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 |
|---|---|
| drug-label arhancanli/drug-label-mcp Answers medication questions from official FDA labels with section citations, resolves drug names via RxNorm, and reports FDA recalls and shortages. | |
| end-of-life-mcp arhancanli/end-of-life-mcp Enables checking project files like Dockerfile, .nvmrc, and CI workflows to determine whether pinned runtime, database, and OS versions are still supported, providing end-of-life dates, latest patches, and upgrade targets for 470+ products. | |
| internet-standards-mcp arhancanli/internet-standards-mcp Enables coding agents to retrieve exact RFC section text, status and obsoleted-by chains, errata, and IANA registry values such as HTTP status codes, media types, and port numbers. | |
| Kube Check arhancanli/kube-check-mcp Enables agents and users to validate Kubernetes manifests (YAML/JSON, multi-document) against the API of a chosen Kubernetes version without needing a cluster. It reports removed or deprecated APIs with replacements, unknown or misspelt fie | |
| license-check arhancanli/license-check-mcp Provides authoritative open source license answers: SPDX identification, copyleft classification, and compatibility checks of dependencies against your project's license. | |
| Domain Health arhancanli/mcp-factory Enables email and domain checks, including SPF lookup limits, DKIM keys, DMARC, DNS records, and registration expiry. | |
| package-truth arhancanli/package-truth-mcp Enables checking packages across npm, PyPI, Go, Maven, Cargo, NuGet, and RubyGems for existence, deprecation, known vulnerabilities, and license issues before installation, providing verdicts like does_not_exist, risky, verify, or ok. | |
| recall-check-mcp arhancanli/recall-check-mcp Searches US product recalls across CPSC, FDA, and NHTSA in one call, matching by name, brand, model number, UPC, or VIN with confidence scoring. | |
| Regex Check arhancanli/regex-check-mcp Runs a regular expression on real engines — JavaScript (V8), Python (CPython re), PCRE2 and RE2 — reporting each engine's own compile errors with positions, every match with its groups and named groups, replacement results, and where the en | |
| release-notes arhancanli/release-notes-mcp Answers upgrade questions from a package's own changelog, listing breaking changes, deprecations, security fixes, and raised requirements between two versions, retrieving notes for a single version, and searching changelog entries for speci | |
| satellite-imagery-mcp arhancanli/satellite-imagery-mcp Finds the clearest Sentinel-2, Landsat, Sentinel-1, or NAIP scene for any location and time, ranked by area coverage, cloud cover, and date, with previews and band download links. | |
| SQL Check arhancanli/sql-check-mcp Runs SQL statements in memory against real PostgreSQL 18 and SQLite 3.49 engines after loading your schema and sample rows, returning each statement's own verdict: errors with line, column, and hints, constraint violations, or the resulting | |
| vuln-priority arhancanli/vuln-priority-mcp Enables prioritizing vulnerabilities by real-world exploitation evidence, combining CISA KEV, EPSS, CVSS, and SSVC to rank CVEs and package versions, and providing fix recommendations. | |
| web-reader-mcp arhancanli/web-reader-mcp Enables reading web pages and PDFs as clean Markdown, extracting main content and letting agents query for relevant passages, outline sections, search in-page, and list links while respecting robots.txt and blocking private addresses. | |
| world-time-mcp arhancanli/world-time-mcp Provides accurate time zone conversions, DST-safe scheduling, holidays for 200+ countries, business day calculations, and cross-zone meeting slot suggestions. | |
| zotero-claude-mcp arhashemi/zotero-claude-mcp Enables Claude to search, retrieve, and cite from your Zotero library, including local databases and zotero.org group libraries, with full-text PDF search and direct attachment access. | |
| Universal Menu arhgap11b/appsdk-universal-menu Provides an interactive decision menu that surfaces contextual choices on every assistant turn, allowing users to navigate available actions through a React widget interface. | |
| ladder-mcp arhimage/ladder-mcp Windows-first MCP bridge for Kimi Code CLI, exposing code analysis, editing, sessions, and diagnostics as tools for AI agents. | |
| xcape ari-systemics/xcape Vacation-quoting MCP server for travel agents that turns plain-language client briefs into priced, bookable proposals with live hotel rates, activities, and dining, plus an assistant skill for building branded, printable quotes. | |
| Korean Law MCP ari11zone/korean-law-mcp Provides 17 tools for accessing Korean statutes, precedents, and administrative rules via the National Law Information Center API, with LLM hallucination prevention, citation verification, impact graphs, and time-travel diff. | |
| canvas_mcp ari310126/canvas_mcp Enables reading and writing Canvas LMS course content using browser session cookies, without needing an API key. | |
| studizba-mcp ari3lyt/studizba-analytics Enables searching and analyzing Studizba teacher reviews with confidence-aware score explanations, rankings, comparisons, history, and explicit refresh operations. | |
| @aria-agentworks/sales-intelligence-mcp aria-agentworks/sales-intelligence-mcp 12 MCP tools for company research, lead scoring, outreach automation, and CRM sync — Claude, GPT, Gemini, Cursor, Windsurf. | |
| 小葵 × 瑞幸 MCP ariaeternity/xiaokui-luckin-mcp Enables ChatGPT to select a coffee shop, products, and specifications, preview real quotes, create orders only after the owner approves each one, return an official QR code for self-payment, and query order and pickup information. It is a s | |
| 小葵 × 麦当劳中国 MCP ariaeternity/xiaokui-mcd-mcp Enables ChatGPT to query stores, menus, meal details, and coupons, calculate official prices, prepare orders for per-order owner approval, submit approved intents, and check order status with duplicate-submission and UNKNOWN safeguards. | |
