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 |
|---|---|
| Developer Research MCP Server ali-nr/developer-research-server Provides structured web search capabilities optimized for technical and software development content via providers like OpenRouter. It enables AI agents to perform research and retrieve relevant technical data in a consistent, programmatic | |
| metatrader-mcp ali-rajabpour/metatrader-mcp Enables users to capture real MetaTrader 5 chart snapshots with custom indicators and fetch market data through natural language in Claude Desktop. | |
| TECHNOVA AI MCP Server ali-raza-ai/technova-ai Enables planning gaming and workstation builds, estimating PSU wattage, checking basic compatibility, comparing hardware specs, recommending workload-suited builds, and searching a sample hardware catalog through MCP tools. | |
| Power BI Modeling MCP Server ali-stats/power-bi-mcp-ai-chatbot Enables AI applications to discover and connect to Power BI Desktop semantic models, inspect tables, columns, and measures, and validate or execute DAX queries through MCP. | |
| Power BI MCP Assistant ali-stats/power-bi-mcp-assistant Enables an AI application to connect to Power BI Desktop semantic models, discover their tables, columns, measures, and metadata, and validate and execute DAX queries so users can ask analytical questions in natural language and receive exp | |
| SMS.ir MCP server ali-toghiani/sms-ir-mcp Enables safe interaction with the SMS.ir Panel V2 API, providing read-only tools like balance and report checks, and billable SMS sending (including verification codes and personalized messages) only when explicitly confirmed and enabled. I | |
| levh ali-ulu/levh LEVH provides persistent, searchable memory for AI coding agents, enabling stateful interactions across sessions and tools with adaptive memory decay and reinforcement. It integrates with MCP-compatible clients and offers features like spac | |
| email-agent-mcp-server ali-zia3500/email-agent-mcp-server Enables AI-powered Gmail triage: fetches unread emails, classifies them, drafts replies for important ones, and sends only after user approval via conversational review. Exposes tools for checking unread emails and submitting review feedbac | |
| Frappe MCP ali08870/mcp Lets Frappe Framework apps expose their functions as MCP tools over a Streamable HTTP endpoint, with tool schemas inferred from type annotations and docstrings, plus OAuth2-based authentication. Works with Werkzeug/WSGI-based servers so exi | |
| Train in Silence ali26950/train-in-silence Enables users to describe an LLM fine-tuning workload once and receive ranked cloud GPU recommendations with estimated VRAM/FLOPs requirements, cost, runtime, and data-source transparency. | |
| Hello MCP Server ali5baway-ship-it/property-outreach-mcp Enables running a stateless MCP server on Cloudflare Workers with a simple greeting tool. | |
| mcp-virustotal ali7265/mcp-virustotal Gives AI agents access to the VirusTotal v3 API so they can analyze files, URLs, IPs, and domains and return detection reports alongside pivotable relationships such as contacted hosts, dropped files, and resolutions. It also supports corpu | |
| Coordigent ali8hsn/coordigent MCP server for shared file state, overlap warnings, and messaging between AI coding agents working in parallel on one GitHub repo. Works with Claude Code, Cursor, Codex, VS Code, Kiro, Windsurf and Perplexity; hosted service by Crews with a | |
| mcp-notes-server aliaksandr-andronchyk/mcp-notes-server Enables AI agents to store, full-text search, and organize notes with tags. | |
| multilingual-rag-mcp aliaksandr-kazarez/multilingual-rag-mcp Enables cross-lingual semantic search over local documents, allowing users to query in one language and retrieve relevant content in another without translation. | |
| rag-mcp aliaksandr-kazarez/rag-mcp Enables local semantic search across documents in multiple languages, allowing queries in one language to retrieve content in another. | |
| FastMCP Production-Ready Server aliaksandr-liapin/fast-mcp A production-ready MCP server that enables users to interact with Neo4j databases through health checks and Cypher query tools. It features a structured, containerized architecture with built-in support for Azure deployments and environment | |
| sqlite-mcp-server alialle/sqlite-mcp-server Read-only MCP server for SQLite databases, enabling AI assistants to safely query and inspect database schemas without write access. | |
| Playwright MCP alialobidm/playwright-mcp A Model Context Protocol server that provides browser automation capabilities by allowing LLMs to interact with web pages through structured accessibility snapshots. It enables fast, lightweight interaction with web content without the need | |
| launch-detector-mcp alialtunar/launch-detector-mcp Spot what companies are about to launch from new subdomains in certificate transparency logs (crt.sh). No API keys. | |
| ATS Resume Review aliameenrana/ats Enables AI agents to upload resumes and receive structured ATS scores with parseability, section coverage, contact-info, and keyword analysis, along with qualitative improvement suggestions via an LLM. | |
| moray-surgeon aliangmo2026/moray-surgeon Enables listing available refactoring actions, executing validated JSON refactor plans inside Git transactions, and running a natural-language refactor loop with automatic verification and rollback via a local Ollama model. | |
| Library Book MCP Server alianza86/cti-mcp-test Read-only MCP server that provides tools to search books, get book details, list authors, and view library statistics from a PostgreSQL database. | |
| Gemini MCP Server aliargun/mcp-server-gemini Model Context Protocol (MCP) server implementation that enables Claude Desktop to interact with Google's Gemini AI models. | |
| WorkPulse MCP Server aliasdhacker/workpulse-mcp Enables MCP clients like Claude to enter and query expenses, invoices, and contracts in a WorkPulse instance via its REST API, with 14 tools, batch rollback, and stdio or OAuth-protected Streamable HTTP transports while keeping credentials | |
