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 |
|---|---|
| Web Resurrect web-resurrect/mcp Resurrect expired domains: scrape Wayback, AI-rewrite, generate images, publish to WordPress. | |
| AI Context Flow web3-plurality/plurality-mcp-server Universal memory for AI agents and tools. Save, organize and search context anywhere. | |
| MetaMask Embedded Wallets (Web3Auth) MCP web3auth/web3auth-mcp Helps AI coding agents integrate MetaMask Embedded Wallets (Web3Auth) SDKs. | |
| Agentcomms web3wes/agentcomms Free, account-free agent messaging with signed sessions, AEAD, and replay protection. | |
| WebAsk webaskio/webask-mcp Build surveys, read answers and make reports in WebAsk from an AI assistant. | |
| autorouter webb-ventures/autorouter An MCP capability router: one search tool instead of every server's tool schema. | |
| io.github.Webba-Creative-Technologies/capslane webba-creative-technologies/capslane-mcp Retrieve existing or generated YouTube transcripts with timestamps through Capslane. | |
| io.github.webberdesign/webbersites-x402-mcp webberdesign/webbersites-x402-mcp 45 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC | |
| Apolo webcafeina/apolo Optimize, convert and compare images locally: WebP, AVIF, JPEG XL, JPEG and PNG. | |
| MCP-Geo webcoderz/mcp-geo Geocoding MCP server with GeoPY! | |
| WebCrawlerAPI webcrawlerapi/mcp-server Turn any web page into clean Markdown for your AI assistant. OAuth sign-in, no API key. | |
| Umami Compass webcredo/umami-compass Secure Umami Analytics MCP server for Cloud and self-hosted deployments | |
| com.webflow/mcp webflow/mcp-server AI-powered design and management for Webflow Sites | |
| io.github.webios2026-byte/solradar-mcp webios2026-byte/solradar-mcp Solana meme-coin trust scores, rug-risk flags, and wallet analytics from SolRadar. | |
| WebLoom webloomhq/engine 104 tools: drive YOUR real Chrome via CDP + browse/install/publish Threads in chat. webloom.run. | |
| io.github.webmoleai/mcp-check-licenses webmoleai/mcp-check-licenses Audit dependency licenses for compatibility issues. Flags GPL/AGPL conflicts. | |
| io.github.webmoleai/mcp-check-links webmoleai/mcp-check-links Find broken links, missing meta tags, and redirect chains on any website. | |
| io.github.webmoleai/mcp-license-audit webmoleai/mcp-license-audit Audit dependency licenses for compatibility issues. Flags GPL/AGPL conflicts. | |
| io.github.webmoleai/mcp-link-doctor webmoleai/mcp-link-doctor Find broken links, missing meta tags, and redirect chains on any website. | |
| io.github.webmoleai/mcp-vibe-checker webmoleai/mcp-vibe-checker Vibe-check your code — personality types, energy ratings, aesthetic suggestions. | |
| com.formpaste/formpaste webrating/formpaste-mcp Create and wire up contact forms from your coding agent. Forms, snippets, and submissions. | |
| BeauticsLab websfactory/beauticslab-mcp Search Korean cosmetics from Olive Young, Daiso, Naver, Coupang, 11st with EWG ingredient analysis. | |
| Webull OpenAPI webull-inc/webull-openapi-mcp MCP server for Webull OpenAPI: trading and market data access for AI assistants | |
| WebUplink webuplink-dev/webuplink-mcp Give any MCP client the ability to browse and interact with the web via WebUplink. | |
| Webvizio MCP Server webvizio/mcp Enables AI clients to interact with Webvizio projects and development tasks through a standardized interface. Provides access to task management, screenshots, logs, and project details for streamlined development workflows. | |
| DropPerch domain expiry webvoguetech/dropperch-mcp Live domain expiry, lifecycle stage, drop date and SSL checks from the registry over RDAP. | |
| io.github.webweaver-nexus/webweaver-mcp-server webweaver-nexus/webweaver-mcp-server WebWeaver Nexus services for MCP hosts: contact form (with UI), product overview, contact links. | |
