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 |
|---|---|
| Resume MCP Agent bugparty/resume-mcp-server Enables AI clients to manage resumes, match job descriptions, and generate tailored PDF resumes. | |
| Bugsniffer bugsniffer-io/bugsniffer-mcp Enables AI coding agents to sniff a deployed app's homepage and receive a free Sniff Score out of 100, a verdict, structured findings, and a paste-ready fix prompt, plus retrieval of earlier results without spending a new sniff. It also rep | |
| reconftw-mcp bugtraceai/reconftw-mcp Enables AI assistants to perform reconnaissance tasks using the reconFTW framework, supporting full, passive, subdomain, vulnerability, and OSINT scans through MCP tools. | |
| Azure DevOps MCP Server bugzy-ai/azure-devops-mcp-server Enables AI assistants to search, create, update, and manage work items in Azure DevOps using natural language. | |
| GitHub MCP Server bugzy-ai/github-mcp-server Enables querying GitHub repositories for pull requests, commits, and comparisons to understand code changes. | |
| Resend MCP Server bugzy-ai/resend-mcp-server Enables sending single and batch emails through the Resend API with support for HTML/plain text content, CC/BCC recipients, and custom tracking tags. | |
| simple-slack-mcp-server bugzy-ai/slack-mcp-server A simplified MCP server for accessing Slack API, enabling AI assistants to list channels, post messages, reply to threads, add reactions, and get channel history. | |
| mcp-rss buhe/mcp_rss MCP RSS is a Model Context Protocol (MCP) server for interacting with RSS feeds | |
| Financial Modeling Prep MCP Server bui232/financial-modeling-prep-mcp-server Exposes 250+ tools spanning stocks, ETFs, crypto, forex, commodities, economics, financial statements, and market news so AI assistants can retrieve and analyze financial data through the Financial Modeling Prep API. Supports dynamic runtim | |
| vivado-mcp bui39701/vivado-mcp Enables AI agents like Claude Code and Cursor to drive a locally installed Xilinx Vivado safely through 32 curated tools covering synthesis, implementation, timing, CDC, XDC, IP, waveforms, and device programming. It provides structured tim | |
| cve-search_mcp bui866/cve-search_mcp Enables querying a CVE-Search API to browse vendors and products, retrieve vulnerabilities by vendor/product or CVE ID, and fetch recent CVEs with CAPEC, CWE, and CPE expansions plus database update details. | |
| @cyanheads/pubmed-mcp-server bui9528/pubmed-mcp-server Enables users to search PubMed and Europe PMC and retrieve article metadata, full text from PMC/Europe PMC/Unpaywall, citations in multiple formats, related and citing works, MeSH terms, and resolved DOI/PMID/PMCID or partial-citation refer | |
| MCP Proxy Server buib7910/mcp-proxy-server Aggregates multiple backend MCP servers (Stdio, SSE, and Streamable HTTP) into a single unified hub, routing tool calls and resource requests to the correct backend and exposing their combined capabilities through one SSE, Streamable HTTP, | |
| codex-mcp-bridge buidangminh23/codex-mcp-bridge Two-way MCP bridge between Claude and Codex: send prompts into a live Codex Desktop thread and messages into a running Claude Code session, keeping each conversation in its own app. Native Desktop tasks on Windows and macOS; CLI/app-server | |
| Vectorize MCP Server buigauck/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking into Markdown, and private deep research through a configured Vectorize pipeline. | |
| viv-mcp-server buigialy30206-eng/viv-mcp-server A Model Context Protocol (MCP) server that exposes 23 free APIs (Steam, WHOIS, email, IP geolocation, currency, stocks, QR codes, and more) for use by AI assistants like Claude and Cursor. | |
| figma-mcp buihung1612/figma-mcp Enables AI coding assistants to draw UI directly on a Figma Desktop canvas and read existing designs back as structured JSON, tokens, CSS, and screenshots, all over a localhost bridge without external API keys. | |
| Turbular builambert097/turbular Enables LLM agents to connect to and query many database types—including PostgreSQL, MySQL, SQLite, BigQuery, Oracle, MS SQL, and Redshift—through a single unified API. It provides schema retrieval and optimized query execution with normali | |
| mcp-agent-toolkit build-with-deepak/mcp-agent-toolkit An MCP server exposing three tools — a read-only PostgreSQL commerce database, a live weather API, and a calculator — behind a real MCP protocol client/server boundary. It enables natural-language questions that combine database and weather | |
| env-mcp buildappolis/env-mcp Secure environment variable and configuration management MCP server with Claude Code integration for storing, managing, and retrieving environment variables. | |
| Satellite MCP Server buildaspacepro/orbit-mcp Enables satellite orbital mechanics calculations including visibility predictions, access window analysis, and TLE generation from natural language descriptions. Supports 200+ world cities and multiple orbit types (LEO, MEO, GEO, SSO, Molni | |
| Aureon MCP buildaureon/aureon-mcp Enables MCP hosts and agents to authenticate, sync and manage a Capital Book, create and monitor Financial Compass objectives, inspect health, timeline, vault and executions, prepare non-custodial vault deposit and withdraw steps, and fetch | |
| BuildBase Agent MCP Server buildbase-app/nextjs-agent-mcp-starter An MCP server that allows AI agents to manage BuildBase resources (users, workspaces, subscriptions, projects) via 48 tools, with built-in agent authentication and discovery. | |
| BuildBetter buildbetter-app/buildbetter-mcp AI for product teams. Connect all your company and customer knowledge to all of your other tools via BuildBetter's MCP. | |
| orca-mcp buildcontext/orca-mcp External MCP server for controlling Orca worktrees, agent sessions, and multi-agent orchestration from any MCP client via stdio or Streamable HTTP. | |
