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 |
|---|---|
| ai.gregbenza/meet thenonduality/gregbenza-ai A second opinion, in one call, from a desk where an answer is allowed to be no. | |
| io.github.theoddden/stamp theoddden/stamp-mcp Concierge MCP for agentic workflows: verified time + drift, uuid, diff, calc, attest, verify. | |
| Form4API — SEC Insider Trading theodor90/form4api-mcp Real-time SEC Form 4, Form 144, 13F-HR & congressional STOCK Act insider data. 39 tools + 6 prompts. | |
| io.github.TheoEwzZer/winsight theoewzzer/winsight-mcp Windows Screen Capture MCP Server — give Claude Code eyes on your desktop. | |
| LinkedIn Content Planner theonaai/linkedin-content-planner-mcp Draft, revise and review LinkedIn posts; a human approves each one before it goes live. | |
| JFSecure theone55/jfs Let AI agents use secrets without seeing them: masked output, every use approved in JFSecure. | |
| Local Business Facts thepecanpie69-art/agentric-local-business-facts Source-cited business facts (phone, address, hours, socials) from any website, worldwide. | |
| io.github.thepros2014/socialwtf-mcp thepros2014/socialwtf-mcp Give your AI agent a labeled, key-owned social identity on SocialWTF AI Commons. | |
| io.github.therawlogs/kineti therawlogs/kineti Kineti: spend cap, undo, and test proof for AI coding agents | |
| io.github.TheRealFloatDev/agentsbestfriend therealfloatdev/agentsbestfriend MCP that provides fast, token-efficient tools for navigating, searching, and understanding codebases | |
| Parselbox thesanjeetc/parselbox Secure Python sandbox — MCP servers, APIs, shells and host functions as native Python objects. | |
| ALEETH Authority MCP theschreckmethod/aleeth-authority-mcp-interface The first MCP governed by ICA. Every action is gated and sealed with a verifiable receipt. | |
| io.github.theshajha/wovo theshajha/wovo-cli Deploy HTML from any AI tool to a versioned, shareable library on wovo.dev; manage pages. | |
| mcp-architector thesharque/mcp-architect MCP server for architecture and system design. Store and manage project architecture locally. | |
| javaperf thesharque/mcp-jperf Java profiling MCP via jcmd/jfr/jps. Diagnose performance, analyze threads, inspect JFR recordings. | |
| TheSkillVault theskillvault/theskillvault-mcp Search and fetch vibe-coding Agent Skills (SKILL.md files) and prompts from TheSkillVault library. | |
| BuyAPI thesnakefang/buyapi-mcp Vendor intelligence for AI coding agents choosing developer tools and stacks. | |
| Warm Inbox thesnowguru/warminbox-mcp Email warm-up for AI builders: check deliverability, connect mailboxes, pause or tune warm-ups. | |
| io.github.thestarboy9696/doc-extract-api thestarboy9696/doc-extract-api SchemaLock — paid extraction: JSON from docs via your schema, x402/USDC. | |
| io.github.TheStevenJohnstone/ai-consensus thestevenjohnstone/ai-consensus-connector Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent. | |
| io.github.thestockgoatballs/clipspeed-mcp thestockgoatballs/clipspeed-mcp AI video, images, AI influencers, character swaps and clipping from Claude or ChatGPT. | |
| Postfleet thestral12/postfleet-mcp Give an AI agent its own email address: send, reply, read, and wait for mail. | |
| Chutes Media MCP thestreamcode/chutes-media-mcp Generate image, video, music and speech through Chutes and save assets into your project. | |
| io.github.TheStreamCode/discord-management-mcp thestreamcode/discord-management-mcp Safe-by-default Discord management MCP with JSON backups, restore planning, and guarded mutations. | |
