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 |
|---|---|
| com.vibsync/vibsync loosedays/vibsync-mcp One shared brain for your AI coding agents: team memory, agent Q&A, tasks, and file claims. | |
| io.github.Looted/kibi-mcp looted/kibi Kibi requirements, traceability, and proof MCP. Install as a project dev dependency. | |
| io.github.lordbasilaiassistant-sudo/base-flash-arb-mcp lordbasilaiassistant-sudo/base-flash-arb-mcp MCP server for AI agents to detect flash loan arbitrage opportunities across DEXes on Base. Scan Uni | |
| io.github.lordbasilaiassistant-sudo/base-gasless-deploy-mcp lordbasilaiassistant-sudo/base-gasless-deploy-mcp MCP server for AI agents to deploy ERC-20 tokens on Base with zero gas fees via CDP Paymaster. Gasle | |
| io.github.lordbasilaiassistant-sudo/base-multi-wallet-mcp lordbasilaiassistant-sudo/base-multi-wallet-mcp MCP server for AI agents to manage multiple wallets with coordinated trading and batch operations on | |
| io.github.lordbasilaiassistant-sudo/base-price-oracle-mcp lordbasilaiassistant-sudo/base-price-oracle-mcp MCP server for real-time token prices on Base from on-chain DEX pools. | |
| io.github.lordbasilaiassistant-sudo/base-security-scanner-mcp lordbasilaiassistant-sudo/base-security-scanner-mcp MCP server to scan smart contracts on Base for honeypots, rug pulls, and vulnerabilities. | |
| io.github.lordbasilaiassistant-sudo/base-token-sniper lordbasilaiassistant-sudo/base-token-sniper-mcp MCP server to discover and trade new token launches on Base chain. | |
| io.github.lordbasilaiassistant-sudo/base-wallet-toolkit lordbasilaiassistant-sudo/base-wallet-toolkit-mcp MCP server for Base wallet interactions: balances, gas, tokens, allowances, ENS. | |
| io.github.lordbasilaiassistant-sudo/broke2built-skills-mcp lordbasilaiassistant-sudo/broke2built-skills-mcp 29 live data skills for agents: email/DNS/domain intel, web audits, EVM reads. Free tier. | |
| ThryxProtocol MCP Server lordbasilaiassistant-sudo/thryx-mcp-server ThryxProtocol v3.1 — gasless AI agent launchpad on Base. 21 tools wrap thryx.fun HTTP API. | |
| io.github.LordMendes/lgpd-mcp lordmendes/lgpd-mcp MCP Server para conformidade LGPD. Ferramentas de bases legais, consentimento, PIA e políticas. | |
| EasyPDF lorenzino69/easypdf-mcp Edit PDF text in place, fonts and layout kept. Compress, merge, split, convert and translate PDFs. | |
| io.github.LorgAI/lorg-mcp-server lorgai/lorg-mcp-server Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP | |
| Droste lorismascio17/droste-memory Local code exploration with progressive zoom and measured token budgets. | |
| Black Flag Alert lorquaid/black-flag-alert-mcp UK company credit risk for England & Wales: R-Score, CCJs, charges, financials. 5.1M companies. | |
| Tag-per-Track lory97/tag-per-track-mcp Audio analysis and A&R scoring for music tracks: tags, lyrics, artist stats, demo triage. | |
| GistPad MCP lostintangent/gistpad-mcp A server for managing and sharing personal knowledge, daily notes, and reusable prompts via GitHub Gists, enabling users to access and edit their gists from any MCP-enabled AI product. | |
| SHEARLINE lostnumber07/shearline Analyst-grade US severe weather: warnings, SPC outlooks, RAP environment, MRMS, GLM lightning | |
| mcp-loudkit loudreader/loudkit allows to connect local natural TTS | |
| @louis030195/apollo-io-mcp louis030195/apollo-io-mcp MCP server for Apollo.io B2B sales intelligence API. Enables searching and enriching people and organizations via natural language. | |
| Obsidian MCP Server louis030195/easy-obsidian-mcp Enables AI assistants to search, read, and analyze Obsidian notes via the Local REST API. | |
| GPTZero MCP Server louis030195/gptzero-mcp Enables AI-generated text detection using the GPTZero API. Provides confidence scores and detailed analysis to identify whether text was written by humans or AI, with multilingual support. | |
| Toggl MCP Server louis030195/toggl-mcp Enables control of Toggl time tracking directly from LLMs like Claude or ChatGPT. Supports starting/stopping timers, viewing current and historical time entries, managing projects, and generating weekly summaries through natural language. | |
