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 |
|---|---|
| TrueRAG MCP Server ad-veritas/mcp-server-truerag Enables interaction with a TrueRAG system through a GraphQL API using the Model Context Protocol (MCP), facilitating access to policies with a Python SDK and GQL library integration. | |
| adextract ad-vertly/ad-extract Ad libraries are public but fragmented. Every platform is a silo - different UI, different filters, different quirks. If you want to see what competitors are running, you're either opening four tabs and pasting into Excel, or maintaining sc | |
| WordPress MCP Server ad02/wordpress-mcp-server A Model Context Protocol (MCP) server that bridges AI assistants to WordPress, enabling natural-language management of posts, pages, media, comments, users, plugins, and settings across multiple sites simultaneously. | |
| wp-ops-mcp ad02/wp-ops-mcp Enables AI assistants to read and edit WordPress sites over the REST API, including Divi 4, Divi 5, and Gutenberg content, with safety features like round-trip verification, draft-based editing, and dry-run previews. | |
| Zentao MCP Server ad19900913/mcp-rdms Enables direct integration with Zentao bug tracking systems through Cursor. Supports authentication, bug retrieval, searching, and listing operations for comprehensive bug management through natural language. | |
| nomad ad3n1ne/nomad-mcp A local MCP server for agentic remote development that enables code sync via rsync, SSH command execution, and long-running task management in remote tmux sessions. | |
| xiaohongshu-ai-life-mcp ada-wong183/xiaohongshu-ai-life-mcp Enables AI clients to automate Xiaohongshu through Playwright, including login, searching and retrieving notes/comments/feeds, analyzing images, interacting via comments/likes/favorites, and publishing or deleting notes with anti-detection | |
| wsltop adachi6k/wsltop Read-only observability MCP for Windows, WSL, Docker, and WSLC. | |
| garmin_mcp adagh2000-ctrl/garmin-mcp Enables read-only access to Garmin Connect data through OAuth, including activities, sleep, HRV, body battery, training status, and scheduled TrainingPeaks workouts. | |
| finary-mcp adagues/finary-mcp Enables read-only access to Finary portfolio data, including profiles, organizations, institution connections, portfolios, and transactions, through MCP. | |
| Log Analyzer MCP Server adai78/log-analyzer-mcp Enables querying and analyzing logs from multiple remote Unix hosts via the Log Collector API, with tools for search, error detection, and summary generation. | |
| SvelteLS.MCP adainrivers/sveltels.mcp An MCP server that wraps the Svelte Language Server to provide IDE-like tools for Claude Code and other MCP clients. It enables advanced Svelte development features including symbol navigation, diagnostics, refactoring, and component-specif | |
| norns-mcp adairbear/norns-mcp Enables reading status, scripts, parameters, and logs from a monome norns and performing gated writes, screenshots, script control, and safe deploys over SSH, OSC, and the matron REPL. Writes are dry-run by default and require explicit live | |
| traderspost-mcp adairbear/traderspost-mcp An MCP server that gives Claude direct access to TradersPost webhook trading. Send trade signals, inspect strategy configs, query trade history, and monitor positions. | |
| testrails-mcp adakh3/testrails-mcp MCP server for TestRail that enables AI agents to manage test cases, runs, and results, plus a bundled skill to convert Jira tickets into TestRail test cases. | |
| weeek-mcp adalekin/weeek-mcp Enables task management on Weeek via the public REST API and knowledge base browsing as MCP resources with full document content. | |
| Solid Multi-Tenant DevOps MCP Server adam-camp-king/solid-mcp-server Enables AI-first DevOps management of multi-tenant Solid SaaS platforms through natural language conversation. Monitor thousands of tenant instances, track AI agent performance, handle errors, manage billing, and provision new tenants direc | |
| semantic-search-mcp adam-hanna/semantic-search-mcp Provides semantic code search over codebases using local embeddings with natural language queries. Supports hybrid search, file watching, and respects .gitignore. | |
| omp A2A Bridge adam-ikari/a2mcp Enables a remote omp client to invoke the host omp's tools over HTTP using the MCP protocol, with no LLM API calls on the host. | |
| Cloudflare Grafitti MCP Server adam-paterson/cloudflare-grafitti-mcp-server A serverless proxy for the Graphiti MCP server, enabling AI agents to maintain memory and context through Neo4j knowledge graphs, deployed on Cloudflare Workers. | |
| MCP Crew AI Server adam-paterson/mcp-crew-ai A lightweight Python-based server designed to run, manage and create CrewAI workflows using the Model Context Protocol for communicating with LLMs and tools like Claude Desktop or Cursor IDE. | |
| rubiks-cube-mcp adam-s/rubiks-cube-mcp Exposes a Rubik's cube to an AI agent, allowing it to manipulate and solve the cube, with a web dashboard for monitoring agent runs. | |
| rounder adam-sari/rounder 29 local file tools for AI assistants: compress, merge and split PDFs, convert and resize images, zip files, shrink and convert video. Runs on your machine, reads only folders you allow, and costs about 700 tokens up front. MIT, no account. | |
| nigrty adam-zs/recalllattice Enables AI agents to store, recall, link, and manage durable local memories using ranked fuzzy search and optional graph context through a compact MCP interface. | |
| sapgui-mcp adam0thman/sap-gui-control-skill Enables AI agents to execute SAP tasks through a cost-routing MCP server that tries API, recorded scripts, WebGUI, and computer-use vision in cheapest-first order, falling back only when needed. It can also promote an interactive GUI routin | |
