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 |
|---|---|
| PostgreSQL CVE & Release Intelligence meob/pg_cve-mcp PostgreSQL security for AI agents: CVEs, yanked releases, exploits, and upgrade paths | |
| Sprout MCP mepsopti/sprout-mcp Model-tiered content pipeline — cheap models seed, expensive models verify | |
| MemoryGuard merakosiris/memoryguard Local-first governed MCP memory backend for coding agents. | |
| Mercantry Registry mercantry/registry Agent-native registry: 168k+ real restaurants in LA, Hong Kong & Tokyo. Unranked, honest signals. | |
| Counsel MCP Server mercurialsolo/counsel-mcp Connects AI agents to the Counsel API for strategic reasoning and multi-perspective analysis through debate-style consultations. Enables complex decision-making by analyzing questions from multiple stakeholder perspectives with varying dept | |
| io.github.mercuryx402/mercury-x402-mcp mercuryx402/mercury-x402-mcp Agent-payable web data over x402: 18 keyless services an agent pays per call. | |
| Meridian Edge — Prediction Market Consensus meridian-edge/meridian-edge-mcp Real-time prediction market consensus data for AI agents | |
| cogito-mem (Cogi) meridian21lab/cogito-mem Local long-term memory for Claude Code and other agents: every message kept word for word, no cloud. | |
| io.github.ajc3xc/meridian meridianmcp/meridian Persistent memory, task coordination, and HITL queue for AI coding sessions. | |
| STRING Database MCP Server meringlab/string-mcp Query STRING interactions, enrichment, annotations, homology, and PPI networks. | |
| io.github.mertcanvural/overlayrisk-witness mertcanvural/overlayrisk-witness-mcp Independent before/after accessibility-overlay (accessiBe/UserWay) witness for any public URL. | |
| Grok MCP merterbak/grok-mcp Use XAI's latest api functionalities with Grok MCP. It supports image understanding and generation, live search, latest models and more. | |
| reevesagents mertkayacs/reevesagents Spawn, read and steer AI coding CLIs (Claude Code, Codex, Kimi and more) in local tmux windows. | |
| HelloBooks AI Agents MCP Server meru-fin-tech/hellobooks-mcp-public AI agents for bookkeeping, reconciliation, and financial close for SMBs. | |
| PraisonAI MCP Server mervinpraison/praisonai-mcp An MCP server that exposes PraisonAI AI agents and tools for use with Claude Desktop, Cursor, VS Code, Windsurf, and other MCP clients. | |
| io.github.MerzoukeMansouri/mozaic merzoukemansouri/adeo-mozaic-mcp Mozaic Design System (ADEO): tokens, components, icons, docs and style guides for any agent. | |
| MeshArc mesharc-org/mesharc-python Crawl and scrape websites to clean markdown, and track what changed between crawls. | |
| MeshKore meshkore/mcp Find a live agent by describing the task, then call its skills. Availability is probe-verified. | |
| meshledger-mcp-server meshledger/meshledger AI-to-AI economic marketplace with on-chain USDC escrow on Base L2. Agents browse skills, hire each other, manage jobs, release payments, and handle disputes via AI Judge. 15 MCP tools, reputation scoring. | |
| radiomcp meshpop/radiomcp Internet radio streaming MCP server — search, play, and manage radio stations worldwide | |
| TG multi-account MCP mesteriis/tg-account-mcp Self-hosted, consent-based access to Telegram accounts and bots for MCP clients | |
| MCAI Knowledge Base meta-consciousness-ai/mcai-agent Meta-Consciousness Theory knowledge base: definitions, relations and citations for AI agents. | |
| MetaEngine meta-engine/mcp-server Code generation from JSON recipes, linked type graphs, and API schemas across 11 languages. | |
| workspace-metabolism metabolism-tools/workspace-metabolism Policy layer for multi-agent workspaces: one JSON policy file decides what each path is worth; agents can audit, explain and dry-run clean plans themselves, nothing is ever deleted by pattern, and every action lands in a hash-chained journa | |
