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 |
|---|---|
| Perch adityaarsharma/perch AI-native server intelligence layer for RunCloud-managed servers. Enables Claude Code to diagnose issues, manage web apps, and automate fixes in plain English via 150+ MCP tools. | |
| librecrawl-technical-seo-audit-mcp adityaarsharma/sitewalk Open-source technical SEO crawler MCP server built on LibreCrawl. Runs full audits inside Claude, Cursor, or Codex — 50+ checks (hreflang, schema.org, security headers, WAF detection on 200-OK pages), chunked-progressive engine for large si | |
| youtube-marketing-skills adityaarsharma/youtube-marketing-skills MCP server that connects AI agents to real YouTube channel analytics and SEO management via OAuth, enabling content strategy, metadata updates, and companion WordPress posts without leaving the agent. | |
| freeWeb MCP Server adityaawaghmare/freeweb-mcp A lightweight MCP server providing web search via DuckDuckGo and page content extraction in multiple formats. | |
| artemis adityabol7/artemis Enables AI assistants and IDEs to drive real Android devices and emulators for cross-app UI automation, testing, and diagnostics, including collecting Logcat output and screenshots. | |
| VTION E-Commerce MCP Server adityac7/vtion-ecom Provides secure, read-only access to VTION e-commerce analytics data through MCP protocol. Enables AI agents to query PostgreSQL databases, discover schemas, and analyze product, order, and customer data with automatic query validation and | |
| Sanbi ADK Agent MCP Server adityadrexel/sanbi-adk-agent Enables AI agents to run brand-visibility audits by querying multiple AI engines, generating competitive leaderboards, and identifying growth opportunities. Integrates with any MCP-capable client to measure and act on brand discoverability | |
| satudata-ngawi adityafba/mcp-satudata-ngawi MCP server for accessing Indonesian local government data from Satu Data Ngawi. Enables querying datasets, organizations, categories, and statistics through natural language. | |
| Cloudflare Playwright MCP Example adityahannn-hub/playwright-mcp-example Enables AI assistants to control a web browser via Playwright on Cloudflare Workers for automated tasks like navigation, clicking, typing, and taking screenshots. It integrates with platforms like Claude Desktop and GitHub Copilot to perfor | |
| gmail-cleanup-mcp adityai4/gmail-cleanup-mcp Enables bulk Gmail inbox cleanup including trashing emails, managing filters, and extracting unsubscribe links, with dry-run previews and automatic retry/backoff to handle rate limits. | |
| LinkedIn Sales & Navigator MCP Server adityaidev/lindin-sales-and-navigator-mcp Enables AI assistants to interact with LinkedIn and LinkedIn Sales Navigator for searching profiles, managing leads, and handling messaging via cookie-based authentication. It supports professional networking tasks such as sending connectio | |
| Twitter/X MCP Server adityaidev/twitter-mcp Connects AI assistants to Twitter/X using cookie-based authentication to read timelines, search tweets, and perform actions like posting and liking. It leverages Twitter's internal GraphQL API to provide full functionality without requiring | |
| Hyperledger Fabric MCP Server adityajoshi12/fabric-mcp-server Enables AI assistants to interact with Hyperledger Fabric blockchain networks, supporting chaincode queries and invocations, block and transaction retrieval, chaincode lifecycle management, and channel operations. | |
| Google Maps MCP Server adityak74/google-maps-mcp Enables AI assistants to search places, retrieve place details, reviews, photos, business posts, and contributor review histories from Google Maps through natural language, with no API keys or paid billing required. | |
| MCP Scholarly Server adityak74/mcp-scholarly Enables users to search for academic articles on platforms like arXiv using specific keywords, with plans to integrate more scholarly databases in the future. | |
| polyagent adityak9822/polyagent Enables Claude Desktop to delegate specialized tasks like security scanning and code review to external AI agents from multiple providers, with dynamic agent registration, flexible pipelines, and safety controls. | |
| chatgpt-mcp-data-platform adityakhadsecode/chatgpt-mcp-data-platform Enables authenticated organization members to submit, query, and manage schema-validated structured records directly from ChatGPT, with membership requests and approval workflows gating access. All operations are tenant-isolated, permission | |
| TickTick MCP Server adityakhandelwal10/ticktick-mcp-server Enables AI assistants to manage TickTick tasks including listing, creating, updating, completing, and deleting tasks, as well as searching and filtering. | |
| crew_research adityakhuteta05/multi-agent-deep-researcher Enables deep web research, verification, and structured report generation with citations directly inside Cursor via MCP. | |
| OrderGuard adityakumarrai2007/orderguard Enables secure autonomous commerce by letting MCP agents propose and recommend purchases while deterministic gates, single-use execution capabilities, and independent re-verification control all payment authorization. | |
| OpenCode Brain adityaladi/ai-bain MCP server that gives OpenCode a persistent, graph-based memory with semantic search, iterative retrieval, and session-aware knowledge management. It supports capturing fleeting and permanent notes, distilling insights, tracking mistakes an | |
| LPDP MCP Server adityaldy/mcp-training Enables users to query information about LPDP scholarship financial disbursement using RAG with Pinecone vector search and Gemini 2.0 Flash, answering questions about funding components, deadlines, living allowances, and required documents. | |
| StudyRelay adityam274/studyrelay Enables interruption-aware, same-day study planning through local MCP tools for managing tasks, fixed commitments, scheduling windows, replanning after interruptions, previewing and approving simulated calendar changes, and persisting or ex | |
| betterbrain-all-in-summit adityamookerjee/all-in-summit An OAuth-secured remote MCP server (22 tools) that lets Claude, ChatGPT, and Codex search All-In Summit attendee profiles, explore the live agenda, check sessions and meetings, detect scheduling conflicts, and export a calendar. Account-cha | |
