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 |
|---|---|
| gmail-mcp-server enoch-sit/gmail-mcp-server A comprehensive MCP server for Gmail, providing 17 tools to read, send, search, and manage emails with OAuth2 authentication, including attachment handling and privacy features. | |
| suanming-mcp enoch666/suanming-mcp A fortune-telling MCP server that generates traditional Chinese-style HTML reports for Ba Zi, Liu Yao, fortune sticks, naming, and a programmer's almanac. | |
| project-planner-MCP enockkipkoech/project-planner-ai-mcp Enables AI assistants like Claude to create and manage projects, todos, priorities, and statuses through natural language, bridging the gap between AI and project management workflows. | |
| Enola enola-labs/enola Enola. is a local Model Context Protocol (MCP) server. A deterministic map of your codebase for AI coding agents — the real architecture, extracted from your source, not guessed. | |
| krackedmaps enonforetsam/krackedmaps Enables creating themed SVG maps, GeoJSON data, projections, React components, and embeddable map builders through natural language requests. | |
| affinity-creative-mcp enoyola/affinity-creative-mcp Enables automation of Affinity Photo, Designer, and Publisher from MCP clients, supporting document creation, layer editing, text replacement, export, and more via safe, validated tools. | |
| MCP Portfolio Server enpalco/mcp-portfolio-server Fetches and normalizes investment portfolio data from eToro and Interactive Brokers (IBKR), enabling AI agents to consolidate, aggregate, and visualize holdings across brokers. | |
| comfy-draftsman enragedantelope/comfy-draftsman The MCP server that drafts ComfyUI workflows a human can actually read. It lets coding agents build, repair, port, validate, and run ComfyUI workflows against your own ComfyUI instance, delivering clean, organized, fully-labeled workflows. | |
| Freshdesk MCP Server enreign/freshdeck-mcp Enables interaction with Freshdesk API v2 to manage support tickets, contacts, agents, companies, and conversations with built-in authentication, rate limiting, and error handling. | |
| productboard-mcp enreign/productboard-mcp Enables AI assistants to interact with your Productboard workspace, allowing features, products, notes, objectives, key results, and releases management. | |
| beacon-mcp enrichgateagent-png/x402-agents x402 agent MCP server (beacon-mcp) exposing tools via Docker + glama.json for introspection. | |
| Enrich Layer MCP Server enrichlayer/mcp-server Provides 25 tools to enrich company, person, contact, school, and job data via the Enrich Layer API, enabling lookups, profiles, and contact discovery. | |
| Zendesk MCP Server enrico90498/zendesk-mcp-server Enables operators to retrieve and manage Zendesk tickets and comments, access Help Center articles as a knowledge base, and generate ticket analyses and draft responses. | |
| mcp-google-oauth enricojam-maker/mcp-google-oauth Enables remote MCP servers with Google OAuth authentication, allowing users to connect and sign in via their Google account. | |
| fathom-mcp-adapter enrique-pastrana/fathom-mcp-adapter Read-only MCP server that exposes Fathom meetings and transcripts as tools for use by skills in the TICKETS workspace. | |
| grafana-mcp-adapter enrique-pastrana/grafana-mcp-adapter Read-only MCP server that exposes Grafana dashboards, datasources, and metric/log queries as tools, for use by skills in the TICKETS workspace. | |
| sysops-mcp enrique-s-j/sysops-mcp An MCP server that gives AI assistants safe, read-only visibility into a host: CPU, memory, disk, processes, network, ports, and logs. | |
| agent-data enrique-z/agentdata-mcp-server Get programmatic access to 170,000+ verified B2B companies in Spain. Featuring a highly-curated premium subset of 26,000+ CEO direct dials and mobile phones. Bypassing legacy corporate gatekeepers has never been cheaper. | |
| mcp-lightrag enriquecatala/mcp-lightrag Enables AI assistants to interact with LightRAG knowledge graphs, supporting smart upsert for Obsidian vaults, semantic queries, and document/graph management. | |
| Playwright MCP enriquedlh97/playwright-mcp Enables browser automation and web page interaction through Playwright's accessibility tree, allowing LLMs to navigate, fill forms, click elements, and extract content without requiring vision models or screenshots. | |
| Enrow MCP Server enrowapi/enrow-mcp Enables AI assistants to find and verify professional emails and phone numbers via the Enrow API. | |
| Taiga Remote MCP Server ens-ray-nguyen/taiga-mcp-remote A remote MCP server for Taiga project management that enables multiple users to connect simultaneously with their own Taiga accounts via OAuth 2.1, providing access to Taiga resources through the Model Context Protocol. | |
| gmail-mcp ensismoebius/gmail-mcp Full Gmail control for any MCP-compatible AI agent. Exposes ~40 tools for reading, composing, labeling, filtering, threading, and account management. | |
| namescope ensp1re/namescope MCP server for evaluating software project name availability across package registries, GitHub, domains, and the command line, with scoring and evidence. | |
| sec-research ensp1re/sec-research-mcp Enables agents and people to run local SEC research queries against EDGAR or demo fixtures, returning verifiable financial data, filing text, charts, and evidence packets with explicit source and coverage. | |
| simplenote-mcp enstw/simplenote-mcp A remote MCP connector that gives Claude.ai projects a persistent, cross-conversation file store, backed by Simplenote and deployed free on Cloudflare Workers. | |
