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 |
|---|---|
| gemini-cortex-mcp atknony/gemini-cortex-mcp An MCP server that delegates tasks to Google Gemini, enabling live web search, video/audio understanding, and summarizing large files. | |
| UK Government Technology Standards MCP Server atksz98/mcp Provides AI assistants with access to 102 curated UK Government technology standards, enabling context-aware recommendations for accessibility, APIs, security, cloud strategy, and more. | |
| Atla atla-ai/atla-mcp-server The Atla MCP Server provides a standardized interface for LLMs to interact with the Atla API for state-of-the-art LLMJ evaluation. | |
| mcp-gitlab atla-digital/mcp-gitlab Fork with more tools and streaming http | |
| sophos-central-mcp atlan-it-masters/nc_sophos-central-mcp Read-only MCP server for Sophos Central that provides endpoint health, firewall inventory, switch settings, and email quarantine inspection through natural language queries. | |
| worksection-mcp atlantdak/worksection-mcp Enables MCP-capable clients to drive Worksection projects, tasks, subtasks, comments, tags, people, time tracking, files, search, and reporting through a consistent set of tools over stdio. | |
| aliyun-bailian-balance atlantisgq/aliyun-bailian-balance-codex Enables users to view Alibaba Cloud account balances, credit limits, and cash voucher status through a persistent Codex panel or natural-language queries using read-only BSS OpenAPI access. | |
| Atlas atlas-compiler/atlas Atlas helps AI agents understand and use information from the web without token bloat or hallucinations. It transforms messy web pages, SPAs, and documentation into clean, structured Markdown and JSON, providing powerful tools for deep comp | |
| atlasopenmagic-mcp atlas-outreach-data-tools/atlasopenmagic-mcp MCP server for ATLAS Open Data that enables LLMs to discover, query, and retrieve public datasets and metadata from the ATLAS experiment at CERN. | |
| Cloudflare Playwright MCP atlas-realty-group/playwright-mcp Enables AI assistants to control a browser through Playwright tools, allowing web automation tasks such as navigation, clicking, typing, and screenshots. | |
| research-mcp atlas-rwa/research-mcp MCP server exposing ATLAS research capabilities: live tokenized stock market data, on-chain source-of-truth reads, and published research atlases. Connects to MCP clients over stdio with no API keys required for public testnet endpoints. | |
| Shade Browser Security MCP atlas-x-ai/shade-browser-security Standalone MCP server exposing only the security-classified tools from Shade Browser, enabling Brave CDP browser automation across 20 isolated profile slots. Built on FastMCP and Playwright Python. | |
| Atlas Cloud MCP Server (Image / Video / LLM APIs) atlascloudai/mcp-server Atlas Cloud MCP Server enables developers to access state-of-the-art AI models for image generation, video generation, and LLMs through a unified MCP interface. Fast, scalable, and cost-efficient alternative to traditional AI providers. | |
| Claude MCP Slack atlasfutures/claude-mcp-slack Enables secure downloading and access to Slack files and images using authenticated Bot User OAuth tokens. Integrates with Claude Code Action to allow Claude to analyze screenshots and files shared in Slack channels. | |
| ALA API MCP Server atlasoflivingaustralia/ala-mcp Enables interaction with the Atlas of Living Australia API to search and access 152+ million biodiversity records. Supports occurrence searches, spatial queries, bulk data downloads, and taxonomic data retrieval through natural language. | |
| mcp-compressor atlassian-labs/mcp-compressor A proxy server that wraps existing MCP servers to significantly reduce token consumption by compressing tool descriptions into a two-step interface. It enables users to integrate extensive toolsets without exceeding context limits or incurr | |
| mcp-ssh atlcomgit/mcp-ssh Enables secure SSH connections to remote servers for executing shell commands and managing active sessions. It supports authentication via passwords or private keys and provides optional host-based access control. | |
| AgileWorks MCP Server atled-workflow/agileworks-mcp-server This MCP server provides tools to interact with the AgileWorks business process platform via its Web API, enabling document management, workflow operations, user administration, and more. | |
| @lisp MCP Server atlisp-org/mcp-server Enables AI agents to control AutoCAD, ZWCAD, GStarCAD, and BricsCAD through 340+ tools for drawing, editing, querying, package management, and automation. | |
| open-memory atmakurakhil/open-memory Exposes a local SQLite-backed long-term memory to AI agents as MCP tools, letting them add conversations and documents, record dated facts with provenance, search and assemble context, and edit, inspect, or forget what was stored. It runs w | |
| SEO Analytics MCP Server atmarcday/seo-mcp Enables querying Google Analytics 4 traffic, engagement, and conversions, as well as Google Search Console performance, index status, and sitemap management. | |
| Agent Tools atmaticai/agent-tools Provides deterministic tools for transforming, formatting, and inspecting structured data for AI agents. | |
| agentshield-mcp atmflow55/agentshield-mcp Real-time smart contract security for autonomous AI agents, offering tools for contract verification, wallet monitoring, drain detection, threat reporting, and leaderboards. | |
| MachineElf atmic/machineelf Routes urgent alerts from autonomous AI agents to human operators with idempotency and strict JSON schemas. | |
| knowledge-base atmos-10x/knowledge-base-plugin Enables agents to search, read, list, and amend a git-backed markdown knowledge base, automatically committing and publishing changes. | |
