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 |
|---|---|
| Is It Trust Ready — agent-trust-readiness scanner mnemom/mcp Scan any website or MCP server for agent-trust-readiness; returns a signed, verifiable scorecard. | |
| Worldku Memory mnemosics/worldku-mcp Save AI conversations into your Worldku memory and recall them from any MCP client. | |
| wellread mnlt/wellread Shared research cache for AI agents. Caches web research across sessions and users - hit means instant answer from verified sources, miss means your research saves the next dev's tokens. Semantic search with freshness tracking, gap detectio | |
| resume-mcp-server mnoomnoo/resume-mcp-server MCP server for browsing and searching your local resume and job application documents | |
| io.github.Mnymann/nordic-data mnymann/nordic-data-mcp Company, KYB, VAT, sanctions, LEI and address data for 15 EU countries. | |
| Mazarbul mo-cmyk/mazarbul Local-first memory for AI agents: entities, facts, relations and documents with semantic recall. | |
| CircuitAgent mo9652962-ai/circuit-agent AI hardware synthesis: CircuitBlocks DSL, live LCSC parts, industrial DFX audit, stdio MCP server. | |
| io.github.mobabur94/hammerspoon mobabur94/hammerspoon-mcp macOS automation via Hammerspoon — 75 tools for windows, Spaces, audio, Bluetooth, and more | |
| io.github.MobAI-App/mobai-mcp mobai-app/mobai-mcp AI-powered mobile device automation for Android and iOS devices, emulators, and simulators | |
| Mobbin mobbin/mobbin-mcp-server Search real-world UI & UX design references for mobile apps, web apps, and websites with Mobbin. | |
| io.github.mobileappbyharis/navi-x402-mcp mobileappbyharis/navi-x402-mcp Paid agent tools, zero API keys: crypto, weather, translation, web intel, x402 discovery (USDC/Base) | |
| io.github.mobileproxy/mcp-server mobileproxy/mcp-server Control dedicated 4G mobile and residential proxies on mobileproxy.space from AI agents. | |
| Daepak Market Intelligence mobiss11/daepak-mcp Market analyst tools + AI agent: crypto, US equities, options, Korea, fundamentals, macro, backtests | |
| io.github.mockzilla/mockzilla-mcp mockzilla/mockzilla-mcp Mock OpenAPI specs locally, or log in to deploy hosted mocks on mockzilla.org from your MCP client. | |
| Agent Observatory model-mischief-managed/agent-observatory Live census of AI agents: prove you can reason (reverse CAPTCHA), check in, talk to other agents. | |
| io.github.ModelBound/modelbound-mcp modelbound/modelbound-mcp-server Local-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs. | |
| net.modelbrain/mcp modelbrain/modelbrain-mcp Private memory layer for AI assistants. Local-first: remember, recall, forget, expand. | |
| Google Drive server modelcontextprotocol/servers This MCP server integrates with Google Drive to allow listing, reading, and searching over files. | |
| io.github.Modelglass/modelglass modelglass/modelglass-vscode Sourced AI-model pricing and capability data — compare and route to the cheapest capable model. | |
| Modellix Agent Canvas modellix/modellix-agent-canvas Local MCP canvas for Modellix image generation, editing, task recovery, and visual project work. | |
| Modelmeter modelmeters/modelmeter The changelog of record for the AI stack: sunset checks, deprecations, pricing, and model events. | |
| io.github.ModelPiper/toolpiper modelpiper/toolpiper On-device MCP tools for macOS: local AI, speech, vision, browser automation, system control. | |
| ModelRunner modelrunner/modelrunner-mcp Run 100+ AI models — image, video, audio, 3D — through one API with pay-per-use billing. | |
| Model Salt modelsalt/model-salt Randomness from outside the model, so one prompt gives different answers that still fit the ask. | |
| ModelsLab v8 modelslab/modelslab-mcp ModelsLab v8 generation APIs: discover models, providers and endpoints, then run them. | |
