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 |
|---|---|
| claude-usage-guard ecerutti/claude-usage-guard An MCP server that exposes Claude Code's real-time rate limit usage so that an orchestrator can check remaining capacity before launching subtasks. | |
| Yolfi MCP Server eceyadav502/yolfi-agent Enables AI coding agents to add stablecoin checkout, payment links, payment status checks, webhook verification, and webhook-based access logic to applications. | |
| database-mcp-server echatzief/database-mcp-server A Model Context Protocol (MCP) server that provides database operations as tools for LLM-powered applications. Supports PostgreSQL, MySQL, and MongoDB databases with connection pooling and flexible result formatting. | |
| Instagram DM MCP server echaudhry41/instagram_dm_mcp Enables sending Instagram Direct Messages and managing DM threads from a connected account, including text, photo, and video messages, listing chats and messages, downloading media, searching users/threads, and retrieving user, story, follo | |
| Vectorize MCP Server echaudhry41/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking into Markdown, and private deep research through Vectorize pipelines. It integrates with MCP clients like Claude, Windsurf, Cursor, and Cline for natural-language ac | |
| Browser Control echelon-agents-ai/browser-control Enables AI agents to drive a real headful Chrome browser using vision-first computer interactions, with support for multi-agent tab groups, password-manager-filled logins, and human handoff. | |
| ServiceNow MCP Server echelon-ai-labs/servicenow-mcp An implementation that enables Claude to connect to ServiceNow instances, retrieve data, and perform actions through the ServiceNow API. | |
| @runehand/mcp-server echelonlabs-sf/runehand-mcp MCP server that wraps the Runehand API v1 as tools, enabling users to operate Runehand bots directly by listing bots and flows, reading and replying to conversations, managing leads, and checking analytics. | |
| Echo MCP launcher echo-browser-for-ai/echo Enables AI agents to drive a local Chromium browser through MCP, with persistent sessions, one-click registration across supported AI apps, and CDP/Playwright-based control. | |
| Booru-Pictag-Get-MCP echo-xianyu/booru-pictag-get-mcp An MCP server that searches booru image boards and cleans their tags into ready-to-use AI-art prompts for Stable Diffusion and similar models. | |
| Danbooru Search MCP echo-xianyu/danbooru-mcp Searches Danbooru for anime/game characters and their associated tags, providing tools to retrieve character profiles, co-occurring tags, wiki descriptions, and tag implications. | |
| echo3s-io echo3s-io/echo3s-mcp AI-powered multi-voice audiobook creation platform. Provides tools for pricing, language support, use cases, onboarding, FAQ, alternatives comparison, and cost estimation. npx echo3s-mcp | |
| reaper-mcp-bridge echo722/reaper-mcp-bridge Enables MCP-capable AI agents to control REAPER through typed tools and a Lua escape hatch for project creation, track management, recording and editing, MIDI writing, mixing, rendering, and batch operations. | |
| Constancy MCP echo983/constancy-mcp Provides long-term memory for AI agents through time-decay validity scoring, so stored facts, notes, and entities are automatically forgotten or flagged as stale instead of being recalled forever. Enables logging high-signal memories, searc | |
| @echobt/figma-mcp echobt/figma-mcp Enables offline reading and rendering of Figma .fig files, allowing AI agents to extract design specs, export assets, and generate code without needing the Figma API or network access. | |
| garmin-connect-mcp-server echocharlie/garmin-connect-mcp-server A read-only MCP server that gives Claude Desktop access to your Garmin Connect data — daily health metrics, sleep, activities, training status, and body composition. | |
| Oura MCP Server echocharlie/oura-mcp-server Provides read-only access to Oura ring biometrics via the Oura API, enabling Claude to query daily summaries, sleep, readiness, stress, workouts, baselines, and heart rate data. Designed to complement a Strava connector for joint analysis o | |
| coder-worker-mcp echocolate-agent/coder-worker-mcp Enables MCP clients to securely execute bounded coding tasks through registered backends, with idempotent job submission, status polling, and artifact retrieval. It isolates each job in Git worktrees and supports optional branch publishing | |
| agent-mcp echodeveloperio/agent-mcp Enables collaborative software development through a team of specialized AI agents (Architect, Developer, Reviewer, Tester) communicating via the Model Context Protocol, with tools for file management, task tracking, and code review. | |
| Echoes MCP Server echoes-io/mcp-server Enables AI integration with the Echoes storytelling platform, providing narrative knowledge graph extraction, semantic search, and arc isolation. | |
| cat-hotel-mcp echoes0302/cat-hotel-mcp A text-based cat hotel management game for AI, where you act as a temporary manager to care for cat customers through MCP tools. | |
| discord-mcp echohello-dev/discord-mcp Enables AI assistants to interact with Discord guilds, channels, messages, threads, members, roles, webhooks, and DMs through a focused set of tools. | |
| jev-mcp-server echohello-dev/jev-mcp Enables coding agents to verify claims, classify states, screen content, make decisions, and extract fields using five judgment tools backed by TypeSafe/OpenRouter. | |
| linkedin-mcp echohello-dev/linkedin-mcp Lets MCP clients sign a member in through LinkedIn's three-legged OAuth flow, read that member's OpenID profile, and publish text posts on their behalf, with stored sessions kept in a local mode-0600 file. It uses only public member APIs, s | |
| agent-market-signals echolonius/boardcheck An MCP server that provides tools to audit AI-agent marketplace integrity by scanning listings for deceptive patterns like fabricated engagement, automated seeding, self-advertisement, unpaid work risk, and high-budget bait. | |