| Nobulex MCP Compliance Server arian-gogani/nobulex-mcp Provides covenant rule enforcement, hash-chained audit logs, and integrity verification for MCP-compatible agents. It enables users to define granular permission rules and maintain a tamper-evident audit trail of all actions. | |
| CC Trading Terminal arianashafiee/smart-trade-ai An MCP server that lets Claude Code (and other MCP clients) trade crypto, read market data, and manage wallets across EVM chains and Solana. | |
| firecrawl-lite-mcp-server ariangibson/firecrawl-lite-mcp-server Enables privacy-first web scraping and structured data extraction using a local headless browser and your own LLM key. Supports tools for scraping, batch scraping, data extraction with prompts or schemas, and screenshots. | |
| Nowhere ariaprism/nowhere-mcp Enables AI to explore real-world coordinates by simulating physical presence with sensory details like terrain, weather, sounds, and local knowledge through MCP tools. | |
| Agent Data Bridge ariascarlet132/sandbox_mcp An MCP server that provides data bridging from Spring Boot interfaces and a lightweight Python sandbox for script execution. It enables agents to fetch data as Markdown or Parquet files and perform automated data analysis within a controlle | |
| kegg-mcp ariashishegaran/kegg-mcp An MCP server that exposes the KEGG REST API — pathways, genes, compounds, reactions, enzymes, diseases, drugs, modules, orthology, glycans, and BRITE hierarchies, with cross-database linking. Provides 34 tools and 8 resource templates. | |
| @ariburaco/free-for-dev-mcp ariburaco/free-for-dev-mcp A Model Context Protocol server that provides semantic search and intelligent access to a comprehensive list of free services and tools for developers. | |
| ExpenseTracker aricode2005/expense-tracker-mcp Enables personal expense management through MCP tools for CRUD operations, search, budgeting, analytics, and CSV export, including monthly trends and budget status alerts. | |
| obsidian-writer-mcp ariedotme/obsidian-writer-mcp MCP server that writes to Obsidian vaults via the obsidian-writer HTTP service. Supports managing inbox entries, lists, notes, and tasks. | |
| mcp-ssh-server arieend/mcp-ssh-server Bridges VS Code on Windows with remote Linux servers via SSH, enabling AI assistants to interact with remote development environments. | |
| sap-support-mcp arief135/sap-support-mcp An MCP server over Streamable HTTP that exposes two SAP help-desk operations to an AI agent: sap_reset_password and sap_unlock_users. | |
| postgres-mcp-server arieffian/postgres-mcp-server An MCP server for safely querying PostgreSQL from an LLM, with read-only default mode, multi-connection aliases, and session-enforced safety. | |
| Maritime Vessel Data MCP Server ariefrsee/maritime-mcp-server Enables querying maritime vessel data via MCP tools and resources, including vessel search, port proximity, and vessel details lookups. | |
| vibe-code-mcp arielaizn/vibe-code-mcp Connects to vibe-code-best-practices.vercel.app to index 817 tools across 185 sections and 10 domains, routes the right tool/Skill for your project need, and can recommend a full stack. | |
| ye-ast arielfalcon/ye-ast This server provides verifiable code facts and entrypoint maps for a repository. It enables AI agents to understand the deterministic impact of code changes by providing evidence-based analysis of dependencies and usage. | |
| scanything arielfikru/scanything Enables agents like Claude Code and Codex to statically scan .zip, .exe, .dll files and GitHub repositories for malware without executing them, explaining likely false positives and letting users dig into reports through natural language. | |
| mcp-sec-clientes-sin-luz arielhernandezcl/mcp-sec-clientes-sin-luz Enables querying power outages and affected customers in Chile from SEC public data, including affected customers by date, region and commune, national customer totals, aggregated outage summaries with rankings, and lists of affected region | |
| Telegram MCP Server arielsacagiu/telegram-mcp A Telegram integration for Claude, Cursor, and other MCP-compatible clients. It exposes Telegram account, chat, message, contact, media, folder, and admin operations through the Model Context Protocol using Telethon. | |
| 3d-asset-server arielshad/3d-asset-server Enables AI assistants to search many 3D asset sites at once, inspect licences and metadata, and download selected models, materials, textures, HDRIs, or game asset packs directly into a project. | |
| Remote MCP Server with GitHub OAuth ariencarnacion/dnd-mcp A Cloudflare Workers-deployed MCP server that provides secure remote access to MCP tools through GitHub OAuth authentication. Includes example tools for basic math operations, user info retrieval, and image generation with configurable user | |
| litecontext-cli aries-0331/litecontext A local-first MCP server that indexes Markdown/Obsidian folders and lets AI clients retrieve cited local context through MCP. | |
| Aries aries-labs-hq/alkanes-aries An MCP server that equips AI assistants with curated knowledge and live chain data for the Alkanes metaprotocol and Subfrost network, enabling them to read docs, query the chain, and scaffold contracts. | |
| DAiMON aries-photonics/daimon Enables AI assistants to check proposed actions against a local ledger of previously ruled-out work, receiving graded alerts with prior verdicts to avoid repeating dead ends. | |
| arena-local aries430323/arena-to-local Enables MCP-compatible AI clients to connect to a Windows machine for file operations, PowerShell execution, Git inspection, task management, memory, and skills. | |
| VNStock MCP Server ariesanhthu/mcp-server-vietnam-stock-trading Provides access to Vietnam stock market data including real-time quotes, historical prices, company financials, trading statistics, mutual fund information, and exchange rates through the vnstock library. |
30,301–30,350 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.