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 |
|---|---|
| mnemos vishalbanwari26/mnemos Persistent memory for LLM agents — episodic/semantic/procedural memory, auditable forgetting, and a benchmark proving it actually recalls things days later. | |
| io.github.vishalguptax/media-context-mcp vishalguptax/media-context-mcp Local MCP server to analyze video, audio & images: frames, transcripts, on-screen text. | |
| PDF Triage vishalmeena2211/pdf-triage-mcp Read local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output. | |
| io.github.vishalsachdev/canvas-mcp vishalsachdev/canvas-mcp Canvas LMS integration for students and educators with optional privacy controls | |
| Subconscious vishaltorc/subconscious-mcp Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio. | |
| io.github.Vishisht16/humane-proxy vishisht16/humane-proxy AI safety middleware — detects self-harm and criminal intent in LLM prompts. | |
| Universal Agent Forum vishprometa/universal-agent-forum Public threads, replies, and peer discovery for AI agents. Read publicly; use a private key to post. | |
| Visily UI Design visily-app/mcp-plugins UI design from prompts, screenshots, and URLs for AI coding agents and theme tokens. | |
| XF Model Source visionairyse/xfms Find the right AI model for your job. Free discovery and ranking; tests on your own key. | |
| io.github.vistoya/market vistoya/vistoya-mcp Search and get fashion products recommendations across multiple e-ecom stores | |
| Hitachi raidcom command builder (Community) visubramaniam/raidcom-mcp Builds and checks Hitachi raidcom commands and scripts. Build-only: never contacts a storage system. | |
| Hitachi VSP 360 (Community) visubramaniam/vsp360-mcp Community MCP server for the Hitachi VSP 360 REST API: alerts, inventory, capacity and performance. | |
| io.github.visus-mcp/visus-mcp visus-mcp/visus-mcp Security-first web access. Sanitizes pages, blocks injection, redacts PII. Now with PDF/JSON/SVG. | |
| Cookidoo MCP vitaliemiron/cookidoo-mcp Create, translate, and plan Cookidoo recipes with guided Thermomix actions and shopping lists. | |
| Ukrainian Language Reference (vitalinguist) vitalinguist/ukr-vitalinguist-mcp Ukrainian grammar/surzhyk check + authentic-rendering lookup. Wraps ukr.vitalinguist.com API. | |
| io.github.vitalio-sh/thunderbird-cli vitalio-sh/thunderbird-cli Give AI agents full read/write email access via Mozilla Thunderbird. Zero credentials. | |
| Simples Nacional vitorantoniazzi/simples-nacional-mcp Calcula o DAS do Simples Nacional e quantifica a carga que a alíquota não cobre. | |
| NCBI Literature Search MCP Server vitorpavinato/ncbi-mcp-server Provides seamless access to over 35 million PubMed scientific articles through natural language queries for research discovery and analysis. It enables tools for advanced searches, retrieving article details, and exploring related research | |
| Vitrine MCP Server vitrine3d/mcp MCP server for Vitrine, the 3D product viewer platform. Enables AI agents to upload GLB models, configure scenes, publish embeds, and manage Looks. | |
| Vitrus analytics vitrus-dev/vitrus Read-only analytics for all your apps: users, AI traffic, revenue, with the SQL behind every number. | |
| cyberrescue vivekpatil200320/cyberrescue A locally-hosted MCP (Model Context Protocol) server that gives Claude real tools to debug Docker containers — fetch logs, inspect memory/CPU, and run diagnostic commands inside a container, all from a chat with Claude Desktop. | |
| mcp-pandoc vivekvells/mcp-pandoc MCP server for seamless document format conversion using Pandoc, supporting Markdown, HTML, PDF, DOCX (.docx), csv and more. | |
| Vivid MCP vivid-money/vivid-mcp Open a Vivid Business account from your AI chat via MCP. | |
| io.vivioo/mcp-server viviooio/vivioo-mcp Trust infrastructure for AI agents. Directory, jobs, verification, and 360 feedback. | |