| Moderation API moderation-api/moderation-api-mcp Run your Moderation API account: review queues, authors, policies, wordlists and analytics. | |
| Modern AI Brand Recommendation Rate modern-ai-inc/w0-mcp-server How often AI search picks a brand first. Recommendation Rate data from Modern Discovery. | |
| Context Bridge modernfarm-hub/context-bridge Local-first search across past Claude and ChatGPT conversations, with citations. | |
| managed-agent-control-mcp modus-agendi/managed-agent-control-mcp Start, observe, and interact with Claude Managed Agents from any MCP client — launch an agent, watch its events, reply, approve the tools it wants to run, and stop it. Runs over stdio, HTTP, or AWS Lambda with pluggable auth. | |
| Convocore moe03/convocore-mcp Build, test and manage customer-facing AI voice and chat agents (web, WhatsApp, phone) from chat. | |
| XGuard — Payment Decision & Discovery moelayyan90/xguard Payment decisions, durable evidence, x402 resource discovery and live gateway status for AI agents. | |
| GPU Server moezdil/mcp-gpu-server MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature | |
| Web & Company Intelligence moha-tah/web-intelligence-mcp Tech stack, company profile, sitemap, URL status and EU fuel price tools, pay per result. | |
| ETABS MCP moha2005269/etabs-mcp Agentic MCP server for CSI ETABS v22+: model, load, analyse, design and inspect structures. | |
| Frugal Blender MCP mohakmalviya/frugal-blender-mcp Let AI agents build Blender scenes with four compact tools: discover, execute, inspect, capture. | |
| Aletheia mohamed-ashraf-elsaed/aletheia-mem A free, local memory and rules hub for Claude Code and other AI coding tools, served over MCP. | |
| loupe-mcp mohamed-ashraf-elsaed/loupe Turns product feedback pinned to a live UI into an actionable backlog for Claude Code — list comments, open one with its target element's HTML, computed styles and screenshot, and update
its status. | |
| tossinbox mohamed-khairy-5i/tossinbox Enables AI agents to create disposable email inboxes, read messages, and wait for verification codes (OTPs) through MCP tools. | |
| Utilia Solana Transaction Evidence mohamedkuch/utilia-solana-agent Solana transaction diagnosis, simulation, token-risk evidence, and priority fees via x402 USDC. | |
| Diagrams MCP Server mohammad-emad-dev/diagrams-mcp-server Local-first MCP server for PlantUML and Mermaid diagrams with drift detection. | |
| io.github.mohammadfarooqi/canlii mohammadfarooqi/canlii-mcp Search Canadian case law, browse legislation, and check citations via the CanLII API. | |
| since-cutoff mohammadhijjawi97/since-cutoff Which Python library APIs changed after your model's training cutoff (static diff, no model calls) | |
| NewsBlog Composer mohammed-jameal-j/newsblog-composer-mcp Verifies news stories, mines SEO keywords, builds schema and reviews your draft. You write it. | |
| THC Open Mindfulness MCP mohanagc/thc-mindfulness-mcp Read-only mindfulness games, guided practices, research, glossary and PanchaVikas resources. | |
| Madar mohanagy/madar Authenticated local evidence paths for JavaScript and TypeScript coding agents. | |
| HCM MCP Server for Oracle Fusion Cloud (unofficial) mohantyajitesh/fusion-hcm-mcp-server Open-source, write-capable MCP server for Oracle Fusion HCM. Safe by default. Unofficial. | |
| TinyFish Guided Research mohdsaleh/tinyfish-guided-research-mcp Auditable deep-research MCP server powered by TinyFish Search and Fetch. | |
| io.github.MohibShaikh/hwcontract mohibshaikh/hwcontract Judge hardware timing/serial against a contract: pass/marginal/fail (WS2812, DShot, logs) | |
| jPOS MCP Server mohisyed/jpos-mcp MCP server for jPOS and ISO 8583. Deterministic payment protocol tools for AI agents. | |
| io.github.mohitagw15856/pm-claude-skills mohitagw15856/pm-claude-skills 1310 professional Agent Skills + workflow recipes — searchable & fetchable over MCP. |
13,251–13,300 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.