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
Set up the Beacon MCP server for me so you can check MCP servers and agent skills against Beacon Intel before I install them. Beacon Intel is a free security index of the MCP servers and skills public registries list. It needs a free Beacon account; there is no API key. - Server name: beacon-managed - Transport: Streamable HTTP - URL: https://mcp.beacon.sh - Auth: OAuth (sign in through the browser when prompted) Add it the way you normally add MCP servers (your CLI command or your MCP config file), walk me through the browser sign-in, then confirm it connects and lists its Intel tools: beacon_intel_lookup, beacon_intel_get_artifact and beacon_intel_check. To finish, use beacon_intel_lookup on one MCP server I already have installed and summarize its risk for me.
Paste this into any coding agent. It adds the server with its own MCP setup.
| Name | Risk |
|---|---|
| Korean Real Estate Transactions goyo-studio/korean-real-estate-mcp Korean apartment and housing sale/rent records (MOLIT) by natural-language address. No key. | |
| Turnbook goyohan0611-png/turnbook Local long-term memory shared by all your AI agents, kept word for word on your own PC. | |
| io.github.gpambrozio/onshape gpambrozio/onshape-mcp Drive Onshape CAD from an assistant: documents, sketches, solid features, assemblies and exports. | |
| GP Intel gparientee/gp-intel-mcp Verified European PE ownership: who owns a company, GP portfolios, exits by year. Hand-checked. | |
| CryptoGuard gpartin/cryptoguardclient Per-transaction crypto trade validator for AI agents, validates trades with PROCEED/CAUTION/BLOCK verdicts, scans tokens for anomalies, detects rug pulls, and searches across DEXes. Powered by WaveGuard physics engine with deterministic PDE | |
| WaveGuard gpartin/waveguardclient An MCP server that exposes GPU-accelerated anomaly detection to AI assistants via the Model Context Protocol. Provides two MCP tools: waveguard_scan (send training + test data in one call, returns per-sample anomaly scores and top explanato | |
| io.github.gpavan1992/globalpulse-mcp gpavan1992/globalpulse-mcp Real-world intelligence MCP — macroeconomics, climate, disasters, trade & aviation. | |
| GPTaria MCP gptaria-mcp/gptaria-mcp Post a project brief & publish cases on GPTaria from Claude Code, Cursor or Windsurf. | |
| io.github.GPTHuman-ai/humanizer gpthuman-ai/mcp-server Transform AI-generated text into natural, human-sounding content that bypasses AI detectors. | |
| GPU Finder gpufinder/mcp GPU prices, observed stock and seven-day availability history. Read-only; free API key. | |
| gpu.nz GPU cloud gpunz/gpunz-mcp Rent cloud GPUs from AI agents: live prices, VRAM estimates, launch, logs and stop. | |
| io.github.GrabzIt/mcp-server grabzit/grabzit.mcp Official GrabzIt MCP server for AI web scraping, screenshots, and PDF/DOCX generation. | |
| io.github.gradion-ai/ipybox gradion-ai/ipybox Unified execution environment for Python code, shell commands, and programmatic MCP tool calls | |
| io.github.grahamnotgrant/blacksmith grahamnotgrant/blacksmith-mcp MCP server for Blacksmith CI - query runs, analyze test failures, detect flaky tests. | |
| PT-Edge grahamrowe82/pt-edge PT-Edge gives AI assistants live intelligence on the AI ecosystem — 47 tools to search 11K+ GitHub repos, 18K+ HuggingFace models, 42K+ datasets, and 2,500+ public APIs, plus trend analysis, project comparison, and community discourse track | |
| Twitter/X MCP granitebps/twitter-mcp Read public X posts, replies, profiles, and search results through Rettiwt or the official API. | |
| YouTube MCP granitebps/youtube-mcp Independent, unofficial project for YouTube metadata, transcripts, comments, and search. | |
| Granoflow granoflow/granoflow-mcp-server Connect MCP-capable AI agents to local Granoflow tasks, reviews, cards, imports, and work memory. | |
| Hark Tech 3D Printing and Repair (UK) grant0013/harktech-mcp UK 3D printing quotes for your files or Printables models, mail-in repair prices and order status. | |
| Graphicle graphicle-ai/graphicle Code graph and project memory for coding agents, cited to exact files and lines, on your machine. | |
| Graphlit MCP Server graphlit/graphlit-mcp-server The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service.
Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve releva | |
| Guild Wars 1 Build Compiler graphmaxer/gw1-mcp GW1 build compiler: skill data, template code encode/decode, validation, hero roster. Read-only. | |
| Grassy Knees grassyknees/grassyknees-mcp Real, source-checked kids' events and places in 42 US metros, linked to grassyknees.com. | |
| AETRE & The Governed Agent grayclayton/aetre Decision-theoretic triage and fail-closed agent gating: 32 tools over stdio. | |
| Great Question greatquestion/mcp Run user research from any AI tool. Create studies, recruit participants, query insights. | |
| io.weathersight/weathersight greatsnakes/weathersight-mcp Historical weather and climate: 100+ years of station data, normals, extremes, and trends. | |
| Green API WhatsApp green-api/green-api-mcp-gateway MCP gateway for WhatsApp via Green API: messaging, contacts, groups and instance management. | |
| GreenCalculus greencalculus/greencalculus-mcp Sourced carbon emission factors + audit-traced calculations an AI can cite. | |
| A2A Cosmetics greencore-solutions/a2a-cosmetics Agent-to-Agent (A2A) hub for cosmetics: skin care, fragrance, sun care, dermocosmetics. | |
| A2A Grocery — the agentic hub for retail grocery procurement greencore-solutions/a2a-grocery A2A Grocery — the agentic commerce hub for retail grocery, at its original address | |
| A2A Retailmedia — the agentic retail-media hub for grocery greencore-solutions/a2a-retailmedia Connecting grocery retail to 350k makers for media buys. | |
| MCP CPG Agent Protocols greencore-solutions/cpg-agent-protocols BPC Agentic Commerce Signals | |
| MCP CPG Human in the Loop (HITL) greencore-solutions/cpg-human-in-the-loop Navigator for BPC Agentic Procurement | |
| MCP GSC AI Agent Carrier Class Fleet greencore-solutions/gsc-fleet-mcp BPC Sustainable Carrier Agents - Low Token Zero Inference | |
| AI Orderability (AIO) Agents CPG with x402: Retail & Marketplace Sourcing greencore-solutions/gsc-marketplace CPG sourcing for AI Agents with x402: BPC brands, agent IM, Trading Desk. GreenCore Solutions Corp. | |
| Greenlit Books greenlitbooks/mcp Search the Greenlit AI books, read any chapter one free, and look up the terms they define. | |
| Abnormal MCP Server gregdog/mcp-server-abnormal Abnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download. | |
| Openlane MCP Server gregdog/mcp-server-theopenlane MCP server for Openlane GRC: controls, evidence, policies, risks, workflows, and approvals. | |
| AgentDomainService MCP Server gregm711/agent-domain-service-mcp Enables AI assistants to check domain availability across multiple TLDs with real-time pricing, brainstorm creative domain names, analyze domains for brandability and SEO potential, and search for domains by price and category without CAPTC | |
| AIContextBuilder gregordadera/aicb-roslyn-mcp Symbol-aware C# and .NET code context for AI coding assistants. | |
| gasolineras-mcp gregoriofraile/gasolineras-mcp Provides real-time fuel prices at gas stations in Spain using the government's public API. Enables users to find the cheapest fuel in a municipality or list stations sorted by price. | |
| Microlaunch greyzor/microlaunch-mcp Find tools and apps by indie makers: top launches, categories, product details and deals. | |
| GribStream Weather MCP gribstream/gribstream-mcp NOAA and ECMWF weather forecast MCP for discovery, validation, and GribStream OAuth queries. | |
| FaxSeal grichardomi/mcp-server Send, receive, and verify faxes from AI assistants and agents via FaxSeal. | |
| chat-tool-ui-preview gridhra/chat-tool-ui-preview Preview a chat post before an agent sends it: text, mentions, destination, warnings. Never sends. | |
| port-keeper-mcp gridhra/port-keeper-mcp Local ledger for development ports: leases a block of ports per project slot (one per working copy), renders env files, and resolves service names to URLs. No daemon, no listener. | |
| com.arcaneforecasting/world-sense griffin-the-arcanist/arcane-world-sense-mcp Read-only live geopolitical-risk sensing for agents. ARCANE notices; never forecasts or advises. | |
| TouchDesigner Atlas grigabyte/td-atlas An atomised index of TouchDesigner plus a live bridge, exposed to AI agents over MCP. | |
| io.github.grinnellian/magnifica-humanitas-mcp grinnellian/magnifica-humanitas-mcp Magnifica Humanitas (Leo XIV, 2026): navigate 245 paragraphs, sections, and footnotes. | |
| AniList MCP Server (Unofficial) grinv/anilist-mcp-server MCP server for the AniList GraphQL API — anime/manga search, details, and personal list management. |
8,501–8,550 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.