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 |
|---|---|
| Nano Banana Remote MCP Server ayonz-dev/nano-banana-remote-mcp A remote MCP server that exposes Gemini image generation/editing as a custom connector for Claude, enabling image creation and editing from any chat interface. | |
| EchoFlow ayoola-tech2024/echoflow-alexa-mcp Enables Alexa+ voice agents to control smart home devices, generate daily briefings, orchestrate routines, and query user context through tools backed by AWS Bedrock. | |
| Artificial Virtual Assistant (AVA) ayoub-etoullali/model-context-protocol-mcp An MCP server that provides AI applications with a toolset for an Artificial Virtual Assistant (AVA) integrated with the Gmail API. It enables users to automate email management and personal tasks through secure Google OAuth authentication. | |
| ArchiBridge MCP Server ayoubmep/archibridge-mcp Connects Claude and ChatGPT to a locally running Archicad project, enabling AI to read and modify building models, inspect 3D and 2D views, and follow guided skills through Archicad's JSON API and Tapir. | |
| GoLogX (logx-mcp) ayoubtadlaoui/gologx Tamper-evident audit logging for AI agents. Append-only, hash-chained, optionally Ed25519-signed log. The MCP server lets an agent keep and verify a record of what it actually did. | |
| npmguard ayoubtadlaoui/npmguard Pre-install risk gate for npm packages.
Stops AI coding agents from running malicious or lifecycle scripts run. | |
| Git Code Review MCP ayoubtrd/git-codereview-mcp Enables AI assistants to perform code reviews by providing access to staged files, git diffs, and repository file content. It allows users to evaluate changes and context within any local git repository before committing or pushing. | |
| Perplexity MCP Server ayoubzeroual/perplexity-mcp Enables web search functionality through Perplexity AI's API with time-based filtering options. Allows users to search the web for recent information within specified time periods (day, week, month, or year). | |
| CRM MCP Server ayousry2122343/crm Enables AI agents to manage contacts, deals, pipelines, and team collaboration in a multi-tenant CRM with Arabic/RTL support. | |
| Groq MCP Server ayrtonfelipe/groqcloud-mcp_server An intelligent server that connects applications to Groq's AI models, enabling text completion, audio transcription, vision analysis, and batch processing through the Model Context Protocol. | |
| Sugar ayse98724/sugar Enables AI coding agents to read and write persistent, local-first memory through MCP, storing decisions, preferences, and error patterns per project while surfacing cross-project guidelines, with semantic search over on-disk SQLite and an | |
| opencode-mcp aysechavez/opencode-mcp Connects MCP clients such as Claude, Cursor, and VS Code to OpenCode's headless API, enabling users to ask questions, implement features, run and monitor background coding work, respond to permissions/questions, and review changes across pr | |
| mcp-virustotal aysegarnier/mcp-virustotal Enables AI agents to query the VirusTotal v3 API for URL, file, IP, and domain security reports, including relationships, pivot searches, sandbox behavior, threat collections, and pagination. Supports stdio and HTTP streaming transports wit | |
| whoop-ai-mcp aysehunt499/whoop-mcp Enables read-only access to your WHOOP recovery, sleep, HRV, strain, workout and body-measurement data from Claude Desktop, Claude Code, Codex or GitHub Copilot, so you can ask natural-language questions about today's status, personal basel | |
| whoop-ai-mcp aysemills0486/whoop-mcp Enables Claude, Codex, and GitHub Copilot users to query read-only WHOOP recovery, sleep, HRV, strain, workouts, and personal health analytics through natural language. It provides baselines, trends, readiness insights, and local dashboard | |
| Figma Context Cache MCP aysllagomes/figma-context-cache-mcp An MCP server that provides cached, refreshable, and structured Figma context for AI coding assistants, reducing API calls and latency by storing node responses locally. | |
| business-data-mcp aystzh/business-data-mcp Provides read-only tools to search customers, orders, and business documents across PostgreSQL, JSON CRM, and Markdown sources, with tenant isolation, PII masking, and auditable access. | |
| Obsidian MCP Server aytacmehmet/obsidian-mcp-server An Obsidian plugin that runs an embedded MCP server inside Obsidian, exposing vault operations and optional GitHub integration to any MCP client. | |
| sap-cloud-erp-mcp aytacmehmet/sap-cloud-erp-mcp An MCP server that provides tools to list, get, create, and update SAP S/4HANA Cloud Public Edition business objects like purchase orders, sales orders, and production orders through the Model Context Protocol. | |
| legends-mcp aytuncyildizli/legends-mcp Your personal council of tech titans, investing legends, and crypto builders. 36 personas. Zero API keys. One npx command. | |
| Paper Pilot aytzey/paper-pilot Your AI's research copilot. Searches 6 academic databases, downloads real PDFs, reads them cover to cover, extracts evidence, renders figures, syncs to Zotero. | |
| memory-mcp ayubmoh1/memory-mcp Persistent memory MCP server for Claude Code. Store, search, and retrieve memories across sessions using hybrid vector + keyword search powered by SQLite, FTS5, and sqlite-vec. | |
| Legal MCP ayunis-core/ayunis-legal-mcp Enables AI assistants to search and analyze German legal texts using vector embeddings and semantic search. | |
| LNR-server-01-input-data-processing ayupow/llm-agent-based-on-tcg-te-pattern-with-graph-guided-mcp-tools This server is to precess files for LNR. | |
| mcp_db ayuriiuni-prog/mcp_db MCP server for exploring metadata of corporate databases: table structures, relationships, dependencies, and export to UML diagrams. | |
