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 |
|---|---|
| Rohlik MCP Server brandon6220/rohlik-mcp Enables AI assistants to shop groceries across Rohlik Group platforms by searching products, managing carts, analyzing purchase history for personalized suggestions, and accessing account, order, delivery, and discount information. | |
| Nano Banana MCP brandon695/nano-banana-mcp Enables image generation and editing using Google's Gemini models with support for model selection and custom aspect ratios. Users can generate high-quality images or modify existing ones through natural language prompts while controlling s | |
| android-control brandonbowmansr/android-autopilot-mcp Enables Claude or any MCP agent to see and operate a real Android phone over adb, with fast screen reads, tap/type/swipe actions, app launching, deep links, and brand-aware setup guidance, all without admin rights or an Android SDK. | |
| roundtable-mcp brandondek/roundtable-mcp Enables Claude to orchestrate multi-model AI roundtable discussions between GPT-4o, Gemini, Grok, and DeepSeek through independent responses and cross-critique rounds. It supports various discussion presets such as debate, brainstorm, and c | |
| PrintVaultMCP brandondoster/printvault_mcp Enables AI assistants to manage 3D printing inventory, filament spools, printers, projects, and print trackers through a self-hosted Print Vault instance. | |
| DreamNet Trading Trappers brandonducar/dreamnet-trading-trappers Enables agents to capture and validate market research including theses, entry conditions, targets, and invalidation, and bundle them into Warper Keeper bundles. | |
| zswarm-mcp brandonkramer/zswarm Enables coordination of CLI AI agent crews across Zellij terminal panes, allowing users to spawn agents, send prompts, inspect outputs, sync signals, and manage git worktrees via natural language. | |
| Circuit brandononchain/circuit-mcp Enables building and running visual workflows conversationally inside Claude, orchestrating your existing connector tools step-by-step without storing credentials or owning integrations. | |
| Gmail MCP Agent brandononchain/gmail-mcp-agent Enables automated Gmail lead nurturing campaigns with intelligent follow-ups, response tracking, and 24/7 operation. Supports CSV-based contact management, template personalization, and real-time monitoring for enterprise-scale email outrea | |
| skillsh-mcp brandonqr/skillsh-mcp MCP server for searching and managing AI agent skills from skills.sh, including search, popular skills, details, and install commands. | |
| SearXNG-MCP brandonstudio/searxng-mcp Provides a bridge between AI assistants and SearXNG, a privacy-respecting metasearch engine, enabling web searches and engine discovery via the Model Context Protocol. | |
| Multi-Service MCP Server brandontomlin2/mcp Enables searching and accessing ArXiv research papers with advanced query capabilities, and provides sequential thinking tools for structured problem-solving. Supports Boolean operators, field-specific searches, author lookups, and dynamic | |
| MCP Market brandonwcode/mcp-market Enables users to connect Claude or ChatGPT to a custodial NFT collection and trade by chatting, including minting, buying, selling, listing, checking balances, and withdrawing test tokens. | |
| tldx-mcp brandonyoungdev/tldx An MCP server for tldx that allows AI agents to brainstorm brand names and instantly verify domain availability using lightning-fast, concurrent RDAP lookups. | |
| azure-devops-mcp-server branjesusdev/mcp-azure-arquitecture Enables interaction with Azure DevOps services including Boards, Repos, and Pipelines through natural language commands. | |
| m3x-mcp-server brano80/m3x-mcp-server Connect any AI agent to M3X — the private pool matching protocol for agent-to-agent deal flow. Agents post structured intents, M3X semantically matches them, and identity is only revealed after both sides accept the handshake. | |
| ableton-mcp brantstuns/ableton-mcp An MCP server to control Ableton Live via the Live API, enabling transport, track, clip, device, and automation manipulation through natural language. | |
| mcp_f1_strategy branuvg/mcp_f1_strategy Enables LLM-powered race engineers to compute Formula 1 pit-stop strategies from real session data, including tire degradation modeling, optimal pit windows, undercut/overcut simulation, and finish-position projection. | |
| quijutsu-mcp brariscoding-rgb/quijutsu-mcp Enables browsing QuiJutsu's public Community Asset Library and inspecting the provenance, review status, and community-decided Spirit Levels behind each entry. Also reads player, tournament, and contributor leaderboards, all read-only and w | |
| brasil-mcp-essentials brasil-mcp/essentials A privacy-first MCP server providing 14 offline Brazilian utilities including document validation, boleto parsing, PIX BR Code generation/parsing, and calendar tools. | |
| postgres-mcp-full-access brassaikao/postgres-mcp-full-access Enables AI agents to execute any SQL command (including DDL/DML) on a PostgreSQL database with zero restrictions, allowing full database control and dynamic database switching. | |
| PostgreSQL MCP Full Access brassaikao/postgresql-mcp-full-access Enables unrestricted SQL execution (DDL/DML) on PostgreSQL databases, allowing AI agents to create, read, update, and delete data with zero query filtering. | |