| restaurant-ksor aliaskarigithub/restaurant-ksor Enables AI agents to query a restaurant's governed knowledge documents, including menu, allergen info, reservation and refund policies, and hours, over MCP. | |
| aliasmail-mcp aliasmail-space/aliasmail-mcp This server enables AI agents to create instant, zero-log disposable inboxes for signups and automated workflows. It also provides robust tools for autonomous extraction of verification codes and deep email security auditing. | |
| enoch-mcp aliasocracy/enoch-mcp MCP server for the Enoch FastAPI control-plane API, enabling inspection and operation of an Enoch instance via tools. | |
| Docling MCP Server aliat93/docling-mcp-server Converts folders of financial and investment documents into structured markdown, JSON, and CSV files with a metadata index, enabling AI assistants to efficiently navigate and analyze large research libraries. | |
| Lingshu FastMCP Medical AI Service alibaba-damo-academy/lingshu_mcp Enables medical image analysis, structured medical report generation, and medical Q\&A through the Lingshu medical AI model. Provides healthcare professionals and developers with AI-powered medical assistance capabilities via a FastMCP serv | |
| Helios alibaba/helios MCP server that securely reviews AI-generated code for vulnerabilities such as SQL injection, command injection, and hardcoded credentials. | |
| youtube-signal-mcp alibabagini-cyber/youtube-signal-mcp Enables AI agents to retrieve YouTube transcripts, video info, channel video lists, and monitor channels for new uploads, with built-in prompt templates for summaries and industry signals—all without an API key. | |
| SmoothyStudio MCP Server alibahrawy/smoothystudio Enables AI agents to generate and compose thumbnails using tools like get_capabilities, measure, render_thumbnail, render_variants, and get_canvas, with a document model that supports layers, effects, and masking. | |
| ForceShift MCP Gateway alibekjailov/forceshift-mcp-gateway An open-source MCP gateway for the ForceShift B2B commerce intelligence platform, enabling AI agents to query verifiable market data, price points, and UI layouts without hallucinations. | |
| tld-list-mcp aliberkyilmaz/tld-list-mcp Enables searching domain name variants across TLDs, comparing registrar registration, renewal, and transfer pricing, calculating multi-year ownership costs, and checking availability via RDAP. It also supports filtering, sorting, metadata d | |
| gohighlevel-mcp alibhatti59/gohighlevel-mcp Exposes CRM operations as MCP tools, enabling agents to search contacts, retrieve contact records, list appointments, log notes, and create new leads. | |
| windcraft-mcp alicanbasak/windcraft-cli Enables Cursor and Claude Code to read design tokens and rules, and validate component code against a design system before generating UI. | |
| Expertise MCP Server alicanefee/ali-can-efe-expert-mcp Enables AI assistants to query and retrieve a structured professional profile, including expertise areas, CV, projects, active research, and target AI queries, through dedicated MCP tools and resources. | |
| Cursor n8n Builder alicankiraz1/cursor-n8n-builder Enables AI assistants in Cursor IDE to manage n8n workflows through the n8n REST API, including creating, updating, activating workflows, viewing execution history, and triggering webhooks. | |
| notion-mcp-proxy alicat99/notion-mcp-proxy Enables MCP clients to access Notion through a permission-checking proxy that restricts operations to a configured root page and its subtree, while blocking unauthorized tools. It also handles Notion OAuth and validates signed permission se | |
| mcp-github-oauth alice-cloudflare/mcp-github-oauth Provides a remote MCP server with GitHub OAuth authentication, deployable to Cloudflare, enabling tools like math operations and GitHub user info access. | |
| bodybridge alice-jin-dev/bodybridge Connects embodied devices (like StackChan, Raspberry Pi, ESP32) to AI via MCP protocol, enabling motion control with zero API cost, no PC required, and fully self-hosted. | |
| UofT Student Helper MCP Server alice0416/uoft-student-helper-mcp Enables University of Toronto students to access academic data from ACORN and Quercus via AI assistants. It provides tools to retrieve course schedules, enrollment details, syllabi, assignments, and announcements. | |
| AI Workspace Kit alice840126-ship-it/ai-workspace-kit Enables Codex, ChatGPT, and Aside to share project work memory by reading private GitHub-backed checkpoints and searching or re-reading allowed local/SSD documents through read-only MCP tools. | |
| Vision-OCR-MCP aliceauto/vision-ocr-mcp-server Enables OCR on images and PDFs, including full-page OCR, region OCR by description or bounding box, and caching with summary capabilities. | |
| Rootstock MCP Server alicecha/rsk-mcp-server Enables Claude AI to interact with the Rootstock blockchain, including calling contracts, checking ERC20 token balances, transferring tokens, and querying gas prices. | |
| sudo-meow-mcp alicefarron/sudo-meow-mcp MCP server that exposes tools to read and control the state machine of a Tauri desktop app, enabling autonomous QA exploration and testing. | |
| CVE-Search MCP Server alicegallo04230/cve-search_mcp Enables users to browse vendors and products, retrieve individual CVE records, list recent CVEs with CAPEC, CWE, and CPE expansions, and check current database update status through a Model Context Protocol interface. | |
| ravelry-mcp alicegetmanchuk/ravelry-mcp-project An MCP server that connects Claude to the Ravelry API, letting knitters and crocheters search for patterns, find yarn, and calculate how much to buy — all through natural language. | |
| MCP REST API Tester alicehughes6319/mcp-rest-api Enables testing and interacting with REST API endpoints from Claude, Cline, and other MCP clients, supporting GET, POST, PUT, DELETE, and PATCH requests with authentication, custom headers, SSL control, and response size limits. |
26,501–26,550 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.