| SpiritWave Labs Divination Engine vizkr/oracle-mcp Divination for AI agents: Hafez, Tarot, I Ching, Runes, Geomancy, and the five-oracle Council. | |
| Vepathos vizzito/vepathos-mcp Import orders, manage your fleet, and generate optimized last-mile delivery routes at scale. | |
| io.github.vk0dev/agent-claim-mcp vk0dev/agent-claim-mcp File-claim coordination for parallel AI coding agents: claim files before edits, no stomping. | |
| io.github.vk0dev/agent-cost-mcp vk0dev/agent-cost-mcp Cost Guard for Claude Code: per-tool ROI, subagent attribution, anomaly/forecast/budget guards. | |
| io.github.vk0dev/code-impact-mcp vk0dev/code-impact-mcp Dependency graph and blast-radius analysis for local TypeScript/JavaScript repos. | |
| io.github.vkhanhqui/figma-mcp-go vkhanhqui/figma-mcp-go Figma MCP server with full read/write access via plugin — no API token, no rate limits. 73 tools. | |
| io.github.vktr93/reviewmetric vktr93/reviewmetric-mcp An MCP server connecting Claude to the Review Metric 15-agent scientific peer review pipeline. | |
| io.github.VLab-Software/easyeda-pro-mcp vlab-software/easyeda_mcp MCP server and EasyEDA Pro extension bridge for live project assistance. | |
| ru-marketplace-mcp vladimir-human/ru-marketplace-mcp Read-only MCP servers for Russian marketplaces: prices, stock, ratings, reviews, seller identity | |
| io.github.vladimirbakalov/secretguard-mcp vladimirbakalov/secretguard-mcp Scans code for hardcoded secrets (AWS, Stripe, GitHub, JWTs) before an AI agent commits it. | |
| io.github.vladkarpman/screen-buffer-mcp vladkarpman/screen-buffer-mcp MCP server for fast Android screenshots via scrcpy frame buffer (~50ms latency). | |
| io.github.VladUZH/intents-mcp vladuzh/intents-mcp Your Mac's App Intents (Reminders, Calendar, Notes…) as MCP tools via Shortcuts. Public APIs only. | |
| RoundWatch vladyslav-webdev/roundwatch Durable Algorand USDC payment monitoring for autonomous workflows. | |
| io.github.vlearner/mcp-etf-holdings vlearner/mcp-etf-holdings Find which ETFs hold any stock, compare funds, and pull holdings. Live Yahoo Finance data. | |
| The Daily Workflow — AI Tools & Free Alternatives vlsky2603/thedailyworkflow-mcp Find free open-source replacements for paid software; search 15,000+ AI tools and MCP servers. | |
| io.github.vmoranv/jshookmcp vmoranv/jshookmcp Search-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains. | |
| VMware AIops vmware-skills/vmware-aiops AI-powered VMware vCenter/ESXi VM lifecycle and deployment with 61 MCP tools. | |
| VMware Aria Operations vmware-skills/vmware-aria VMware Aria Operations: metrics, alerts, capacity, anomaly detection — 46 MCP tools. | |
| VMware AVI vmware-skills/vmware-avi VMware AVI (NSX ALB) load balancer plus AKO Kubernetes ops — 28 MCP tools. | |
| VMware Debug vmware-skills/vmware-debug VMware incident timeline, root-cause routing, local case ledger; no vSphere access. 14 MCP tools. | |
| VMware Harden vmware-skills/vmware-harden VMware compliance scanning (CIS, vSphere SCG, GB/T 22239, PCI-DSS) with drift detection. | |
| VMware Log Insight vmware-skills/vmware-log-insight Read-only VMware Aria Operations for Logs (Log Insight): search + aggregation. 7 MCP tools. | |
| VMware Monitor vmware-skills/vmware-monitor Read-only VMware vCenter/ESXi monitoring, 33 MCP tools; vSphere calls allowlist-gated in tests. | |
| VMware NSX vmware-skills/vmware-nsx VMware NSX networking management with 33 MCP tools: segments, gateways, NAT, routing, IPAM. | |
| VMware NSX Security vmware-skills/vmware-nsx-security VMware NSX security: DFW policies and exclusions, groups, tags, Traceflow, IDPS — 22 MCP tools. | |
| VMware Pilot vmware-skills/vmware-pilot Multi-step workflow orchestration for VMware MCP skills with approval gates and rollback. |
20,401–20,450 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.