| AdvisorPPC X Ads MCP Server atmosphere-ai/advisorppc-x-ads Enables MCP clients to manage X/Twitter advertising campaigns, ad groups, audiences, pixels, and creative assets via the Ads API v12, with safety defaults like paused writes and explicit confirmations for spend and deletions. | |
| AdvisorPPC X Organic atmosphere-ai/advisorppc-x-organic Enables policy-safe organic X/Twitter community management through MCP, including posting, threads, replies, inbox/DM handling, media uploads, and engagement actions with confirmation safeguards. | |
| Knowledge Server atnguyen143/mcp Provides LLM-agnostic access to API documentation through MCP and REST endpoints, enabling AI assistants to retrieve, search, and proxy requests to whitelisted APIs across multiple platforms. | |
| normativa-andalucia ato097/mcp_boja Enables searching, retrieving, and reading the full text of Andalusian regional legislation published in the BOJA, including laws, decrees, and resolutions, through natural language queries. | |
| symapse atobouh/symapse Provides code analysis tools for AI coding agents to understand project architecture, search for symbols, and plan changes with token reduction. | |
| FreeCAD MCP atoi-ming/freecad-mcp An MCP server that enables automation of FreeCAD model creation, macro execution, and view management through a server-client architecture, supporting integration with external AI tools like Claude and Cursor. | |
| Drin MCP Server atom00blue/drin-mcp Enables MCP-capable agents to send, receive, and manage email, including domains, inboxes, contacts, templates, webhooks, and delivery metrics, through the Drin API. | |
| MCP Server for iOS Simulator atom2ueki/mcp-server-ios-simulator A bridge between iOS simulators and the Model Context Protocol, enabling programmatic control of iOS simulators through standardized communication interfaces. | |
| Synology MCP Server atom2ueki/mcp-server-synology Enables AI assistants to manage Synology NAS devices with file operations (create, delete, move, search) and Download Station control through secure authentication and session management. | |
| Theneo MCP Server atombreak/theneo-mcp Enables AI assistants to automatically create, update, and publish API documentation through Theneo's platform. Supports OpenAPI specs, Postman collections, AI-powered description generation, and natural language interactions for seamless d | |
| Garmin Agent Tools atomchung/garmin-agent-tools Enables a personal agent to read selected live Garmin Connect activity, readiness and device fields and, only after explicit approval of an exact preview, to create, schedule and request device synchronization of one fixed 20-minute running | |
| ib-async-mcp atomcp-ai/ib-async-mcp MCP server for Interactive Brokers API, enabling account management, trading, market data, options, scanners, and news via natural language. | |
| polygon-mcp atomcp-ai/polygon-mcp Enables querying real-time and historical financial market data for stocks, options, forex, and crypto, including quotes, trades, technical indicators, and reference data through a set of MCP tools. | |
| MCP Ollama Consult Server atomic-germ/mcp-consult Enables consulting with local Ollama models for reasoning from alternative viewpoints. Supports sending prompts to Ollama models and listing available models on your local Ollama instance. | |
| Optimist MCP Server atomic-germ/mcp-optimist An intelligent code optimization MCP server that analyzes and improves codebases across multiple dimensions including performance, memory, code smells, and complexity. | |
| mcp-resonance atomic-germ/mcp-resonance Monitors and analyzes interactions between MCP servers to detect emergent patterns, visualize coupling relationships, and suggest optimal next actions based on system coherence and resonance state. | |
| MCP X-Platform atomic-germ/mcp-x-platform Analyzes codebases for cross-platform compatibility issues, detecting platform-specific APIs, file path problems, line ending inconsistencies, and shell command incompatibilities across Windows, macOS, and Linux. | |
| renode-mcp atomicdog/renode-mcp Enables MCP clients to launch, control, and inspect headless Renode emulations via its telnet monitor, including loading scripts, running or pausing execution, accessing system-bus memory, and capturing UART output. | |
| leads-mcp atomicintuition/leads-mcp- Lead generation MCP server for AI agents. Find emails, verify contacts, enrich profiles, and search prospects using Hunter.io, Apollo.io, and Abstract API. | |
| Jiji MCP atomicman57/jiji-mcp Enables extension-free sign-in to a marketplace and gives AI agents tools for searching and paginating listings, comparing sellers and asking prices, reading inbox conversations, and preparing owner-approved seller messages with a WhatsApp | |
| duet-mcp atomicmbag/duet-mcp Enables an AI assistant such as Claude to operate a Duet machine (RepRapFirmware) over LAN/WLAN by reading status, managing files, viewing camera snapshots, homing axes, and starting or supervising prints while enforcing safety approvals an | |
| bsky-mcp atomicnixon/bsky-mcp Remote MCP server giving Claude-family agents credential-isolated access to Bluesky/ATProto via a self-hosted PDS, with read triage, search, and write tools (posts, replies, likes, reposts, follows) governed by policy ceilings and consent. | |
| mcp-searxng atomlong/mcp-searxng An MCP server that integrates the SearXNG API for web search and URL content extraction with advanced features like pagination, caching, and proxy support. | |
| mcp-weather-plus atomlong/mcp-weather-plus Provides real-time weather forecasts, air quality data, and timezone information via Open-Meteo API, with no API key required. | |
| chatgpt-image-bridge-mcp atomtanstudio/chatgpt-image-bridge-mcp Enables text-only agents to generate, edit, and analyze images through a signed-in ChatGPT/Codex account, saving to project assets and returning visual findings as plain text. |
31,551–31,600 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.