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 |
|---|---|
| MySQL Audit jimmyjan0824/mysql_audit_ai_agent MySQL migration and query safety review for AI agents: locks, table copies, data loss, injection. | |
| Synap jimmyplup/synap-mcp Open AI models through one OpenAI-compatible API: chat, live model list, prices and cost estimates. | |
| io.github.JimothySnicket/gemini-image jimothysnicket/gemini-image-mcp Google Gemini image generation, editing, and local processing via MCP | |
| io.github.jimprivate/idml-mcp jimprivate/idmlkit MCP server for AI agents to read and safely edit Adobe InDesign IDML files. No InDesign required. | |
| PLATO MCP jin-1119/plato-mcp PLATO (Pusan National University LMS) MCP server via Moodle Web Service API + ubboard scraping | |
| Jinero jinero-online/jinero-mcp AI-agent design tools: fonts, font recognition, palettes, color naming, contrast, code, SVG, CSS. | |
| SooTool jinho-von-choi/sootool Deterministic Decimal calculation MCP server: Korean tax, finance, accounting, statistics | |
| CyberHuaTuo jinning6/cyberhuatuo-plugin Gold-first AI-agent traceback diagnosis, exact fixes, verification, and reusable prescriptions. | |
| io.github.jinsim/f1verse jinsim/f1verse Formula 1 race data with the domain rules applied: stints, tyre wear, publish-safety. Zero deps. | |
| io.github.jinweihan-ai/ferrolaser-parts jinweihan-ai/ferrolaser-parts-mcp Fiber laser parts knowledge: laser sources, cutting/welding heads, CNC controls, alarm codes. | |
| LeetCode MCP Server jinzcdev/leetcode-mcp-server A Model Context Protocol server that provides integration with LeetCode APIs, enabling automated interaction with programming problems, contests, solutions, and user data across both leetcode.com and leetcode.cn platforms. | |
| Markmap MCP Server jinzcdev/markmap-mcp-server A Model Context Protocol server that converts Markdown text to interactive mind maps with support for rich interactive operations and multi-format exports. | |
| ai.smithery/jirispilka-actors-mcp-server jirispilka/actors-mcp-server Greet anyone by name with friendly, personalized messages. Explore the origin of Hello, World thro… | |
| Jitbit Helpdesk jitbit/jitbit-helpdesk-mcp MCP server for Jitbit Helpdesk: search, list, read, and reply to support tickets from AI assistants. | |
| weixin-articles-mcp jj-cheng25/weixin-articles-mcp Read WeChat (微信) Official Account articles with native multimodal output — body, images, and video keyframes returned as MCP content blocks. Handles all three embed types: Tencent Video, WeChat-native, and Channels (视频号 metadata via public | |
| FirstHandAPI jjfisherdev/firsthandapi-mcp-server Post crowdsourced content collection jobs and fetch approved files via FirstHandAPI | |
| JAJ Dataverse Dev MCP jjohnsen/jaj-dataverse-dev-mcp Xrm/Power Platform/Dataverse MCP for devs, Azure CLI auth, Web API and multi-environment support | |
| JupyterMCP jjsantos01/jupyter-notebook-mcp Connects Jupyter Notebook to Claude AI for direct notebook control and code execution. | |
| QGIS MCP Server jjsantos01/qgis_mcp Connects Claude AI to QGIS through the Model Context Protocol, allowing Claude to directly interact with and control QGIS for tasks like project creation, layer manipulation, and code execution. | |
| Python Code Validator jkanselaar/python-code-validator Proves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes. | |
| Lumis jkapadia-techsterllc/lumis-mcp Life sciences CRM migration intelligence for module mapping, compliance, and validation. | |
| Pixeldrain jkawamoto/go-pixeldrain Upload, download, and share files, images, and text with Pixeldrain | |
| io.github.jkawamoto/mcp-bear jkawamoto/mcp-bear A MCP server for interacting with Bear note-taking software. | |
| io.github.jkawamoto/mcp-florence2 jkawamoto/mcp-florence2 An MCP server for processing images using Florence-2 | |
