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 |
|---|---|
| 1Money Network MCP 1money-co/1moneynetwork-mcp MCP server for the 1Money Network Protocol, providing tools to interact with accounts, tokens, transactions, checkpoints, chain, and utility functions like signing and address derivation. | |
| PwnBridge 1mr0-tech/pwnbridge Enables AI assistants to execute security testing tools on a Kali Linux machine over SSH, including reconnaissance, web app scanning, and static/dynamic analysis. | |
| 1msg MCP 1msg/1msg-mcp Enables interaction with the 1msg Chat API through 60 public MCP tools, supporting stdio and hosted HTTP transports. It lets users leverage chat API functionality in Cursor, Claude Desktop, and other MCP clients. | |
| MCP Integration Suite Server 1nbuc/mcp-integration-suite Enables interaction with SAP Integration Suite for designing, creating, and managing integration artifacts including integration flows, message mappings, packages, and B2B trading partner relationships through AI-powered natural language co | |
| aeo-graph-engine 1nc0gn30/aeo-graph-engine Enables AI agents to crawl live websites, audit AEO readiness, generate Schema.org @graph JSON-LD, llms.txt, ai.txt, and robots.txt, inject structured data into HTML, validate optimizations, and retrieve framework-specific code snippets. | |
| cwv-speed-engine 1nc0gn30/cwv-speed-engine Enables AI agents to audit Core Web Vitals, transform HTML for speed, generate PWAs, and export performance configurations via the Model Context Protocol. | |
| deepsearch-research-agent 1nc0gn30/deepsearch-research-agent Enables autonomous multi-perspective deep research, evidence harvesting, and verified report synthesis with confidence scoring, directly from MCP-compatible clients. | |
| envguard 1nc0gn30/envguard-secrets-vault Enables AI agents to scan and audit environment files for leaked secrets, sanitize them, encrypt/decrypt vaults, and run processes with zero-disk secret injection. | |
| nexus3d 1nc0gn30/nexus-3d-scene-studio Enables AI agents to procedurally generate, transform, inspect, and export 3D meshes and scenes through MCP tools. | |
| omnipost-social-engine 1nc0gn30/omnipost-social-engine Enables AI agents to manage social media posts across multiple platforms by scoring virality, generating threads, converting formats, optimizing hooks, scheduling campaigns, and validating platform limits. | |
| subsweep-recon 1nc0gn30/subsweep-lead-scanner Enables AI assistants to perform live subdomain enumeration, passive DNS OSINT, technology stack profiling, port scanning, and B2B lead harvesting directly from chat. | |
| vision-gesture-control 1nc0gn30/vision-gesture-control Enables AI agents to access real-time touchless gesture recognition, 3D hand landmarks, virtual key event injection, facial telemetry, sensitivity adjustment, and system health diagnostics through the Model Context Protocol. | |
| web-security-guard 1nc0gn30/web-security-guard Enables AI agents to audit URLs for security headers, generate CSP Level 3 policies, compute SRI hashes, evaluate WCAG 2.2 contrast, and remediate headers. | |
| reading-cottage 1nwooozip/reading-cottage Enables local EPUB reading with AI agents, supporting annotations, parallel editions, and MCP tools. | |
| Agent Guard 1of1canopus/agent-guard Authorization, human approval, audit trail and budgets for Spring AI agents and MCP servers. Spring Boot starter, on Maven Central. | |
| MCP Servers for QA and Release Coordination 1olegshev/mcp-servers A collection of MCP servers for Slack, Jira, Confluence, and release coordination to automate QA workflows and daily release status reporting. | |
| MCP Memory Server 1ooyan/mcp-memory Enables AI assistants to store and retrieve long-term memories with semantic search, supporting various memory types and tags via PostgreSQL and pgvector. | |
| z_ai_vision_mcp_server_clone 1orzero/z_ai_vision_mcp_server_clone OpenAI-compatible MCP server for running image analysis tools against your own vision model endpoint. | |
| mcp-1panel 1panel-dev/mcp-1panel 1Panel MCP Server is an implementation of the Model Context Protocol (MCP) server for 1Panel. | |
| android-rpa 1parado/android-rpa Enables MCP-compatible AI agents to perceive and control an Android phone through tools for screenshots, visible text and coordinates, app/screen queries, taps, swipes, text input, key events, app launching, and interrupt/resume, closing th | |
| xmind-mcp 1parado/xmind_mcp Enables AI agents to create, read, convert, validate, and render .xmind mind maps, including PNG/SVG/HTML output and compatibility with the official Xmind client. | |
| Flashlight 1percentsync/flashlight Enables whole-codebase code search using natural language queries by leveraging DeepSeek's 1M context window. Automatically shards large projects and utilizes prefix caching for cost-effective repeated searches. | |
| juvina-mcp 1picassoai/juvina-mcp Bridges stdio MCP clients to the locally installed Juvina memory engine, enabling persistent local AI memory for coding assistants. | |
| OnePlatform MCP Server 1platformlabs/oneplatform-mcp Enables code agents to search platform documentation and perform permitted API operations using their own keys, defaulting to QA. It supports read-only account data and payment-link creation or cancellation while excluding administrative, c | |
| visualgen-mcp 1raghavm/visualgen-mcp An MCP server that enables Claude Code to generate images and short videos using Google's Gemini API (Imagen 4 for stills, Veo 3.1 for video). It integrates directly into development workflows, allowing AI assistants to create visual assets | |