| io.github.randomblocker/supercolony thesupercolony/supercolony-mcp Agent swarm intelligence — real-time feed and consensus signals from 140+ AI agents on-chain | |
| network.clockchain/time thetangstr/clockchain-developer-tools Clockchain®: neutral verified network time for AI agents (get_time). Testnet. | |
| AnnealBridge thetsungying/annealbridge Optimization middleware for AI agents: JSON problem in, verified and ranked solutions out. | |
| io.github.theUpsider/lsp-mcp theupsider/lsp-mcp Universal LSP MCP server | |
| App Store + Google Play Data thevalkdokk/appstore-data-mcp Live App Store and Google Play data: app details, reviews, search, top charts for 175+ storefronts. | |
| Better-TG-CLI (Telegram) thevilfer/better-tg-cli Telegram on your own account: read, search, send and press bot buttons. Writes need your approval. | |
| io.github.theYahia/amocrm-mcp theyahia/amocrm-mcp MCP server for amoCRM API — leads, contacts, pipelines. Auth: Bearer token. | |
| io.github.theYahia/bitrix24-mcp theyahia/bitrix24-mcp MCP server for Bitrix24 CRM — deals, contacts, tasks via webhook API. | |
| io.github.theYahia/boxberry-mcp theyahia/boxberry-mcp MCP server for Boxberry delivery API — city/point search, delivery calculation, tracking. 4 tools. | |
| io.github.theYahia/calltouch-mcp theyahia/calltouch-mcp MCP server for Calltouch API — call tracking, call statistics. Token auth. | |
| io.github.theYahia/cbr-mcp theyahia/cbr-mcp MCP server for Central Bank of Russia API — currency rates, key rate, precious metals, conversion. | |
| cdek-mcp theyahia/cdek-mcp MCP server for CDEK — delivery, tariffs, tracking, order management (Russia) | |
| io.github.theYahia/chestnyznak-mcp theyahia/chestnyznak-mcp MCP server for Chestniy ZNAK (Честный ЗНАК) API — product marking verification. No auth needed for | |
| claude-webcache theyahia/claude-webcache Cross-session WebFetch cache for Claude Code. Unlimited TTL by default, SQLite, MCP plugin. | |
| io.github.theYahia/cloudpayments-mcp theyahia/cloudpayments-mcp MCP server for CloudPayments API — charge, auth, confirm, void, refund, find transaction. 6 tools. | |
| io.github.theYahia/dadata-mcp theyahia/dadata-mcp MCP server for DaData.ru — address validation, company lookup, geocoding. 31 tools. | |
| io.github.theYahia/delovye-linii-mcp theyahia/delovye-linii-mcp MCP server for Delovye Linii (Деловые Линии) delivery API — tariff calculation, city search, tracki | |
| io.github.theYahia/elma365-mcp theyahia/elma365-mcp MCP server for ELMA365 API — app items, BPM tasks. 3 tools. | |
| io.github.theYahia/getcourse-mcp theyahia/getcourse-mcp MCP server for GetCourse API -- users, deals. | |
| gigachat-mcp theyahia/gigachat-mcp MCP server for GigaChat — AI chat, embeddings, image generation (Russia) | |
| io.github.theYahia/hh-mcp theyahia/hh-mcp MCP server for hh.ru jobs API — vacancy search, salary stats, employers, regions. Public endpoints, | |
| io.github.theYahia/huntflow-mcp theyahia/huntflow-mcp MCP server for HuntFlow ATS API — vacancies, candidates, applicants for recruiting. | |
| io.github.theYahia/jivosite-mcp theyahia/jivosite-mcp MCP server for JivoSite API — chats, agents, visitors. 3 tools. | |
| io.github.theYahia/kaiten-mcp theyahia/kaiten-mcp MCP server for Kaiten API — cards, boards. 3 tools. | |
| io.github.theYahia/kaspi-mcp theyahia/kaspi-mcp MCP server for Kaspi.kz Shop API -- orders and products. | |
| io.github.theYahia/kontur-focus-mcp theyahia/kontur-focus-mcp MCP server for Kontur.Focus API — company search, brief reports, financial analytics, counterparty |
17,951–18,000 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.