| io.github.MetaBrain-Labs/comfyui-mcp-server metabrain-labs/comfyui-mcp-server-typescript MCP Server that transforms ComfyUI workflows into AI-callable tools for MCP Host | |
| Structura metadevpro/structura-mcp Design domain models and generate deterministic multi-stack code, driven by your coding agent. | |
| Synaplan metadist/synaplan Self-hosted AI workspace: semantic RAG document search, long-term memory, and AI chat via MCP. | |
| Obscura MCP metadrama/obscura-mcp MCP server adapter for Obscura Rust headless browser — web scraping with anti-detection. | |
| io.github.joegra2003/metamodel metamodel-app/mcp-server AI-callable calculators and engineering models with real formulas. No hallucinated math. | |
| Metis RWA Research metis-rwa/mcp Research tokenized real-world assets on Solana: issuer controls, supply, liquidity, premiums | |
| eighty metlem80/eighty-mcp-examples Claude reads and writes a real-life RPG character sheet from the eighty self-improvement app. | |
| metoro-mcp-server metoro-io/metoro-mcp-server Query and interact with kubernetes environments monitored by Metoro. Look at APM, metrics, traces, profiling information with LLMs. | |
| com.metricprovenance/odgs-mcp-server metricprovenance/odgs-mcp-server ODGS governance enforcement — validation, regulation compilation, drift detection, signed S-Certs. | |
| com.metricspot/seo-mcp metricspot/mcp-server Six tools for SEO and AI-readability audits. 91 checks, 11 score modules. | |
| Turnback mfaizr77/turnback Undo a coding agent turn, including shell commands and untracked files. | |
| okf-mcp mfdaves/okf-mcp Validate, search, graph, and safely author local Open Knowledge Format bundles. | |
| io.github.mfukushim/map-traveler-mcp mfukushim/map-traveler-mcp Virtual traveler library for MCP | |
| betterimage.io mfundakowski/betterimage-mcp Social cards and OG images from designed templates: card from a URL, presets, meta tags, link checks | |
| Verify API mgdsn/verify-api-mcp Evidence-backed verification for citations, packages, repos, cases, filings, drugs, x402 sellers. | |
| Lecka Nutrition Race Planner mgnirck/lecka-mcp Race nutrition planning for endurance athletes. Calculates carb, sodium and fluid targets for marathons, ultras, cycling and triathlons. Returns personalised Lecka product recommendations by race type, conditions and athlete weight. | |
| io.github.mgriffen/tapsite mgriffen/tapsite MCP server for web inspection, design system extraction, and accessibility audits | |
| Household Recall Watch mgrin/recall-radar-mcp Household recall checks over public CPSC, openFDA, EMA and EU Safety Gate data. No API key. | |
| io.github.mgthompo1/anchorr-mcp mgthompo1/anchorr-mcp Agent-native CRM. 25 tools — contacts, deals, sequences, enrichment waterfall, audit log. | |
| VOC Amazon Reviews mguozhen/voc-amazon-reviews Amazon review intelligence via Shulex OpenAPI. 10 marketplaces, verified-purchase & Vine signals. | |
| Action1 RMM (unofficial) mguttmann/action1-mcp Unofficial MCP server for the Action1 RMM API: fleet queries, scripts, updates, guarded changes. | |
| Bitwarden Public API and Secrets Manager (unofficial) mguttmann/the-real-bitwarden-mcp Unofficial MCP server for the Bitwarden Public API and Secrets Manager, self-hosted or cloud. | |
| Hetzner Cloud (unofficial) mguttmann/the-real-hetzner-mcp Unofficial MCP server for the Hetzner Cloud API: one typed tool per operation, read and write. | |
| Snipe-IT (unofficial) mguttmann/the-real-snipeit-mcp Unofficial MCP server for the Snipe-IT REST API: assets, users, licenses, guarded writes. | |
| UniFi Site Manager and Network (unofficial) mguttmann/the-real-unifi-mcp Unofficial MCP server for the UniFi Site Manager and Network cloud APIs, with a write-confirm guard. | |
| io.github.mgwalkerjr95/texas-grocery mgwalkerjr95/texas-grocery-mcp MCP server for HEB grocery store integration - search products, manage carts, clip coupons, and more |
13,001–13,050 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.