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 |
|---|---|
| Grok FAF wolfe-jam/grok-faf-mcp Persistent project context for xAI Grok. IANA-registered .faf format. | |
| mcp-better wolfe-jam/mcp-better AAIF-verified modern MCP setup optimised to the 2026-07-28 model (BETTER textbook). | |
| MCP Context Card wolfe-jam/mcp-context-card MCP server for a project's context (AGENTS.md), memory, and identity — base or drop-in extension. | |
| Rust FAF wolfe-jam/rust-faf-mcp Persistent project context — Rust-native MCP server. IANA-registered .faf format. | |
| Rust MCP Preflight wolfe-jam/rust-mcp-preflight Check an MCP Registry listing before you publish: README mcp-name line, server.json, name. | |
| openaaas-mcp-adapter wolido/openaaas Python MCP adapter connecting Claude/Cursor/Cline to the OpenAaaS scientific agent network. | |
| Korea Business Verify (KBV) wonderfulian/kbv-server Korea import requirements by HS code, plus Korean company lookup by name, status and KYB checks. | |
| hatchable-mcp woobox/hatchable-mcp Build and host full-stack web apps and sites on Hatchable from any MCP client. Each project gets a dedicated Postgres database, auth, storage, custom domains, and cron. | |
| SearchHub woodcoal/searchhub Aggregate Serper, Tavily, Exa and AnySearch behind one MCP-ready API with key rotation and quotas. | |
| Monumenten woonstadrotterdam/mcp-monumenten Look up Dutch BAG verblijfsobject IDs and monumental status. | |
| io.github.woonyong-choi/hermes-agent-mcp woonyong-choi/hermes-agent-mcp Operate a local Hermes Agent install over stdio: tasks, cron, config, gateway, doctor. No network. | |
| adr-skills wooxogh/adr-mcp-setup Automatically generates Architecture Decision Records (ADRs) from Claude Code conversations using Claude Opus. Features AI quality review,
duplicate detection, and dependency graph. | |
| io.github.worakorn-prince/th-memory-mcp worakorn-prince/th-memory-mcp Local long-term memory MCP server (SQLite) for AI coding agents — OpenCode, Claude Code, Cursor | |
| io.github.Wordpressistic/bridgistic wordpressistic/bridgistic-claude-marketplace Connect Claude to WordPress safely: signed requests, scoped keys, approvals, logs, snapshots. | |
| APIFold work90210/apifold Turn any REST API into a hosted MCP server. 18 free public servers (GitHub, Stripe, Slack, OpenAI, Notion, and more) — no setup required, bring your own API key. | |
| io.github.World-999-Labs/proof-layer world-999-labs/proof-layer Signed, hash-chained provenance receipts for AI agent actions. | |
| markets.tally/mcp worldclasstom/tally-mcp AI risk officer: private trading theses, evidence, exit criteria and decision history. No execution. | |
| pro.worldclock/time worldclockpro/worldclock-mcp A real clock for AI agents: current time, timezone conversion, and DST facts from the IANA tzdb. | |
| World Weather Online worldweatheronline/wwo-mcp Global weather API: forecasts, historical data, marine, ski, astronomy and timezone. | |
| MindCore Memory MCP woshilaohei/mindcore-memory-mcp AI long-term memory MCP server with importance scoring and confidence calibration | |
| Woven woven-video/woven-mcp Make and edit videos in Woven, the AI video editor for Mac. Needs the Woven app. | |
| WoWSQL wowsql/mcp-server Managed Postgres MCP: projects, SQL, docs search, and storage buckets via OAuth. | |
| Chestnyi Znak MCP Server woyaxnini/mcp-chestnyi-znak MCP server for Chestnyi Znak — Russian product marking system. 10 tools: codes, documents, stocks. | |
| io.github.woyaxnini/max-messenger woyaxnini/mcp-max-messenger MCP server for MAX Messenger by VK. 21 tools: messages, media, buttons, members, events. | |
| Ozon Seller MCP Server woyaxnini/mcp-ozon-seller MCP server for Ozon Seller API. 26 tools: products, prices, orders, analytics, finance, rating. | |
| Wraps Email for Amazon SES wraps-team/wraps-js Send email through your own Amazon SES account, and check domain verification, the suppression list and sandbox status. Works with any SES account; Wraps adds send history and delivery events. | |
