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 |
|---|---|
| AWS FinOps MCP Server beatriza04180/aws-finops-mcp-server Enables users to query AWS cost and usage data, run waste and savings audits, and monitor budgets through natural-language prompts in MCP-compatible clients. It keeps AWS credentials local and supports multi-profile and multi-region analysi | |
| Federal Reserve Economic Data MCP Server beatrizgarcia71/fred-mcp-server Enables browsing, keyword/tag searching, and retrieval of any of the 800,000+ FRED economic time series, with support for date ranges, frequency aggregation, and unit transformations such as percent change or natural log. It also supports b | |
| tmux-bridge-mcp beatriznaik472/tmux-bridge-mcp Enables AI agents such as Claude Code, Gemini CLI, Codex, and Kimi CLI to read, type into, and send messages to one another's tmux panes through standard MCP tool calls. This lets users coordinate multi-agent workflows like review pipelines | |
| BigQuery MCP server beatrizr1856/mcp-server-bigquery Enables LLMs to inspect database schemas, list tables, and execute SQL queries against a configured cloud data warehouse, with optional dataset filtering, service-account credentials, and query timeouts. | |
| Vectorize MCP Server beatrizward/vectorize-mcp-server Enables users to perform vector search and document retrieval, extract and chunk files into Markdown, and generate private deep research reports from configured pipelines. | |
| Onboard GEO Precheck MCP Server beatshon/onboard-geo-precheck-mcp Enables to precheck landing pages and Figma frames for readiness to be cited in AI Overviews, providing audit scores, grades, and improvement actions. | |
| VS Auto Trend MCP Server beatshon/vs-auto-trend-mcp MCP server that wraps VS Auto Trend API to provide trend data and concept brief generation tools for LLMs. | |
| MCP Python Interpreter with Docker beatwad/mcp_docker_python_interpreter Enables executing Python code, managing environments and packages, and performing file operations within Docker containers. | |
| Network Ops MCP beau-wood/network-ops-mcp Aggregates network operations tools such as retrieving local network configurations and scanning ports, enabling IT professionals to perform these tasks via natural language. | |
| DNS MCP Server beauchompers/dns-mcp-server Provides comprehensive DNS lookup capabilities including A, AAAA, MX, TXT, NS, SOA, CNAME, SRV, CAA, DNSSEC records, reverse DNS lookups, and bulk queries for multiple domains or IPs. | |
| Quick Data for Windows MCP beaulewis1977/quick-data-for-windows-mcp A Windows-optimized server providing universal data analytics for JSON and CSV files through over 32 tools including schema discovery and interactive visualizations. It is specifically designed for seamless integration with Claude Desktop o | |
| GetSms beautifulsoup/get-sms MCP server that lets AI agents retrieve the latest SMS verification code by keyword, using self-hosted phone forwarding and persistent storage. | |
| mcp-telegram beautyfree/mcp-telegram A Telegram MCP server that connects agents to a real Telegram user account via MTProto, enabling reading, searching, sending, moderating, and managing Telegram chats through natural language or automated tool calls. | |
| finviz-mcp beavernest/finviz-mcp Enables read-only access to Finviz US market data through 14 tools covering per-ticker quotes and fundamentals, batch multi-ticker comparisons, market movers and breadth, news, insider trades, economic/earnings/dividend calendars, and secto | |
| ImageGen MCP beavernest/imagegen-mcp Free, keyless image generation MCP server that lets AI agents create images from text prompts via Pollinations/Flux. Supports multiple aspect ratios and returns local image file paths. | |
| godot-omni bebabinlarsson-blip/godot-mcp Enables AI assistants to automate the Godot Engine editor, including scene authoring, node transforms, tilemap editing, animation, shaders, and live GDScript execution via MCP. | |
| Godot MCP bebabinlarsson-blip/godot-mcp-archive Enables AI coding assistants to directly control a running Godot editor for autonomous game development, including scene building, tilemap and animation manipulation, UI automation, and live GDScript execution. | |
| mcp-examples bebebebebebebebebebebebebebebe/mcp-examples Enables retrieving user and post data through MCP tools, with Zod-based request validation and OpenAPI/Swagger UI support. | |
| mcp-redmine beborico1/mcp-redmine MCP server for Redmine that lets coding agents read and write Redmine: search issues, view histories, comment, log time, browse wiki, and download attachments. Enforces explicit user permission for any write operations. | |
| fh5-mcp bebulli/fh5-mcp MCP server that provides Forza Horizon 5 telemetry tools (session listing, summaries, telemetry windows, tuning recommendations) to AI assistants, enabling natural language queries about driving sessions. | |
| TriSync beburit/trisync Enables users to turn structured training plans into Garmin Connect workouts, schedule them, queue delivery to registered devices, and optionally coordinate timed Google Calendar events with workout summaries. | |
| antigravity-browser beccaceci/antigravity-browser Enables Gemini to control a visible dedicated Chrome profile with structured page controls, screenshot/coordinate tools, and compact output via Playwright MCP, without a separate API key. | |
| obole beccariavf/obole Exposes long-term stock analyses (log-price regression, valuation in σ, annualized trend, 5/10-year potentials), ticker search, a French-universe screener, thesis drafting, and portfolio reads/writes to an AI client over stdio, with an opti | |
| ikuai-mcp beck-8/ikuai-mcp MCP server for interacting with iKuai routers, enabling Claude to query system status, manage devices, and configure router settings via natural language. | |
