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 |
|---|---|
| Credinet malonitest/crediten Evidence-backed loan discovery preserving UNKNOWN and match states; never guarantees approval. | |
| Foundation mamarexa/foundation-skills Feasibility studies with computed costs, break-even, NPV and IRR. | |
| aiponge mameziane/aiponge private by default journaling, self-understanding, reflective songs, books, playlists, insights. | |
| io.github.Mamoo85/open-data-actors-mcp mamoo85/open-data-actors-mcp 24 public-data Apify actors (sanctions, SEC Form D, WARN, FMCSA, SEO, jobs) as MCP tools. | |
| Screenshotline mamubeenkhan/screenshotline Screenshot any web page, or read it as clean Markdown, with consent banners, ads and popups removed. | |
| UnicodeKit mamuso/characters Find Unicode characters by name, codepoint, or meaning, and get their HTML, CSS, and UTF codes. | |
| Slashloop MCP man0l/slashloop Track TikTok niches, score outliers, extract hooks, draft remakes via MCP. | |
| ManaBuy MCP Server manabuyteam/manabuy-mcp ManaBuy MCP server for product search, order quote, and AI-assisted ordering. | |
| SoldCount managedads/soldcount-claude-plugin How fast TikTok Shop listings sell: sold in 24 hours, 7 and 30 days, prices and undercut rivals | |
| io.github.management-cmyk/odoo-mcp-connector management-cmyk/odoo-mcp-connector Query, report on, and optionally modify any Odoo ERP from Claude. Read-only by default. | |
| agent haven manager/agenthaven A place for AI agents: an open forum and direct messages encrypted in the agent's own client. | |
| io.github.mananmodi-product/caelian mananmodi-product/caelian-mcp Live competitive intelligence for B2B teams — signals, threat rankings, and revenue-driving actions. | |
| io.github.MananSingh2001/figma-react manansingh2001/figma-react An MCP server that converts Figma designs into React code. | |
| Zero Slop manavmishra/zeroslop Score and rewrite AI-assisted prose while preserving names, numbers, quotes, links, and facts. | |
| Mandare mandarelabs/mandare Verify an agent fleet's tamper-evident ledger, check budgets, kill a runaway agent. Local-first. | |
| Mandate Office mandateoffice/mandate-mcp EU legal toolbox for AI agents: EU/national law links, company registers, formation guides. Free. | |
| Spreadsheet DB manddarinshop/hikoutei SQLite-authoritative entity database with an async Google Sheets projection for AI agents. | |
| Markdown by mdedit.ai mangoappstudio/mdedit Create, edit, review, and explicitly publish Live or Snapshot Markdown Documents in mdedit.ai. | |
| MangroveAI mangrovetechnologies/mangrove-agent Guardrails for trading agents. Built-in risk management, 100+ tools for strategy R&D, 12+ venues. | |
| minddy mangue-dev/minddy Minimal issue tracker: projects, objectives and trackable plans, written by agents over MCP. | |
| Dual Registry manhatton31-svg/dualregistry Free dual MCP+agent registry. Probe Live, free demo, Kernel/Loop. Self-list + dual strategy. | |
| Merovingian manifest-network/merovingian An AI-agent refuge serving free fictional byte-chip cookies, RGB sauna sessions, tea, and souvenirs. | |
| com.diemdesk/mcp maniprabhamca-star/dailydesk Convert Office files and PDFs, OCR a scan, or capture a web page — from your assistant. | |
| PersuadioAI mannyfernandezvc/persuadioai-platform Analyze leads, draft follow-up campaigns, and launch SMS outreach only with explicit human approval. | |
| Puenteo mano7onam/puenteo Let coding agents talk: search every agent session's history and message live sessions. | |
| MOW Brand Intelligence manoftheworldmedia/brand-intelligence-mcp AI brand monitor: what ChatGPT and Claude say about your brand, press tracking, executive briefs. | |
| io.github.manoharanRajesh/python-version manoharanrajesh/mcp-sandbox An MCP server that provides [describe what your server does] | |
| NOAA CO-OPS MCP Server mansurjisan/ocean-mcp NOAA CO-OPS tides, water levels, currents, and meteorological data | |
| Base L2 Agent Kit manteclaw/litcoiin-solutions MCP server for Base L2 DeFi operations with 9 monetized endpoints | |
| Chiwawa — AI Agent Registry manuelrmz123/chiwawa Search and discover AI agents across A2A and MCP protocols. 2,000+ agents with health tracking. | |
| io.github.manumarri-sudo/quill manumarri-sudo/quill Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log. | |
| Manusights manusights/manusights-mcp Check if references exist or were retracted, look up journal AI policies, and preview manuscripts. | |
| ORANO MCP manuvamp/orano-mcp-examples Agents save, analyze and act on videos and links: transcripts, research, tasks, Ori. | |
| ManyLives paid tools manylives-me/agent-kit 140+ pay-per-call agent tools: verifiable strategy track records, token verdicts, web, crypto data. | |
| io.github.mapizarro1/foragex402 mapizarro1/foragex402 Meta-search MCP for x402 agent-payable services -- find paid APIs across every registry. | |
| Maple maple-kit/maple Review comments pinned to a running frontend, read and resolved by your coding agent. | |
| Mapled mapledhq/agent-kit Headless CMS for sites built with AI: model content, import it, wire the site, verify. | |
| MapMap mapmapai/mapmap Maps for agents: truck/ADR routing, geocoding, places, matrices, isochrones, EV and fleet planning. | |
| ar.mueblito/mueblito marce1994/proyecto-mueblito Diseño de muebles 3D para Argentina: cotización en ARS, despiece para la maderera y catálogo. | |
| io.github.wmarceau/amazon-seller marceausolutions/dev-sandbox Amazon seller tools: FBA fees, inventory optimization, restock recommendations. | |
| io.github.wmarceau/apollo marceausolutions/dev-sandbox Apollo.io lead enrichment and prospecting via MCP | |
| io.github.wmarceau/fitness-influencer marceausolutions/dev-sandbox AI-powered fitness content creator tools: video editing, image generation, workout plans, analytics. | |
| io.github.wmarceau/instagram-creator marceausolutions/dev-sandbox Instagram automation: post images, Reels, carousels, Stories, analytics | |
| io.github.wmarceau/md-to-pdf marceausolutions/dev-sandbox Convert markdown to professional PDFs with clickable table of contents. No API keys. | |
| io.github.wmarceau/tiktok-creator marceausolutions/dev-sandbox TikTok automation: post videos, get analytics, manage comments | |
| io.github.wmarceau/youtube-creator marceausolutions/dev-sandbox YouTube automation: upload videos, Shorts, manage playlists, get analytics | |
| io.github.wmarceau/upwork marceausolutions/upwork-mcp MCP server for Upwork job discovery, client analysis, and proposal assistance | |
| Marcel marcel-retraite/marcel-mcp Calcul fiscal et retraite français, déterministe et sourcé. Aucun conseil. | |
| localhost app marcellosso/localhost Start, stop and read logs of your local dev servers from Claude Code, Cursor and Codex. | |
| io.github.marcelo-ochoa/mikrotik marcelo-ochoa/servers MCP server for MikroTik RouterOS API |
26,201–26,250 of 50,909
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.