| Instagram MCP Server adam20785/ig-mcp It enables AI applications to interact programmatically with Instagram Business accounts through Instagram's Graph API, including retrieving profile and media data, analyzing insights, publishing content, and managing direct messages when a | |
| Gmail MCP Server adam51-code/gmail-mcp-server Enables managing Gmail messages and threads via archive, label, search, trash, and other operations. | |
| Mist MCP Server adam5isalive/mist-mcp-server Exposes Juniper Mist REST API as 22 curated MCP tools, enabling AI agents to query and manage network resources like sites, devices, WLANs, and Marvis AI insights through natural language. | |
| IDA Pro MCP Server adam6025/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis, including executing Python scripts, retrieving binary metadata, searching values/text/bytes, and obtaining disassembly. | |
| testlink-mcp-server adama007/mcp-testlink Enables LLM agents to interact with TestLink test management system via XML-RPC API, supporting test projects, suites, cases, plans, executions, and custom fields. | |
| mcp-capability-guard adamabdo-xynora/mcp-capability-guard Demonstrates capability-token write authorization for MCP servers, enforcing per-mutation single-use warrants and human confirmations over an in-memory CRM to prevent unauthorized or destructive actions. | |
| bothread-room-for-ai-agents adamace9/bothread A free, local room where multiple MCP-compatible AI coding agents collaborate on one codebase — collisions prevented, human in command. | |
| Apollo.io MCP Server adamanz/apollo-io-mcp-server A Model Context Protocol server implementation that enables AI assistants to interact with Apollo.io data, allowing for people and organization enrichment, search capabilities, and job posting retrieval through natural language commands. | |
| Exa Websets MCP Server adamanz/exa-websets-mcp A Model Context Protocol server that enables interaction with Exa's Websets API for AI-powered web search and data collection, allowing users to create and manage customized websets through natural language queries. | |
| gemini-video-mcp-server adamanz/gemini-video-mcp-server Enables AI coding assistants like Claude Code and Cursor to analyze and understand video content using Google's Gemini AI, supporting long videos, segment analysis, and Q\&A. | |
| Qwen3-VL Video Understanding MCP Server adamanz/qwen-video-blaxel-mcp Enables AI agents to analyze, summarize, and extract text from videos and images using the Qwen3-VL-8B-Instruct model deployed on Blaxel. It supports media analysis via URL, including video Q\&A and speech transcription capabilities. | |
| Qwen Video Understanding MCP Server adamanz/qwen-video-mcp-server Enables AI agents to analyze videos and images using Qwen3-VL deployed on Modal, supporting hours-long videos with timestamp grounding, text extraction, video summarization, and Q\&A with 256K context window. | |
| TMDB MCP Server adamayoung/tmdb-mcp Integrates with The Movie Database (TMDB) API to provide movie information, search capabilities, and recommendations. | |
| sanxiao-mcp adambbhe/kingdee-sanxiao-mcp Enables read-only querying of Kingdee's Three-Effect project management system, covering projects, reimbursements, loans, payments, working hours, and budgets, via MCP tools. | |
| kingdee_star adambbhe/kingdee-star-mcp Enables read-only access to Kingdee Cloud Star financial data, invoice tax calculation, and generation of reimbursement draft payloads through MCP tools. | |
| TDX Finance MCP Plugin v3 adambbhe/tdx-finance-mcp-plugin-v3 Enables access to TDX A-share financial data, including real-time quotes, K-line, F10 fundamentals, stock screening, and code retrieval via natural language. | |
| TDX Local MCP adambbhe/tdx-local-mcp Bridges a local Tongdaxin client to MCP, exposing tools for market data, financial information, sector management, terminal push, simulated trading, and automatic price alerts, enabling natural-language data retrieval, analysis, and order o | |
| Foundry VTT MCP Bridge adambdooley/foundry-vtt-mcp Connects Claude Desktop to Foundry VTT for AI-powered campaign management, enabling natural language interaction with game data including quest creation, character management, compendium searches, and dice rolling. Provides 20 MCP tools for | |
| euenergy-mcp adambenhassen/euenergy-mcp A read-only MCP server that exposes European day-ahead electricity prices for ~41 bidding zones via tools like hourly prices, cheapest hours, current price, and cross-zone summary, enabling AI agents to query energy market data. | |
| shelly-api-mcp adambenhassen/shelly-api-mcp Provides read-only access to Shelly Cloud energy data, including live power, lifetime energy, and historical consumption with cost, enabling AI agents to monitor electricity usage without device control. | |
| MCP SCP Server adambrand/mcp-scp Enables secure file transfer operations with remote Linux and Windows systems via SCP/SFTP protocols. Supports uploading, downloading, listing, and managing files on remote servers through SSH authentication. | |
| Pluts MCP adamburmister/pluts-mcp An OAuth-protected MCP server for Pluts on Cloudflare Workers that provides secure access to ledger data using short keys and Cloudflare Access authentication. | |
| Google Workspace MCP adamcfield/google-workspace-mcp-worker Enables authenticated read/write access to a user's Sheets, Drive, Docs, Gmail, Calendar, Tasks, Contacts, Chat, Slides, Forms, Photos, YouTube, and Meet through a remote OAuth flow. | |
| zoho-analytics-mcp-worker adamcfield/zoho-analytics-mcp-worker Exposes the Zoho Analytics API v2 as an MCP server, enabling Claude and other clients to query, manage, and analyze Zoho Analytics data through natural language. | |
| AI Model Registry MCP Server adamchall87/ai-model-registry Enables AI agents to discover and query live model information from OpenRouter, HuggingFace, and Ollama Cloud, ensuring recommendations are based on current data. |
23,551–23,600 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.