| Video to Shorts Captions ent-e-pro/video-to-shorts-captions Enables MCP clients to turn direct video URLs and chosen start/end times into ready-to-post vertical 9:16 MP4 clips with animated burned-in captions, thumbnails, and SRT files, including batch processing for multiple highlights. | |
| laravel-artisan-mcp entanglr/laravel-artisan-mcp Enables secure execution of Laravel Artisan commands through AI assistants, allowing controlled management of Laravel projects via natural language. | |
| MediaWiki API MCP Server entanglr/mediawiki-api-mcp Enables LLMs to interact with MediaWiki installations as a bot user, supporting page editing, searching, moving, deleting, comparing revisions, and retrieving site information through the MediaWiki API. | |
| iconify-mcp entaytion/iconify-mcp Enables searching, fetching SVG, and discovering icons from Iconify's 200,000+ icon library across 150+ sets. | |
| mcpstrike ente0/mcpstrike MCP server that connects an LLM via Ollama to security tools for autonomous or guided penetration testing from a terminal interface. | |
| autodesk-connector entech-labs/contech-ai Enables Claude Desktop to read live Autodesk Construction Cloud project data—such as RFIs, issues, submittals, cost, members, and documents—through natural-language queries. | |
| html2pptx-mcp enterner/html2pptx_mcp Enables generating native, editable PowerPoint (.pptx) files from restricted HTML through MCP tools for validation, conversion, contract export, and slide-design prompts. | |
| constellation-mcp enternovate/constellation-mcp Exposes the five Enternovate security tools as 23 Model Context Protocol tools, enabling agents to scan attack surfaces, query knowledge graphs, audit websites, check email security, and run POPIA compliance assessments via a single MCP con | |
| Ek-Chuah MCP entheos69/ek-chuah-mcp Read-only MCP server that serves the Archivo Epistemico (epistemic graph), enabling AI to read and query the epistemic path autonomously via tools like search, get_via, resolve, and get_necesidad. | |
| Abacus enthusiasm23/abacus An MCP server for local Excel automation, providing 88 tools for reading, manipulating, and analyzing Excel files. It supports .xlsx, .xls, and .csv formats, with a unique nine-chapter classification system. | |
| empresa-mcp-demo entiemen/empresa-mcp-demo Demonstration MCP server for Claude Team integration, enabling querying of sample business data (orders, clients, products) and real-time currency exchange rates through natural language. | |
| ArchiMate MCP Server entira/archi-mcp Enables generation of PlantUML ArchiMate enterprise architecture diagrams with full ArchiMate 3.2 specification support across all 7 layers, including automatic validation, multi-format export (PNG/SVG/XML), and instant diagram viewing thro | |
| sdrpp-mcp entitledosprey/sdrpp-mcp Enables an MCP client to drive a running SDR++ instance to discover, analyze, identify, demodulate, record, decode, and log radio signals. | |
| claude-tiktok-mcp entity02/claude-tiktok-mcp Enables Claude to query a TikTok account on demand, retrieving profile information, recent videos, today's videos, and detailed video statistics. | |
| entra-mcp entracareers/entra-mcp Enables AI agents to search verified tech and AI jobs, match resumes to roles with explainable fit scores, retrieve salary statistics, and prepare human-in-the-loop applications via the ENTRA job platform. | |
| @dm2233/agent-data-mcp entreprisedaney33-rgb/agent-data-mcp An MCP server that enables AI agents to verify facts, check market and on-chain data, search the web, and run AI text tasks through five general-purpose tools, with pay-per-call USDC settlement on Base via x402 and no API key required. | |
| Web Icons Generator CLI MCP entro314-labs/web-icons-generator-cli-mcp Generates all required web app icons and manifest files from a single source image with framework auto-detection. Supports Next.js App Router, traditional web apps, and PWA standards with zero configuration. | |
| Data Product MCP entropy-data/dataproduct-mcp Enables AI agents to discover, request access to, and query data products in Data Mesh Manager, enforcing governance policies while retrieving business data from platforms like Snowflake and Databricks. | |
| consensus-mcp entropyvortex/ai-consensus-mcp An MCP server that enables multi-model debate and consensus building through a single tool. It orchestrates multiple AI models from various providers to debate topics and reach validated conclusions with real-time progress tracking. | |
| askgrokmcp entropyvortex/askgrokmcp Brings xAI's Grok API into Claude Code as native tools, enabling chat, image generation, model listing, and multi-round consensus/validation analysis. | |
| entroute entroute/web-search-agent Enables web search for AI agents with pay-per-search in USDC, no API keys needed. | |
| RPG Maker MZ MCP Server enushin/rpg-maker-mz-mcp Enables creating RPG Maker MZ games using natural language through AI assistance, with tools for project management, map creation, event systems, and batch operations. | |
| env0 env0/mcp-server Enables AI agents to manage environments and access resources on the Env0 platform through natural language, including deploying, canceling, and viewing logs of environments, as well as querying Cloud Compass. | |
| EnvarPay envarai/envarpay Enables agents to sell MCP tools and Hermes capabilities behind an x402 v2 / USDC payment gate, and to buy other agents' capabilities through a wallet tool. Sellers quote a price, verify the exact transfer and nonce, then execute, while buy |
48,201–48,250 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.