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 |
|---|---|
| aiarchitect-blog-mcp aiarchitecturedev/aiarchitect-blog-mcp Provides read-only MCP tools to search and retrieve articles from the AI Architect Korean tech blog, covering topics like MCP, AI agents, and enterprise architecture. | |
| manifestation-mcp aiarghya1/manifestation-mcp Enables coding agents to design first by interviewing users, refining specs in digestible chunks, producing bite-sized TDD plans, and autonomously executing them through subagents with a server-verified red/green testing gate. | |
| Personal Task Manager MCP aiarghya1/personal-task-manager-mcp Enables AI assistants to manage tasks with full lifecycle support including due dates, priorities, tags, subtasks, and project lists via 19 SQLite-backed MCP tools. | |
| Barnsworthburning MCP aias/barnsworthburning-mcp A Model Context Protocol server that enables searching content from barnsworthburning.net directly through compatible AI clients like Claude for Desktop. | |
| Context7 MCP Clone aiatamai/atamai-mcp Provides up-to-date, version-specific documentation and code examples for software libraries directly to LLMs, enabling resolution of library identifiers and retrieval of relevant documentation with code snippets. | |
| LAX MCP Server aiautomationagentesting/genesis-lax-mcp-prototype Enables clients to search agents, retrieve offers, inspect jobs, and submit applications through a registry-backed MCP server, with input validation and no automatic write retries. | |
| mcplocal aiautotool/mcplocal Local Files MCP server that lets MCP-compatible clients read, search, and modify files inside a sandboxed directory. Provides file management and coding workflow tools with security controls like path boundary enforcement and disabled delet | |
| Badgr — GPU Compute for AI Agents Copy aibadgr/badgr-mcp Badgr lets AI agents launch GPU workloads, deploy inference endpoints, run models and execute AI workflows through MCP. Route workloads to available compute, track execution and costs, and retrieve verified results without managing GPU infr | |
| whatsapp-local-mcp aibe13/whatsapp-local-mcp Enables Claude to read and search WhatsApp messages, transcribe voice notes, and analyze images locally through a read-only bridge. | |
| Mine AI MCP aibengineering/mine-ai-mcp Provides external AI agents with reliable, observable tools to inspect, navigate, and act in a Minecraft world, enabling autonomous playthroughs such as beating the game. | |
| oferty-spike-mcp aibiz-automatyzacje/oferty-spike-mcp Enables testing an MCP v2 streamable HTTP server protected by Supabase OAuth 2.1, including Dynamic Client Registration, consent flow, and token-based identity verification for Claude clients. | |
| Open Computer Use aibo204/dsh-plugin-computer-use Enables AI agents to observe and control the user's live desktop by listing apps, reading accessibility trees, and performing clicks, typing, scrolling, dragging, and other input actions with per-action approvals and local audit archives. | |
| @eustore/mcp-server aibollingmo/eustore-mcp-server Enables AI agents to autonomously provision, pay for, and manage S3-compatible storage and vector databases without human intervention. | |
| AgenticRAG MCP Server aibozo/agenticrag-mcp An intelligent codebase processing server that provides agentic RAG capabilities for code repositories, enabling semantic search and contextual understanding through self-evaluating retrieval loops. | |
| stacks-mcp-server aibtcdev/stacks-mcp-server Enables AI assistants to interact with the Stacks blockchain, including account generation, balance checks, network status, block/transaction info, and API status. | |
| AI Coach MCP Server aic0t/ai-coach-mcp Enables Claude to control the AI Coach desktop pet, making the mascot react to the conversation, accept care, show messages, act out activities, preview local files, and manage user memos. | |
| bigquery-mcp aicayzer/bigquery-mcp MCP server for secure BigQuery access across multiple Google Cloud projects, enabling querying, schema exploration, and data analysis with SQL validation and read-only controls. | |
| iqa-mcp aicent-stack/iqa-mcp Enables MCP agents to derive action-independent intent addresses, decode AE-128 envelope structure, and verify envelopes offline with caller-supplied keys while rejecting malformed or tampered frames fail-closed. | |
| Altiplano aichholzer/altiplano MCP server for Vikunja. Runs locally over stdio, or as a shared HTTP service with per-client tokens. Projects, tasks, kanban, labels, relations, and comments, on both the v1 and v2 APIs. | |
| Electricity Shutdowns MCP Server aickathon-2025-08/blackout-tracker-mcp Monitors electricity outage schedules in Ukraine's Dnipropetrovsk region, enabling users to check outages, receive notifications, and calculate optimal charging time for MacBooks. | |
| Panda Router MCP aicodeking/pandaorchestrator Enables MCP clients to profile a task locally and pick the cheapest model likely to succeed from a chosen pool, then escalate after a failure, record the outcome, and list available models over stdio JSON-RPC. | |
| Khan Academy MCP Server aicoder2009/khanacademymcp Enables AI assistants to search, browse, and read Khan Academy's educational content, including courses, articles, and video transcripts. It provides tools to navigate the subject hierarchy and retrieve detailed metadata without requiring a | |
| calculator_mcp aicoder2048/calculator_mcp A comprehensive MCP server providing basic and advanced math operations (addition, subtraction, statistics, etc.) as well as smart prompts for multiplication tables, equation solving, financial calculations, geometry, unit conversion, loan | |