| MongoDB MCP Server 1rb/mongo-mcp A protocol server that enables LLMs like Claude to interact with MongoDB databases, providing tools for schema exploration, aggregation queries, and data analysis through natural language in Cursor. | |
| Labellerr MCP Server 1sarthakbhardwaj/labellerr-mcp-server A Model Context Protocol (MCP) server that provides a comprehensive interface to the Labellerr SDK for managing annotation projects, datasets, and monitoring operations through AI assistants like Claude Desktop and Cursor. | |
| Domain Availability MCP Server 1shanra1/domain-checker-mcp Enables checking domain name availability for .com, .ai, and .net TLDs using WHOIS, DNS, and RDAP lookups. | |
| ya-frida-mcp 1shin-7/ya-frida-mcp A comprehensive MCP server for Frida dynamic instrumentation, enabling AI agents to manage devices, processes, scripts, memory, and ADB operations. | |
| kubeaid-mcp 1shubham7/kubeaid-mcp-ts Exposes a Kubernetes cluster to MCP-compatible AI clients, enabling read-only and optional write operations on cluster resources like pods, deployments, and namespaces through natural language. | |
| dsh-unity-mcp 1shuqing/dsh-unity-mcp-authfix Lets DeepSeek Harness AI agents directly control the Unity Editor through 34 tools for scene, GameObject, asset, prefab, menu, testing, and console operations, with automatic token authentication and connection management. | |
| ER:LC MCP 1sidplayer/er-lc-mcp Connects an ER:LC private server's API to MCP clients so users can read live players, locations, vehicles, staff, queues, logs, bans, and emergency calls, and send remote server commands. It covers API v2 with v1 compatibility, structured e | |
| GoogleMCP 1solomonwakhungu/googlemcp Gives an MCP client scoped, read-only-by-default access to your own Google account across Workspace apps and other Google APIs including Gmail, Calendar, Drive, Tasks, YouTube, Search Console, Analytics, and Photos. Runs locally over stdio | |
| fiverr-phantom-mcp 1st-anomaly/fiverr-phantom Enables AI assistants to manage Fiverr seller profiles, update bios and taglines, bulk-add skills, and check session status through stealth automation. | |
| Agent Handoff Bridge 1ststepai/agent-handoff-bridge Enables supervised task handoffs among Codex, an OpenAI Dot, and six STP Grok Bots with separate credentials, atomic task claiming, owner approval for agent-created dispatches and completions, and an append-only audit history. | |
| NexonCo MCP 1sustgmboab/nexonco-mcp An advanced Medical Care Platform server designed for accessing and analyzing clinical evidence data to support precision medicine and oncology research. | |
| Sairen 1tylermitchell/sairen_mcp Provides remote SSE-based computational infrastructure with 40+ deterministic tools, including free utilities like JSON repair and context trimming, plus pay-per-call web3 and network oracles for autonomous AI agents. | |
| XiaoHongShu MCP 1uokun/xiaohongshu-mcp-js Enables AI agents to publish content to XiaoHongShu (Little Red Book) social platform, including checking login status and posting with titles, content, images, and hashtags through browser automation. | |
| confluence-mcp 1vecera/confluence-mcp A Confluence MCP server optimized for AI agents, enabling surgical section edits, fast page tree downloads, smart image handling, and more. | |
| evoctl 1vecera/evoctl Enables AI agents to interact with an Evolution API deployment through three MCP tools for discovering operation schemas, reading chats/messages/status, and performing sends, pairing, or permitted admin actions over local, HTTP, HTTPS, or S | |
| domin8 1withall/domin8 A deterministic MCP server that enforces auditable workflows by requiring AI agents to provide structured justifications and obtain human approval for file operations. It provides a secure, tamper-evident pipeline for tracking agent intent | |
| codex-mcp-agent 1worldcapture/codex-as-mcp Enables Claude Code, Cursor, and other AI tools to call OpenAI Codex for task execution, with safe and writable modes. | |
| mcp-hello-test 1xkuson/mcp-hello-test A minimal MCP server with greet, add, and whoami tools, designed to validate deployment pipelines and environment variable injection. | |
| Figma MCP Server 1yhy/figma-context-mcp A Model Context Protocol server that integrates Figma design files with AI coding tools like Cursor, Windsurf, and Cline, allowing AI tools to access and understand Figma design data for generating more accurate code. | |
| OSS MCP Server 1yhy/oss-mcp A Model Context Protocol server that enables large language models to upload files directly to Alibaba Cloud Object Storage Service (OSS), supporting multiple OSS configurations and specified upload directories. | |
| Front Desk 1zaia/front-desk Enables small businesses to manage appointments through natural-language voice commands, including listing services, checking free times, booking, canceling, rescheduling, and viewing daily summaries with structured data and spoken response | |
| GPT-GitHub Bridge 20001025hx-ui/gpt-github-bridge Bridges ChatGPT to GitHub with full write access, enabling repository management, file operations, and pull request creation. | |
| task-manager-mcp 2000sister/xx-task-mcp Enables AI to directly manage tasks, tags, categories, and projects in the xx-task desktop app's SQLite database, offering full CRUD operations through MCP tools. | |
| idm-mcp 2000teddy/idm-mcp Enables monitoring and control of IDM Navigator 2.0 heat pumps via Modbus TCP. | |
| cisco-pt-mcp 2001sithum/cisco-pt-mcp Enables AI clients like Claude Desktop and Cursor to control Cisco Packet Tracer through natural language, including generating network topologies, running device configurations, and managing simulations. |
21,901–21,950 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.