| mcp-app echomodel/mcp-app Framework for building and running MCP servers as HTTP services. Define tools as pure Python functions, wire up with two lines, run with one command. | |
| Hearth echoo19/hearth AI-native open-source 2D game engine whose MCP server exposes every editor operation to coding agents as typed commands, so an agent can build, run, and verify a game inside the editor. It runs locally on macOS, Windows, and Linux with no c | |
| Echo Vault echoomegaprime/echo-credential-broker Enables agents to securely use credentials for GitHub, Cloudflare, OpenAI, Stripe, and xAI without ever reading the secret values, including credential health, rotation, and audit features. | |
| Echo QCoder echoomegaprime/echo-qcoder Governs and manages Qwen Code builder sessions with tools for previewing, starting, inspecting, queuing tasks, and stopping sessions, all within a scoped, redacted environment. | |
| Echo RunPod echoomegaprime/echo-runpod Governed RunPod control plane for ECHO OMEGA PRIME, providing agent entry points with confirmations and manifest policies. Enables authorized agents to observe, prepare, and execute RunPod operations via MCP scopes. | |
| Echoteka MCP echoteka/echoteka-mcp Enables MCP clients to measure a track's loudness and peak levels, strip artifacts left by AI generators, compare mastering presets, and master single tracks or batches to streaming targets via a hosted remote server or a local stdio bridge | |
| blade-computer-use echovic/blade-computer-use Enables MCP clients to control macOS via accessibility and screen recording, providing tools to list apps, observe UI, click, type, press keys, and scroll. | |
| Mermaid Chart MCP echovic/mermaid-chart-mcp A powerful Model Context Protocol server that automatically generates Mermaid diagrams from code and provides SVG beautification features. | |
| Figma MCP Tool echoxiawan/figma-mcp-full-server Enables interaction with Figma designs through the Figma API, allowing users to export images in multiple formats, extract style data and CSS, analyze design elements, and retrieve SVG code from Figma files. Supports batch operations and co | |
| idealo MCP auth proxy echsecutor/idealo-proxy Lets Cursor use the official Idealo MCP server through a local stdio bridge, handling OAuth authentication with an allowed redirect callback. | |
| yt2md echtelerp/yt2md Provides Claude with tools to retrieve YouTube transcripts, list available transcripts, and read transcript files as Markdown, enabling natural-language requests to download and summarize video content. | |
| Research Insights MCP Server ecidk/mcp-research-insights Supercharge Claude Desktop with bulk analysis of 1500+ user research calls, validation workflows, and Signal export capabilities. | |
| toolcargo-demo eclipseagency/toolcargo-demo Enables AI assistants to perform read-only website audits, search literature databases, and inspect Python packages through MCP connectors, using offline fixtures by default or live public APIs. | |
| twitch-mcp eclipsevr-live/twitch-mcp This project is a fork and expansion of TomCools' Twitch MCP Server, which implements a Model Context Protocol (MCP) server that integrates with Twitch chat, allowing AI assistants like Claude to interact with your Twitch channel. | |
| Twitch-MCP-Smithery eclipsevr-live/twitch-mcp-smithery A comprehensive Twitch MCP (Model Context Protocol) server providing chat moderation, stream management, and Twitch API integration for AI systems. | |
| vcctrl-mcp ecliptik/vcctrl Enables MCP clients to remotely control a real retro or legacy computer, including keyboard and mouse input, video capture, audio, power cycling, and file transfer, so agents can run tests against physical hardware. | |
| Aspen Catalog MCP ecmulli/aspen-catalog-mcp Enables AI clients to search Aspen Discovery library catalogs and check real-time book availability by keyword, author, or ISBN. This server allows users to verify local library inventory and filter book recommendations accordingly. | |
| Game World Sandbox MCP ecnu3d/game-sandbox-mcp Enables creation and management of structured game worlds for text adventures and RPGs with character creation, world generation, and natural language interaction through AI integration. | |
| Universal Image Generator MCP Server ecnu3d/universal-image-generator-mcp A multi-provider AI image generation server that allows users to create and transform images using Google (Imagen & Gemini), ZHIPU AI CogView-4, or Alibaba Bailian through any MCP-compatible application. | |
| Ecological Provisioning MCP Server eco-wealth/ecological-provisioning-agent A local-first MCP server stub that exposes provisioning tools for converting ecological intent into work packets, proof plans, receipts, and validation workflows. | |
| ecoclaw-mcp ecoclaw/ecoclaw-mcp Manages local AI skills for Claude Desktop, enabling listing, running, tuning, forking, contributing, and updating skills stored as markdown files. Customizations are persistent and survive updates. | |
| astrondesign ecokg/astrondesign Enables AI agents to build and audit web UIs by serving a fixed workflow and rule-priority guide, running deterministic static linting of source, rendering pages headlessly at multiple widths for screenshots and accessibility snapshots, and | |
| AmzDownloader MCP ecom-crawl/amzdownloader-mcp Enables AI clients to start and monitor Amazon product extraction jobs, retrieve cached product media, convert Amazon playlist videos to MP4, and check account usage through a hosted MCP endpoint or local stdio bridge. | |
| com.gladeapi/api ecom-crawl/gladeapi-mcp Provides read-only access to normalized Amazon marketplace data, including product details, search, offers, reviews, sellers, categories, deals, best sellers, identifiers, stock, and sales estimates across 13 marketplaces. | |
| Vercel MCP Relay Server econ-watch/mcp Enables AI assistants to interact with the Vercel REST API to manage projects, deployments, domains, environment variables, and teams through natural language commands. |
46,851–46,900 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.