| iStoreOS MCP Server beck-8/istoreos-mcp Enables AI assistants to read-only monitor iStoreOS/OpenWRT routers via SSH or HTTP/ubus API, providing 31 tools for system status, network info, logs, and plugin status (OpenClash, Passwall, AdGuardHome, etc.). | |
| Claude Patent Creator MCP Server beck862/claude-patent-creator Exposes 20+ tools that let MCP-compatible clients answer patent-rule questions via hybrid RAG search over MPEP, USC, and CFR, hunt for prior art across 100M+ patents through Google BigQuery, run automated claim and application compliance ch | |
| Agentic Travel Recommendations API beckett-eiland/mcp-service-proof-of-concept MCP server that provides AI agents with personalized travel recommendations for members, enforcing partner-specific rules such as category exclusions, loyalty tier eligibility, and recommendation caps. | |
| runtime-mcp-server becketthayes/runtime-mcp-server Provides AI coding agents with real-time visibility into local development runtime state, enabling them to tail application logs, inspect ports, monitor process metrics, and diagnose network errors. | |
| kicad-jlcpcb beckhamlabsllc/kicad-jlcpcb Automates PCB design from idea to fabrication: sources JLCPCB parts, fetches pin maps from EasyEDA, places and wires footprints in KiCad, and hands off to EasyEDA for auto-routing and ordering — all via Claude Code. | |
| Linux Desktop MCP Server beckhamlabsllc/linux-desktop-mcp Enables AI assistants to interact with native Linux desktop applications through AT-SPI2 accessibility interfaces. Provides semantic element targeting, natural language search, and automation capabilities (clicking, typing, keyboard shortcu | |
| Oracle MCP Server becksclair/oracle-mcp Enables consulting oracle AI models (Codex or Claude) for expert reasoning and analysis on complex problems, architectural decisions, and design tradeoffs through a unified CLI interface. | |
| EnriVision bedolla/enrivision An MCP server that enables analysis of local media files, including video, audio, and documents, by uploading them to EnriProxy for server-side extraction. It supports various complex file formats and provides structured model analysis for | |
| EnriWeb bedolla/enriweb An MCP server that provides web search and URL fetching capabilities by delegating execution to an EnriProxy server. It enables AI agents to perform structured web searches and retrieve content with support for filtering, recency limits, an | |
| Codex Orchestrator bedonweekends/codex-mcp Enables safe, isolated Codex implementation runs with planning approval, verification, and bounded fixes, without merging or pushing code automatically. | |
| bitwig-gemini-mcp bedri/bitwig-gemini-mcp Enables AI agents to control and monitor Bitwig Studio in real-time using natural language commands through MCP and OSC. | |
| Email Send/Receive MCP Server bedro96/email-send-mcp Enables sending and receiving emails through SMTP, IMAP, and POP3 protocols with support for attachments, HTML content, and email validation. | |
| mcpelauncher-agent bedrock-mc/mcpelauncher-agent Enables controlling a real Minecraft Bedrock client by injecting input and reading frames through the launcher's agent socket, including launching, stopping, screenshotting, sending chat, and managing multiple bot instances. | |
| Signet bee-san/signet A provider-neutral MCP human approval gateway that requires explicit confirmation before executing write operations, supporting adapters like Fastmail and WhatsApp. | |
| Plan-MCP bee4come/plan-mcp An MCP server that uses Google Gemini AI to analyze requirements, create project plans, review code quality, and provide execution analysis feedback for software development projects. | |
| simple-ai-provenance beedev/simple-ai-provenance An MCP server that tracks AI prompts in Claude Code and automatically annotates git commits with the history of what was asked. It provides tools to query session summaries, retrieve uncommitted work, and manage AI provenance directly withi | |
| axonn-mcp beee003/axonn-mcp MCP server for Axonn, enabling access to US energy regulatory filings, real-time ISO prices, and market data. | |
| vynn-mcp beee003/vynn-mcp MCP server for Vynn — self-improving AI workflows & backtesting. | |
| earshot beeeeen/earshot Enables an Alexa+ assistant to answer home-care questions while keeping protected values off the spoken channel, delivering sensitive details privately to the asker's own device via an out-of-band inbox. | |
| Strava MCP Server beefsupreme21/mcp-hackathon Enables AI assistants to retrieve and display Strava activity data including workout details, distance, time, and dates. Currently uses sample data but can be extended for real Strava API integration. | |
| Gemini MCP Server beehiveinnovations/pal-mcp-server A Model Context Protocol server that gives Claude access to Google's Gemini 2.5 Pro for extended thinking, code analysis, and problem-solving with a massive context window. | |
| beeimg-mcp beeimg/beeimg-mcp Enables uploading images to BeeIMG, deleting images, and retrieving premium account info through a local stdio MCP server. | |
| CadKitty beejay805/cadkitty Enables AI assistants to build and edit native CAD parts and assemblies, inspect saved geometry and measurements, retain revisions, run mechanism and interference checks, and export STEP/STL/GLB artifacts through MCP tools. | |
| voice-gate beejsbj/voice-gate Enables MCP clients to submit completed speech or typed text to a self-hosted decision engine and receive judgments such as ordinary speech, command, retained thought, uncertainty, or no action, along with session and decision inspection. | |
| gmod-mcp beekamai/gmod-mcp MCP server for Garry's Mod enabling RCON command execution, Lua scripting, window control, screenshots, and SFTP file management. | |
| mcp-dotnet beekamai/mcp-dotnet Enables LLMs to read .NET assemblies as C# by providing tools to list types, decompile types, decompile assemblies, and search decompiled source. |
33,401–33,450 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.