| OpenGrok MCP Server ayush-jain17/opengrok-mcp Query and explore code repositories in OpenGrok directly from VS Code using GitHub Copilot and the Model Context Protocol (MCP). | |
| Gmail MCP Server ayush-k-shukla/gmail-mcp-server Integrates with Gmail APIs to manage emails and labels, including sending, deleting, summarizing, and semantic search via RAG. | |
| atliq-hrms-assist ayush-og/atliq-hrms-assist An MCP server that enables AI assistants to manage HR operations like employee onboarding, leave requests, meeting scheduling, and equipment tickets through natural language. | |
| twitter-automation ayush-oswal/twitter-automation A Model Context Protocol (MCP) server that enables Claude to automate Twitter posting with AI-generated images and thread support. | |
| Expense Tracker MCP ayush-patel-29/expense-tracker-mcp A simple MCP server for tracking expenses in a local SQLite database, enabling add, read, update, delete, and summarization of expenses with predefined categories. | |
| codelore-mcp ayush-sadekar/codelore-mcp Turn any code repository into a searchable Obsidian vault — then let Claude Code navigate it as a set of MCP tools. | |
| commit-discipline-mcp ayush-singh-0601/commit-discipline-mcp An MCP server that enforces disciplined Git workflows by planning coding tasks into small, test-gated commits, ensuring tests pass before staging and preventing out-of-scope or oversized changes. | |
| book-notes-mcp ayush1298/book-notes-mcp MCP server for processing raw book notes into structured, searchable knowledge using embeddings and semantic search. | |
| mcp-wormhole ayush7614/mcp-wormhole Open-source MCP servers that connect AI agents to tools like Asana and Vercel via natural language. | |
| personal-context ayush7614/personal-context Aggregates your digital footprint (GitHub, blogs, resume) into a single AI-readable profile and exposes it via MCP tools so AI agents can query your context live. | |
| Debug Web MCP ayushchouhaan/debug-web Enables agents to inspect localhost web applications through Chrome DevTools Protocol by listing Chrome targets, attaching to a page, capturing and querying network, console, navigation, and WebSocket events, and managing ephemeral sessions | |
| Generic SQL MCP Server ayushedunext/db-mcp A configurable, database-agnostic MCP server that enables LLMs to safely interact with SQL databases through read-only operations and schema inspection. | |
| gpu-router ayushg8/gpu-router Enables AI agents and their users to submit, route, and monitor training jobs across free-tier GPU clouds (Kaggle, Colab, Lightning, local MPS) through a local daemon that tracks quota, explains routing decisions, and gates long or secret-r | |
| Savage in a Suit MCP Server ayushg8/sias-mcp-server Enables Claude to directly manage the Savage in a Suit website through 31 tools for pages, events, members, testimonials, podcast episodes, and site content, with all changes logged. | |
| codesentry-mcp ayushgundecha/codesentry-mcp AI-powered code review assistant that analyzes repositories for security vulnerabilities, performance bottlenecks, and code quality issues through natural language interactions. | |
| claims-coverage-assessment-assistant ayushgupta94/claims-coverage-assessment-assistant MCP server that reviews insurance claims against policy documents, providing coverage decisions, policy clause retrieval, claim history lookup, coverage rule checks, and fraud risk scoring via four tools. | |
| MCP Server Starter ayushii1612/mcp-toolkit Provides a TypeScript scaffolding that auto-loads drop-in tools, resources, and prompts, and serves them to MCP-compatible clients over stdio or streamable HTTP. | |
| PaperPilot-AI ayushisingh51/paperpilot-ai MCP server for semantic research: search arXiv, fetch papers, and answer questions grounded in the actual paper text via RAG tools, resources, and prompts. | |
| RA-Nested-MCP ayushkhandelwal-bits/ra-nested-mcp A two-layer nested MCP server that acts as a telecom Revenue Assurance knowledge agent. It uses an orchestrator LLM (Llama 3.3 70B via Groq) to decompose questions, retrieve from a local vector store of RA documents, and synthesize answers, | |
| WETH ayushkumar2601/wallet_weth Enables AI agents to analyze Ethereum wallets, simulate transactions, and draft transfers with deterministic policy and risk scoring, requiring human approval before on-chain execution. | |
| WETH MCP Server ayushkumar2601/weth_wallet_devcon Enables AI agents to safely interact with Ethereum by providing structured tools for reading blockchain state, simulating transactions, and drafting transactions that require human-in-the-loop approval. | |
| remote-mcp-server-authless ayushlm10/remote-mcp-server-authless Deploys a remote MCP server on Cloudflare Workers without authentication, enabling connection to Cloudflare AI Playground and Claude Desktop. | |
| PowerPoint MCP Server ayushmaniar/powerpoint-mcp Enables PowerPoint automation on Windows, including template-based creation, real-time editing, LaTeX equations, animations, and multimodal slide analysis, all via natural language. | |
| LinkedIn MCP Server ayushnagvanshi101098-ship-it/linkedin-mcp-server MCP server for posting to LinkedIn, managing drafts, scheduling, commenting, and reacting, all from the terminal. | |
| photoshop-mcp-pro ayushnagvanshi101098-ship-it/photoshop-mcp-pro A professional MCP server that lets AI assistants directly control Adobe Photoshop for document creation, layer management, filters, adjustments, shapes, text, and design intelligence like palette generation and font pairing. |
32,251–32,300 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.