| Replicate MCP Server aicoder2048/img_gen_replicate_mcp Enables LLM clients to generate, edit, and evaluate images through the Replicate API. | |
| PrintAnything MCP Server aiconceptlab/3d-lab-004-printanything Enables AI agents to refine a parametric phone-stand specification, build it as real Blender geometry, and export a validated STL through bounded tools. | |
| Agent Jobs MCP Server aiconnect-cloud/agentjobs-mcp Allows AI agents to query and manage asynchronous jobs in the Agent Jobs system of the AI Connect platform, supporting operations like listing, creating, and canceling jobs. | |
| AICostBudget AI API Pricing aicostbudget/ai-api-pricing-data ai-api-pricing-data MCP server | |
| AICre8 MCP Server aicre8dev/mcp-server Enables AI agents to create, modify, and deploy web projects through the AICre8 platform's sandbox environment. It supports project management, code generation, and direct shell command execution for streamlined web development. | |
| hermes-bridge aidalinfo/hermes-bridge Relay MCP server enabling synchronous multi-turn communication between Hermes agents, allowing one agent to delegate tasks and await replies without third-party dependencies. | |
| mcp-catalogue aidan-kay/mcp-catalogue A browse-first MCP middleware that provides an LLM-friendly catalogue for discovering and invoking tools across multiple upstream MCP servers, reducing context overhead. | |
| MCP Nexus aidan-kay/mcp-nexus A single MCP endpoint for AI agents to browse, inspect, and call tools from multiple upstream MCP servers without loading all schemas upfront, reducing context overhead. | |
| Vault MCP aidan-kay/vault-mcp Enables hybrid search, reading, writing, and managing a local Obsidian vault through MCP tools and a REST API, including section patching, appending, moving notes with link rewriting, and frontmatter updates. | |
| Chess MCP Server aidanouckama/chess-mcp Enables AI assistants to play chess against users, manage games, make moves, and visualize boards with Stockfish AI opponent. | |
| ATLAS Governance Gateway aidant64/atlas-mcp-gateway A secure middleware that intercepts AI agent tool calls to evaluate risks and manage human-in-the-loop approvals via durable Inngest workflows. It ensures compliance with standards like the EU AI Act by pausing high-risk actions until autho | |
| cwprep-mcp aidatacooper/cwprep Generating Tableau Prep data flow (.tfl) files | |
| cwtwb aidatacooper/cwtwb ai generate tableau file | |
| AiDD MCP Server aidd-app/mcp-server Integrates Apple Notes with AI-powered task extraction and prioritization, enabling automatic processing of notes into actionable items and syncing across multiple productivity services like Google Tasks, Todoist, Notion, and more. | |
| mcp-test-stepfun aiddlx/mcp-test-stepfun An MCP protocol test server with 35 test tools across 3 transport modes for compatibility verification, plus a development Skill for the Stepfun AI desktop assistant to help write MCP servers. | |
| fleetmcp aiden-ferrante/fleetmcp Enables a coding agent to drive four local apps through 50 curated, OpenAPI-generated tools spanning reads, writes, and destructive actions gated by impact-token checks the apps themselves enforce. It carries each app's own refusal message | |
| Sentiment Analysis MCP Server aiden-jeon/huggingface-mcp-course An MCP server that provides sentiment analysis functionality using TextBlob, allowing users to analyze text for polarity, subjectivity, and sentiment assessment through Cursor AI. | |
| apic-docs-mcp aiden-kwak/ibm-apic-doc-mcp Unofficial MCP server for searching and reading IBM API Connect 12.1.0 documentation. | |
| comfyui-local-mcp aiden-yanzy/comfyui-local-mcp Enables MCP clients to generate images using local ComfyUI with FLUX.2 Klein models optimized for Apple Silicon, plus model management and system diagnostics. | |
| lattice-mcp aidenappl/lattice-mcp MCP server for the Lattice container orchestration platform, enabling Claude Code to manage workers, stacks, containers, and deployments through natural language. | |
| Financial Data MCP Server aidenbmiller26-finanalyst/mcp-server Enables AI assistants to access real-time stock, crypto, and market index data from Yahoo Finance, supporting queries for prices, history, company info, and comparisons. | |
| claude-tradingview-mcp aidenhecker/claude-tradingview-mcp An MCP server that lets Claude analyze your TradingView charts by reading the window and taking screenshots, with no write tools or trade execution. | |
| Hello3DMCP Server aidenlab/hello3dmcp-server An MCP server that bridges AI clients with a frontend 3D visualization application to control model properties, lighting, and camera settings via WebSocket. It enables real-time manipulation of 3D scenes through natural language commands fo | |
| spacewalk-mcp aidenlab/spacewalk-mcp Lets Claude and ChatGPT open and drive a Spacewalk 3D chromatin viewer alongside the conversation. | |
| mapbox-mcp-server aidenyangx/mapbox-mcp-server MCP Server for the Mapbox API. | |
| EchoLoopMCP aidevksh/echoloopmcp Enables AI agents to notify users via Telegram or Discord when tasks complete, then wait for and receive the user's reply as the next instruction within the same session. | |
| Joke Generator MCP aidevshakil/mcp-learning Enables users to fetch developer and programming jokes, either random or by specific topic, through simple MCP tools. |
25,051–25,100 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.