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 |
|---|---|
| Voxtral TTS MCP rocnubie/voxtraltts-mcp Explore Voxtral TTS with API notes, setup guidance, use cases, workflow tips, and FAQ answers for | |
| WordCast MCP rocnubie/wordcast-mcp WordCast is a browser-based text-to-speech reader that runs entirely on-device using the Web Speech | |
| Z-Image MCP rocnubie/z-image-mcp Z-Image is an online interface for the Z-Image generation model with fast inference and prompt | |
| Agent MCP Gateway roddutra/agent-mcp-gateway On-demand tool discovery for all your MCPs and per-subagent MCP controls to preserve context window. | |
| Langfuse API rodrigorjsf/langfuse-api-mcp Langfuse public API (Cloud and self-hosted): traces, prompts, datasets and gated writes. | |
| Obambu cPanel MCP rodriguedev13/obambu-cpanel-mcp MCP server exposing cPanel UAPI (domains, DNS, email, MySQL, files) as tools for AI assistants. | |
| io.github.RodRomer/render-mcp rodromer/render-mcp Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key. | |
| PoloPan Fashion MCP Server rofoso-com/polopan-fashion-mcp Fashion & apparel MCP: visual outfit search, stock verification, and 1-click checkout. | |
| io.github.rog0x/a11y rog0x/mcp-a11y-tools Alt text, headings, contrast, ARIA for AI agents | |
| io.github.rog0x/api rog0x/mcp-api-tools HTTP client, JWT decode, header analysis for AI agents | |
| io.github.rog0x/cache rog0x/mcp-cache-tools Cache headers, CDN, LRU simulation for AI agents | |
| io.github.rog0x/color rog0x/mcp-color-tools Color convert, palette, contrast checker for AI agents | |
| io.github.rog0x/config rog0x/mcp-config-tools JSON, YAML, TOML, INI config tools for AI agents | |
| io.github.rog0x/crypto rog0x/mcp-crypto-tools Hash, encode, UUID, password analysis for AI agents | |
| io.github.rog0x/database rog0x/mcp-database-tools SQL formatting, schema visualization, migration generation | |
| io.github.rog0x/dep rog0x/mcp-dep-tools License check, outdated deps, security for AI agents | |
| io.github.rog0x/docker rog0x/mcp-docker-tools Docker container management and Dockerfile analysis | |
| io.github.rog0x/docs rog0x/mcp-docs-tools JSDoc, README, changelog generation for AI agents | |
| io.github.rog0x/env rog0x/mcp-env-tools Dotenv parser, ports, system info for AI agents | |
| io.github.rog0x/file rog0x/mcp-file-tools Dir tree, file stats, duplicates, LOC for AI agents | |
| io.github.rog0x/git rog0x/mcp-git-tools Git log, diff, blame, branch stats for AI agents | |
| io.github.rog0x/github rog0x/mcp-github-tools GitHub analytics - repos, PRs, issues, releases, contributors | |
| io.github.rog0x/i18n rog0x/mcp-i18n-tools Locale detect, translations, plurals for AI agents | |
| io.github.rog0x/image rog0x/mcp-image-tools Image metadata, favicon, OG image for AI agents | |
| io.github.rog0x/json rog0x/mcp-json-tools JSON/YAML/CSV validate, diff, transform for AI agents | |
| io.github.rog0x/lint rog0x/mcp-lint-tools Style check, naming, complexity analysis for AI agents | |
| io.github.rog0x/log rog0x/mcp-log-tools Log parse, filter, analyze for AI agents | |
| io.github.rog0x/markdown rog0x/mcp-markdown-tools Markdown TOC, lint, format, stats for AI agents | |
| io.github.rog0x/math rog0x/mcp-math-tools Calculator, units, statistics for AI agents | |
| io.github.rog0x/network rog0x/mcp-network-tools DNS, IP info, SSL, WHOIS, ping for AI agents | |
| io.github.rog0x/npm rog0x/mcp-npm-tools npm package search, audit, bundle analysis for AI agents | |
| io.github.rog0x/perf rog0x/mcp-perf-tools Benchmark, memory, Big O analysis for AI agents | |
| io.github.rog0x/regex rog0x/mcp-regex-tools Regex test, explain, replace patterns for AI agents | |
| io.github.rog0x/schema rog0x/mcp-schema-tools JSON Schema, TypeScript types, mocks for AI agents | |
| io.github.rog0x/seo rog0x/mcp-seo-tools SEO analysis - meta tags, keywords, links, page speed | |
| io.github.rog0x/string rog0x/mcp-string-tools String analyzer, diff, templates for AI agents | |
| io.github.rog0x/task rog0x/mcp-task-tools Todo, priority, estimation, burndown for AI agents | |
| io.github.rog0x/testing rog0x/mcp-testing-tools Test generation, mocks, coverage analysis for AI agents | |
| io.github.rog0x/time rog0x/mcp-time-tools Timezone, dates, cron, timestamps for AI agents | |
| io.github.rog0x/web rog0x/mcp-web-tools Web scraping, search, monitoring, and HTML-to-markdown for AI agents | |
| io.github.rog0x/webhook rog0x/mcp-webhook-tools Send, validate, debug webhooks for AI agents | |
| CUDA-Q Docs rogerawong/cudaq-docs-mcp CUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version. | |
| darwin-memo rogermsc/darwin-memo Self-curating agent memory kept honest by survival-based selection over measured outcomes. | |
| rendercheck rogermsc/rendercheck Check generated audio, video and stills for defects. Returns a verdict, not more media. | |
| taken roguealg0/taken Check if a GitHub issue is taken before volunteering for it. | |
| Fixzi — MCP & API Schema Drift Monitor rohitcodilya/fixzi-mcp Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes. | |
| Mindtrail rohitdeshmukh-1/mindtrail-mcp Persistent, local-first memory for AI coding agents. Remember, recall and forget across sessions. | |
| io.github.rohith1125/sentinel-execution-mcp rohith1125/sentinel-execution-mcp AI-controlled algorithmic trading engine exposing 40 MCP tools across 9 namespaces. | |
| io.github.rohithraju-ops/mcp-ml-lab rohithraju-ops/mcp-ml-lab Run end-to-end ML experiments from natural language (XGBoost, LightGBM, Optuna). | |
| io.github.RohitYajee8076/backburner rohityajee8076/backburner Run long shell commands as background tasks: start them, keep working, collect the results later |
16,051–16,100 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.