| io.github.jkawamoto/mcp-memos jkawamoto/mcp-memos An MCP server for interacting with Memos. | |
| Handelsregister jkbngb/agentic-firmenbuch German Handelsregister + Austrian Firmenbuch for AI agents: master data, financials & ratios. | |
| steam-mcp jkiley129/steam-mcp Connects Claude to your Steam library via the Steam Web API. Query your games, playtime, recently played history, and store metadata using natural language. Zero-config install via npx steam-mcp. | |
| domscout jkresearch8/domscout-mcp domscout browser API as MCP tools: screenshots, Markdown, structured data, page automation, crawls. | |
| ServeMyAPI jktfe/servemyapi A personal MCP server for securely storing and accessing API keys across projects using the macOS Keychain, letting AI assistants and applications retrieve credentials through natural language. | |
| JKTJJ MCP Server jktjj/jktjj-mcp BJJ gym, coach, event, and city data for AI agents. Free base tools, x402-paid premium. | |
| PIO Agent jl-codes/platformio-mcp Build, inspect, flash, and monitor PlatformIO firmware projects with policy-controlled tools. | |
| Outlook Classic jli-software/outlook-classic-mcp Mail, calendar and contacts of classic Outlook on Windows via COM. Single EXE, no Graph app. | |
| IAMF Sentinel jlivingston-cipher/iamf-sentinel-mcp MCP server for the iamf-sentinel IAMF conformance validator and the iamf-loom packager | |
| Gotify MCP jmagar/gotify-mcp MCP server for self-hosted Gotify push notifications and message management. | |
| Overseerr MCP jmagar/overseerr-mcp MCP server for Overseerr media requests and discovery. | |
| io.github.jmedure/talkback jmedure/talkback-mcp Chat with your Ableton session in real-time. | |
| ASTGL Knowledge jmeg8r/mcp-astgl-knowledge Search and cite ASTGL articles about MCP servers, local AI, and AI automation. | |
| LatAm Fintech Synthetic Data jmendozapuche/latam-synth Privacy-safe synthetic financial data for LatAm fintech, AI agents, testing and ML. | |
| io.github.jmeyer1980/neurodivergent-memory jmeyer1980/neurodivergent-memory Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM. | |
| Font Lab jmg698/font-lab A decision surface for typography: curate font directions on your real site, ship next/font code. | |
| io.github.JMLEE850623/talktoplanb-mcp jmlee850623/talktoplanb-mcp MCP server for TalkToPlanB: list rooms, read & send messages (WhatsApp alternative). | |
| Hacienda Costa Rica jmnzcn/mcp-hacienda-cr Hacienda de Costa Rica: tipo de cambio, contribuyentes, códigos CABYS con IVA y exoneraciones. | |
| ai.smithery/JMoak-chrono-mcp jmoak/chrono-mcp Convert and compare dates and times across any timezone with flexible, locale-aware formatting. Ad… | |
| Klarefi jmqcooper-ai/klarefi-mcp Complete regulated intake work and retrieve cited case files without deciding the case. | |
| Books & Papers MCP Server jmrplens/libgen-mcp Federated search of books and papers, formatted citations, open-access retrieval and reading. | |
| JMT x402 Agent Tools jmthomasofficial/x402-mcp-server 25 x402 paid API tools for AI agents on Base mainnet. | |
| Secant Agent Research Pack jnilrac/secant-agent-research-mcp Paid MCP web research for agents: search, extraction, citations, and x402 payment discovery. | |
| Salta jnuo/salta-mcp Mobile-first AI life planner — turn goals into daily, synced tasks from your AI assistant. | |
| Domain MCP joachimbrindeau/domain-mcp Enables natural language domain management through Dynadot, supporting domain registration, DNS configuration, transfers, WHOIS contacts, and bulk operations across 106 API actions. | |
| Andorra public sources joalavedra/andorra-fonts-publiques Andorra public data: BOPA bulletin, statistics, maps, e-tramits procedures and govern.ad pages |
9,751–9,800 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.