| openmedia-mcp builderstar/openmedia-mcp Enables AI agents to extract, analyze, and manipulate images, PDFs, video, and audio while conserving context through downscaling, truncation, and frame/page caps. | |
| youtube-music-cli-mcp builderstar/youtube-music-cli-mcp-fork Provides a local stdio MCP server for controlling YouTube Music through the CLI, enabling playback, search, queue management, and library access via MCP-compatible clients. | |
| Buildez MCP Server buildezai/buildez-mcp Enables AI assistants to build complete, live websites from natural language descriptions by connecting to Buildez.ai. | |
| MCP Server Template buildfound/mcp-server-template A minimal, forkable TypeScript MCP server that exposes an add tool for simple arithmetic and a word_stats tool for counting words and characters and returning ranked word frequencies, plus an info://server resource reporting package metadat | |
| MarketIntel MCP Server buildingagentswithdeepak-beep/mcpserver Exposes market-research tools over SSE with pluggable providers for offline or Tavily-backed search. | |
| OpenBrowser buildingopen/openbrowser Enables AI tools to browse the web as the user by providing access to a persistent browser session with logged-in accounts, supporting recipes for email, PRs, calendar, and more. | |
| jobber-mcp buildminimal/jobber-mcp Enables AI assistants to read field-service business data through a read-only MCP integration, including jobs, invoices, quotes, schedules, clients, and draft client messages. It handles authentication, token refresh, throttling, schema ver | |
| eywa-mcp buildoak/eywa-continuum Provides cross-session memory for Claude Code by extracting structured handoffs at session end and retrieving relevant past context at session start. | |
| lazy-guard buildproject222/lazy-guard Enforces a policy ladder for Solana AI agents so on-chain actions are vetted before signing, checking whether an action is justified, recently repeated, or targets only known programs, and applying spend, daily, and slippage caps plus recip | |
| MCP Todo & Context Server buildswithadnan/mtcs-mcp-todo-and-context-server Provides AI clients with per-project todo management and persistent context notes via MCP, enabling task tracking and resume summaries. | |
| Frappe Assistant Core buildswithpaul/frappe_assistant_core MCP server that enables LLMs to interact with ERPNext/Frappe sites for document CRUD, search, reports, workflows, and analytics, respecting user permissions and logging all actions. | |
| Housewarden buildwithabid/housewarden Enables household management through natural language, covering bills, chores, shopping, reminders, budget, and smart-home devices, with every mutating action dry-run, confirmed, and audited. | |
| Shopify MCP Server buildwithabid/shopify-mcp Read-only access to a Shopify store over the Admin REST API. Search orders by status, date range or customer email; check inventory by product title or ID; look up customers by email, name or phone; and generate sales summaries. Four read-o | |
| Housecall Pro MCP Servers buildwithbeacon/housecallpro-mcp A collection of over 20 specialized MCP servers that enable LLMs to manage customers, jobs, scheduling, invoicing, materials, and more in Housecall Pro's field service management system. | |
| OwnerRez MCP Server buildwithmanag/ownerrez-mcp MCP server that connects OwnerRez to Claude and other MCP clients, enabling natural language management of bookings, guest communication, property info, expenses, and webhooks. | |
| omni-video-mcp buildwithtaza/omni-video-mcp An MCP server that transforms LLM-enabled IDEs into professional video editors by pre-processing footage into text proxies, generating motion graphics via HTML/CSS, and orchestrating complex FFmpeg renders. | |
| built-online-podcast-command-center built-online/built-online-podcast-command-center Provides AI tools with direct read access to the Built Online Podcast Command Center data, enabling validation, recommendations, and visibility of missing data without guessing. | |
| Yūsetu builtbyaakash/yusetu Self-hosted MCP gateway that aggregates many MCP servers into a single endpoint for AI clients, supporting hosted, local stdio, and Git-sourced MCPs. | |
| HRIS MCP Connector builtbybianca/hris-mcp-connector Enables querying HR data like recent hires, employee details, departments, and PTO balances through natural language in an MCP client. | |
| rubyhash-mcp builtbyproxy/rubyhash-mcp Enables comparing Ruby hash literals and converting Ruby hashes to JSON with deterministic diff reports, running locally for privacy. | |
| BuiltWith MCP builtwith/builtwith-mcp Enables AI assistants to query BuiltWith's technology detection data directly, supporting natural language questions about website technologies. | |
| tmux-bridge-mcp buimoore/tmux-bridge-mcp Enables AI agents running in separate tmux panes to read, type into, and message each other through standard MCP tool calls, coordinating cross-pane workflows without custom frameworks or protocols. | |
| psd2ui buinghiemtrang/psd-mcp Enables Claude to read PSD files, export alpha-trimmed sprites, build layout specs, and match them to existing Unity uGUI prefabs, then apply rects, sprites, TMP fonts, and colors. It also renders prefabs for a side-by-side visual diff agai | |
| stock-mcp buipolyakov756/stock-mcp Enables AI agents and backend integrations to access standardized market data, technical indicators, fundamentals, news, filings, money-flow analysis, and code-export outputs across A-shares, US equities, ETFs, indices, and crypto. It expos | |
| Express REST API and MCP Server Framework buir341/express-rest-api-and-mcp-server-framework Enables LLMs to discover and invoke generated API actions as MCP tools and read context through MCP resources for list and get-by-id operations. It provides HTTP-based MCP access for clients such as Cursor and Claude without extra glue code |
36,001–36,050 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.