| mcp-docx-template adityanarendra-ssit/mcp-docx-template Enables cloning a styled Microsoft Word template and filling it with content from another document, preserving formatting, images, and layout, with optional PDF conversion. | |
| cf-analyser adityanath-madishetti/cf_analyser Enables analyzing Codeforces activity through local MCP tools, including weekly practice summaries, problem recommendations, user comparisons, weak-topic detection, contest tracking, and rating progress. | |
| mcp-langchain-agent adityapal26may/mcp-langchain-agent An MCP server exposing document search, retrieval, and summarization tools, paired with a LangChain agent that performs multi-step tasks like finding and summarizing relevant docs. | |
| tabella adityaparab/tabella Enables AI agents to interact with Tabella's CRM data through tools for listing objects, querying records, and creating/updating records, with changes visible in the UI in real time. | |
| JobApplication adityapat958/jobapplication Enables Claude to search job listings on selected sites, filter and score them against your own skills, track application status, and generate a tailored LaTeX/PDF resume for each job. It also supports importing an existing Word or PDF resu | |
| Employee Leave Management MCP Server adityapatel143/genai_employee_leave_management-mcp_server Manages employee leave with Claude Desktop via natural language. Enables checking balances, applying, approving, and reviewing leave requests through a Supabase-backed MCP server. | |
| Adi MCP Server adityapatel143/genai_mcp Enables LLMs to fetch real-time weather data for any city and perform basic arithmetic operations like addition. | |
| News Fact-Checker MCP Server adityapawar327/news-factchecker-mcp Enables fact-checking of news headlines using Google Gemini AI and web search verification, and retrieves trending news topics from RSS feeds with comprehensive multi-source analysis. | |
| MCP Text-to-SQL Agent adityapratap-521/mcp-text2sql-agent Enables users to inspect database schemas, validate SQL syntax, and execute queries against PostgreSQL and Apache Hive through standardized Model Context Protocol tools for safe query generation and validation. | |
| argocd-mcp adityaraj178/mcp-argocd-py Enables AI assistants to interact with Argo CD applications through natural language, providing tools for cluster, project, application, and resource management via stdio and HTTP transports. | |
| VeriSight MCP adityarajtiwari880/verisight Enables LLM agents to autonomously run sub-3ms multi-spectral forensic inspection of claim images to detect generative AI inpainting, deepfake tampering, duplicate reuse, and screen-recapture attacks. Exposes tools for CLAHE normalization, | |
| Strapi MCP Server adityarapid/strapi_mcp Enables AI assistants to interact with Strapi CMS instances through REST API operations. Supports content management, media uploads, schema introspection, and multiple server configurations with JWT authentication. | |
| chess-mcp adityareus/chess-mcp An MCP server that fetches and filters chess.com game data, returning compact summaries instead of massive JSON, enabling LLMs to answer questions about player performance and head-to-head records. | |
| MindSync MCP adityarya24/mindsync-ai Local-first MCP server for multi-agent memory sync and focus conflict detection, enabling multiple coding agents to share a session registry and receive conflict warnings when focuses overlap. | |
| Canvas LMS MCP Server adityas0604/mcp-canvas Connects Claude AI to your Canvas LMS account, enabling natural language interaction with coursework including assignments, grades, announcements, and calendar. | |
| Bing Search MCP Server adityas7netapp/bing-search-mcp A Model Context Protocol server that provides AI-grounded Bing search capabilities using the Azure AI Project Client. It enables intelligent web searches with automated citation tracking and URL extraction for seamless AI integration. | |
| browsercontrol adityasasidhar/browsercontrol MCP server for vision-first browser automation that annotates interactive elements with numbered markers, allowing AI agents to control any webpage by simply referencing element numbers. | |
| OpenAI Ads MCP adityash8/openai-ads-mcp Enables management of OpenAI Ads campaigns, ad groups, ads, and insights through MCP, with approval-gated live mutations for safe write operations. | |
| duet adityasingh-byte/duet Enables an AI coding agent to drive a real Android phone over adb and one or more visible Chrome windows in the same test run, with safe guarded commands, screenshots returned as images, per-step logs, reports, and recordings. It lets agent | |
| repo2diagram adityasingh-ops/repo2diagram Enables AI assistants to generate Mermaid architecture diagrams, inspect repository structure and module details, and assess changed-module blast radius versus a git ref for local codebases. | |
| Adi MCP adityasingh2929/adi-mcp A remote MCP server that exposes tools from many services (X, LinkedIn, GitHub, Gmail, Notion, etc.) through a single endpoint on Cloudflare Workers, enabling unified access to third-party APIs via natural language. | |
| SkillSync MCP adityasugandhi/skillsync-mcp An MCP server for searching, security scanning, installing, and managing skills from the SkillsMP marketplace, designed for Claude Code and other MCP-compatible clients. | |
| NoteMind adityathedev/notemind-mcpserver A lightweight, intelligent note-organizing server that acts as an AI-powered personal memory vault for capturing, organizing, and retrieving insights using FastMCP and SQLite. | |
| Local Weather & International Time MCP Agent adityaverma19/weather_time_mcp_app Provides real-time weather forecasts and international time details through MCP tools, including geocoding, hourly/daily forecasts, and timezone information for any city. | |
| Cortex adityavg13/cortex Private local memory for AI tools that provides persistent, private memory via HTTP and MCP protocols, enabling tools to store and recall context without external services. | |
| ResearchMCP adityay009/researchmcp Enables LLMs to search arXiv, extract and analyze paper content, and build a personal semantically-searchable research library with saved papers and notes. |
23,851–23,900 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.