| WRDO wrdo-development/wrdo-mcp-connector Local businesses, menus and price lists in Cape Town and the Western Cape; start a request in WRDO. | |
| io.github.wrenchpilot/it-tools-mcp wrenchpilot/it-tools-mcp MCP server exposing 100+ IT tools and utilities for developers and system administrators. | |
| wrg-sigma-rules wrg-11/wrg-sigma-rules Sigma detection rule writing, validation, and pySigma-based multi-backend conversion (Splunk, Elastic, Wazuh, Kibana) via 3 MCP tools and 3 Claude Code skills, backed by a 61-rule production corpus across 11 MITRE ATT\&CK tactic categories. | |
| io.github.Writbase/writbase writbase/writbase MCP-native task management for AI agent fleets with scoped permissions and provenance. | |
| io.github.write-space/writespace-mcp write-space/writespace-mcp Persistent docs and memory for AI agents — read, write, organize & search a shared workspace. | |
| WARM writerslogic/warm Local persistent memory for AI agents with recall, search, forgetting, and encrypted storage. | |
| io.github.writesdavid/open-primitive writesdavid/open-primitive-api 33 tools, 30 US federal data domains. Ed25519 signed, provenance chains, entity graph. Free. | |
| io.github.alexlarcheveque/writio writio/mcp-server LinkedIn-native AI content creation, scheduling & analytics via MCP. | |
| com.writulos/scribe writulos/writulos-mcp Generate clean markdown documentation for your code — one file, or up to 20 in one batch. | |
| online.pageaudit/pageaudit wrpbr/pageaudit Technical SEO, passive security and page-delivery audits with evidence and suggested fixes. | |
| WSAPI WhatsApp MCP Server wsapi-chat/wsapi-mcp Enables AI assistants to interact with WhatsApp through the WSAPI service, supporting comprehensive messaging, contact management, group operations, and account management functionality. Allows sending various media types, managing chats, a | |
| io.github.WSattazahn/caveat-lang wsattazahn/caveat-lang Authoring bridge for Caveat: validate, check and test programs; explain decisions; find dependents. | |
| io.github.wspringer/math-svg-mcp wspringer/math-svg-mcp Convert LaTeX math expressions to crisp, scalable SVG images | |
| Ableton Live MCP Server wstierhout/ableton-live-mcp Control Ableton Live with 156 typed tools for music production and offline .als analysis. | |
| EU e-invoicing and business checks (EN 16931, Peppol, VAT, sanctions) wsystemdev/eu-business-data-mcp EN 16931/XRechnung e-invoice validate+create, Peppol routing, EU VAT/EORI, sanctions, KYB. Free tier | |
| io.github.wtronk/geolocation-mcp wtronk/geolocation-mcp Geolocation tools (reverse geocoding, ip lookup, etc) using Jeleo Geolocation API | |
| io.github.wtznicy/my-websearch wtznicy/my-websearch MyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required. | |
| Tool Pantry wu736139669/toolpantry-mcp Find and use 216 free browser tools for PDF, images, video, audio and text that run locally. | |
| AI-HIVE AIGC wubin1836/ai-hive-mcp-server Generate and edit images and videos for ecommerce, marketing and advertising with AI-HIVE. | |
| SAP SuccessFactors wudaoyou/successfactors-toolkit SAP SuccessFactors OData and Compound Employee queries with PII tokenization for AI agents. | |
| io.github.wujinkim/korea-business-verify wujinkim/korea-business-verify 한국 사업자 검증 액션 MCP 서버 — 진위확인·휴폐업·과세유형·세금계산서 발행 가능 여부 (국세청 공공데이터 기반) | |
| LiuHe wulun811/liuhe LLM-native code tools: 44 MCP tools for AI agents to read, understand and modify code. Rust tree-sitter parse daemon (crash-isolated), SQLite symbol index (repo map 98ms), transactional journal-backed writes, deterministic quality gates (ze | |
| Wuniq KE (Knowledge Engine) wuniq/wuniq-mcp The structured memory layer your AI is missing. Requires the free Wuniq desktop app. | |
| CRIC物业AI MCP Server wuye-ai/mcp-server-wuye-ai Enables users to access real estate property industry news daily and search a specialized knowledge base covering laws, regulations, company info, and more. |
20,751–20,800 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.