| io.github.louis49/melchizedek louis49/melchizedek Persistent memory for Claude Code — offline, single-file, hybrid search. | |
| FateStar Ziwei louislin0723/fatestar-ziwei Zi Wei Dou Shu for AI agents: free natal charts, six transit levels, and optional readings. | |
| Lovable lovablelabs/mcp Official MCP server for Lovable, the AI-powered full-stack app builder. | |
| Lovec lovec-tech/lovec-mcp Prompt-injection detector for untrusted text before it reaches an LLM (RU/EN). BYO lovec.tech key. | |
| io.github.loved0543-dotcom/kdata-gate loved0543-dotcom/kdata-gate-mcp Korean market data for AI agents: K-beauty/K-food products, Naver trends, stocks, real estate. | |
| No-Shell Agent Architect MCP loved0543-dotcom/no-shell-agent-operating-pack Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries. | |
| io.github.lovelyquality/korail-mcp lovelyquality/korail-mcp 한국철도공사(KORAIL) 공공데이터 MCP 서버 — 98개 도구, API 키 신청 불필요. 역·열차·화물·통계 데이터 자연어 조회. | |
| Lovie Company Formation lovieco/lovie-company-formation-mcp-npx Form companies, manage bank accounts, cards, invoices and more — directly from your AI coding tools. | |
| MCP AST Explorer lovranran/mcp-ast-explorer Python symbol exploration for codebase onboarding agents. | |
| MCP Repo Mapper lovranran/mcp-repo-mapper Deterministic repository structure mapping for onboarding agents. | |
| MCP Test Runner lovranran/mcp-test-runner Local test execution and coverage summaries for onboarding agents. | |
| WebKitUI MCP lowrisk75/webkitui-mcp Native WebKit for Mac. Human approval and persistent sign-ins. Requires the companion app. | |
| Lowtoxgear Storefront lowtoxgear/lowtoxgear-mcp Read-only catalogue MCP for Lowtoxgear — Australian low-tox lifestyle brand. 5 tools. | |
| NuMetric lowwmax/numetric-mcp-connector Read-only NuMetric.work accounting & ERP data: statements, KPIs, reports, invoices, documents. | |
| io.github.lozit/mcp-freestyle lozit/mcp-freestyle Read-only FreeStyle glucose sensor access via LibreLinkUp. Not a medical device. | |
| io.github.lozit/mcp-standardnotes lozit/mcp-standardnotes End-to-end encrypted access to a Standard Notes vault (protocol 004, local stdio only). | |
| WhyLingxi 保险顾问 Insurance Advisor lpb123/whylingxi-insurance-mcp 保险产品搜索、推荐、保费试算、核保预检。覆盖65家保司483款产品。China insurance MCP server. | |
| Unitree Go2 MCP Server lpigeon/unitree-go2-mcp-server A server built on the Model Context Protocol that enables controlling the Unitree Go2 robot using natural language commands, which are translated into ROS2 instructions for the robot to perform corresponding actions. | |
| eCFR.io Federal Regulations lrehmann/ecfr-mcp Search and read US federal regulations with legal and inline citations linking to ecfr.io. | |
| US Code Federal Statutes lrehmann/uscode-mcp Search and read U.S. Code statutes with legal and inline citations linking to uscode.ecfr.io. | |
| qa-probe ls-siem-llp/qa-probe Probes your live API and classifies why each endpoint failed (root cause, evidence, and a calibrated confidence level), exposed over MCP so your AI assistant debugs from evidence instead of guessing. Works with FastAPI, Express, Next.js, tR | |
| MCP Sidecar lsequeiraa/mcp-sidecar Cross-platform MCP server for managing long-lived background processes from any MCP client | |
| DexSQL lsposed/dexsql-release SQL for Android APK and DEX files: classes, methods, strings, references and smali. | |
| app.vercel.proof-stack-lake/proofstack lttxzmj/proofstack-mcp Audited indie product business cases with source-backed pricing, revenue and pricing benchmarks. | |
| com.essentras/placements ltv-so/essentras-mcp Buy press coverage in 3,800+ vetted media outlets. Price a basket, get a checkout link. | |
| Python Exec Sandbox lu-zhengda/mcp-python-exec-sandbox Sandboxed Python execution for AI agents. PEP 723 inline deps, multi-version Python, zero pollution. |
11,101–11,150 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.