MCP server that validates semantic version ranges using npm's semver engine, with payment via x402 on Base mainnet. | |
| Discord MCP encryptman/discord-mcp An MCP server that exposes Discord bot actions as tools for LLM clients. | |
| Telegram MCP encryptman/telegram-mcp https://github.com/EncryptMan/telegram-mcp | |
| C2PA Knowledge Graph encypherai/c2pa-knowledge-graph MCP server for querying versioned C2PA specification knowledge graphs, enabling AI agents to browse entity definitions, validation rules, and version diffs via natural language. | |
| Cloudflare Authless Remote MCP Server end0z/mcp Enables deployment of a stateless remote MCP server on Cloudflare Workers without authentication, allowing users to register custom tools and connect from clients like Cloudflare AI Playground and Claude Desktop. | |
| repos-expert end1989/repos-expert MCP server that studies a folder of code repositories, generates markdown documentation (architecture, interfaces, activity), and serves answers over MCP with live ripgrep search and file reads so AI assistants can query codebases and their | |
| Model Context Protocol PostgreSQL Server endaoment/endaoment-postgres-mcp A server that allows AI models to interact with PostgreSQL databases through a standardized protocol, providing database schema information and SQL query execution capabilities. | |
| Ansim Dolbom Assistant enddn/ansim-dolbom-mcp Enables caregivers to log daily care activities and generate draft notification reports for the elderly, with automatic safety constraints to prevent AI-generated inaccuracies. | |
| klattsch-mcp endeavor-doxidoxi/klattsch-mcp Enables AI models to speak and sing using retro-style formant speech synthesis, converting text or phoneme strings to WAV audio via MCP tools. | |
| Trading 212 MCP Server enderekici/trading212-mcp Enables AI assistants to interact with Trading 212 investment accounts for portfolio tracking, account management, and real-time order execution. It supports managing investment pies, analyzing historical data, and monitoring market perform | |
| xero-payroll-au-mcp enderguardian25/xero-payroll-au-mcp Provides read-only MCP access to Xero accounting data, with strict safeguards against mutations and sensitive field leakage, while Australian payroll pay run, payslip, and superannuation tools are planned but not yet exposed. | |
| Dice Roller MCP Server endikoci02/dice-roller-mpc-server A Model Context Protocol (MCP) server that provides random dice rolling capabilities for AI assistants. | |
| Clean-Cut-MCP endlessblink/clean-cut-mcp Enables users to create professional React-powered videos through Claude Desktop using natural language and the Remotion framework. It provides a persistent studio environment for generating animations, managing video assets, and rendering | |
| sociableWiki endmoseung/sociablewiki Public, agent-searchable knowledge base about AI-native software development, served as an MCP server with tools to search, read, and list topics. | |
| protheus-mcp-server (piloto) endrews-dfl/mcp-protheus-tdn Read-only MCP connector for querying the Protheus (TOTVS) system, exposing 10 GET endpoints as MCP tools with OAuth2 authentication and friendly error handling. | |
| Pilot Browse MCP endymionlee/pilotbrowsemcp Enables AI agents to browse websites, record workflows, and generate reusable operation manuals, reducing token usage and execution time for future tasks. | |
| QR Reader MCP Server endymionus/qr-reader-mcp-server Enables AI assistants to decode QR codes from images, with tools for scanning full images and enhancing blurry or reflective regions before decoding, plus quality diagnostics to guide retry strategies. | |
| google-ads-mcp eneelkant/google-ads-claude-plugin Enables full read/write control of Google Ads accounts—managing campaigns, ad groups, ads, keywords, Performance Max, budgets, targeting, and performance reporting through natural language. Supports Search, Display, Video, and Demand Gen ca | |
| smart-retail-mcp eneidyscastellano/smart-retail-mcp MCP server that provides predictive inventory analysis tools to AI agents, including current stock, sales velocity, and replenishment alerts. | |
| Power BI Desktop MCP Server enelyse/powerbi-mcp-server Bridges the Model Context Protocol to the Tabular Object Model, enabling natural language inspection, optimization, and authoring of DAX in Power BI Desktop. | |
| MCP-MySQL Server enemyrr/mcp-mysql-server Enables AI models to perform MySQL database operations through a standardized interface, supporting secure connections, query execution, and comprehensive schema management. |
48,051–48,100 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.