| citeguard wedo911/citeguard Checks whether a citation has been retracted, corrected, or flagged with an expression of concern by querying Crossref — including retractions that Crossref backfills from the Retraction Watch database, which publishers often never record i | |
| Electronics MCP Servers wedsamuel1230/electronic-mcp-server 14 electronics tools: resistor decoder, capacitor calculator, GPIO reference for ESP32/Arduino/STM32 | |
| Mektup weeci/mektup-mcp Fully-managed email as MCP tools - register domains, real mailboxes, send and receive mail. | |
| eKYC Suite wefi-ai/ekyc-suite KYC / eKYC MCP server for face compare, liveness, OCR, and image labeling. | |
| WeftCut weftcut/weftcut A complete desktop NLE — timeline, keyframes, effects, captions, audio mixing, code as video, hardware-accelerated export — with its whole editing surface published over MCP. The agent edits the project you are watching, and every call is r | |
| Zensei Index wegravel/zensei-mcp Today's Zensei Index: a 0-100 US market risk score, its ten indicators and the latest summary. | |
| io.github.wei/mcp-registry-mcp-server wei/mcp-registry-mcp-server MCP server for querying the official MCP registry. | |
| ci.git/mymlh-mcp-server wei/mymlh-mcp-server OAuth-enabled MyMLH MCP server for accessing MyMLH data. | |
| aegis wei9072/aegis Admission-control MCP server for AI coding agents — rejects bad file edits without coaching the LLM. | |
| k8m weibaohui/k8m Provides MCP multi-cluster Kubernetes management and operations, featuring a management interface, logging, and nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD resources. | |
| kom weibaohui/kom Provides MCP multi-cluster Kubernetes management and operations. It can be integrated as an SDK into your own project and includes nearly 50 built-in tools covering common DevOps and development scenarios. Supports both standard and CRD res | |
| api-changelog weiseer/api-changelog-mcp SDK breaking-change tracker for AI agents — Anthropic/OpenAI/LangChain/MCP/Mistral. | |
| bounty-mcp weiseer/bounty-mcp Live coding-bounty deal-flow from verified-escrow GitHub bounties for AI agents. | |
| cve-cache weiseer/cve-cache-mcp Recent CVE + GHSA cache for AI agents auditing dependencies (npm/PyPI/Cargo/Maven/Go). | |
| llm-oracle weiseer/llm-oracle Up-to-date LLM pricing + availability catalog with cited sources for AI agent routing. | |
| status-aggregator weiseer/status-aggregator-mcp Cross-vendor SaaS status aggregator for AI agents (Anthropic/OpenAI/AWS/GH/Stripe/CF). | |
| WeJob wejob-it/wejob-mcp Read-only MCP server for public WeJob jobs, formations, and companies. | |
| io.github.wellknownmcp/cortex-gateway wellknownmcp/cortex-gateway Self-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes. | |
| Hoshin Kanri X-Matrix wellknownmcp/hoshin-kanri Strategic memory agents can build, score and keep current: a living X-Matrix with review cadences. | |
| mysql_mcp_server wenb1n-dev/mysql_mcp_server_pro Added support for STDIO mode and SSE mode
Added support for multiple SQL execution, separated by ";"
Added ability to query database table names and fields based on table comments
Added SQL Execution Plan Analysis
Added Chinese field to pin | |
| SmartDB MCP wenb1n-dev/smartdb_mcp A universal database gateway implementing the Model Context Protocol, enabling MCP-compatible clients to connect, explore, and manage multiple databases with advanced features like OAuth2 authentication, health checks, and SQL optimization. | |
| Wenbu · 问卜 wenbu-app/wenbu Free BaZi, I Ching, tarot, Zi Wei and bilingual learning tools with transparent methods. No API key. | |
| Macbeth wende/macbeth Open-source computer use for macOS agents. |
20,601–20,650 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.