| gpt-action-mcp-demo brasspage/gpt-action-to-mcp Serves the free Frankfurter exchange-rate API as MCP tools over stateless Streamable HTTP on Cloudflare Workers, letting clients list supported currencies, fetch the latest rates, and look up historical rates for a given date. Each OpenAPI | |
| Segmind MCP Server bratcliffe909/segmind-mcp Enables AI image and video generation using Segmind's API with 30+ models including FLUX, Stable Diffusion XL, and more, accessible through any MCP-compatible AI assistant. | |
| dbt-mcp bratko1234/dbt-mcp MCP server that provides tools to interact with dbt, including dbt Core, Cloud CLI, Semantic Layer, and Discovery API. | |
| Pipedrive MCP Server bratland/pipedrive-mcp-server Connects the Pipedrive API v2 to LLM applications, providing read-only access to CRM data including deals, contacts, and pipelines. It enables users to search and retrieve organization information, activities, and notes through natural lang | |
| Fonbet MCP bratz121/fonbet-odds-mcp MCP server for reading Fonbet sports events and odds, enabling search for events, retrieval of odds, and value-bet checking via natural language. | |
| Modal MCP Server braullynn/modal-mcp Connects AI agents to Modal.com infrastructure, allowing management of deployments, apps, containers, volumes, secrets, and environments via MCP tools. | |
| Claude IPC MCP braun19677/claude-ipc-mcp Enables AI assistants to register named instances, send persistent messages to one another, and check inboxes across platforms and sessions using natural language commands. | |
| LunchMoney MCP Server braun2301/lunchmoney-mcp Enables AI assistants and other MCP clients to manage personal finances through the LunchMoney API, covering transactions, budgets, categories, tags, recurring items, accounts, crypto, and balance history. | |
| FlowLens MCP Server braun62/flowlens-mcp-server Enables coding agents to access complete browser flow recordings—including user actions, network traffic, console logs, storage, DOM events, and screen recordings—so they can debug issues and perform regression testing without reproducing t | |
| jev bravegeek/jev-claude Enables Claude Code to delegate subagent model routing and to answer yes/no, choice, and score questions about entire files using a small, cheap external model, so large numbers of files can be screened without filling the main context wind | |
| Backblaze B2 MCP Server braveram/backblaze-mcp Enables seamless integration with Backblaze B2 cloud storage for managing buckets, uploading/downloading files, handling large multipart uploads, and managing application keys through natural language interactions. | |
| ATracker MCP Server braveva/atracker-mcp Syncs ATracker time tracking data to a local SQLite database and provides MCP tools for querying tasks, entries, tags, and exporting data. | |
| docx-fnbib-mcp bravo111034/word-footnotes-bibliography-mcp Enables adding footnotes, in-text citations, and a bibliography/works-cited section to Word .docx files without Word, supporting APA 7, MLA 9, and Chicago 17 styles. | |
| bravoric-ssh-mcp bravoricdev/bravoric-ssh-client Exposes the SSH + tmux client over stdio so agents can drive hosts, tmux sessions, commands, broadcasts, tunnels and audit logs programmatically. It offers 47 grouped tools covering host and session management, connectivity checks, and back | |
| Dokploy MCP Server bravos2k5/mcp Exposes all Dokploy API endpoints as MCP tools, enabling AI models and other clients to manage projects, applications, databases, and more on a Dokploy server. | |
| QuickBooks Online MCP Server brax-tech-internal/qbo-mcp-multicompany Provides complete QuickBooks Online API integration for Claude Code and other MCP-compatible clients, enabling full CRUD operations on 29 entity types and 11 financial reports. | |
| industrial-mcp brayangcastro/mcp-industrial-agent An MCP server that gives Claude (or any MCP-compatible AI host) read access to industrial sensor data and safety-gated control over motors and actuators. | |
| mcp-analytics brayannexgen/nexgenacademy-mcp Exposes product analytics metrics from an internal data warehouse via MCP, enabling agents to query metrics, product summaries, and event breakdowns. | |
| oficio brayans7/oficio Enables agents to turn customer conversations into provably correct remodeling quotes by extracting catalog-bounded line items with evidence and calculating prices deterministically. | |
| MCP Gastos brayantm/mcp-basico Enables personal expense management through CSV storage, allowing AI agents to add, query, and analyze expenses with automatic categorization and payment method validation. | |
| garmin-connect-personal-mcp braydenabo/garmin-mcp Syncs your own Garmin Personal API data into a local SQLite archive and lets any MCP-capable AI assistant query sleep, HRV, stress, body battery, training and activity trends through natural language, with optional interactive charts. Every | |
| agent-06-mcp-server braylo777/agent-06-mcp-server Enables any MCP client to connect over Streamable HTTP and call calculator, word-stats, note-search, and UTC-time tools, plus read a shared notes resource, with JSON-RPC tool catalogs and spec-compliant error reporting. Runs statelessly on | |
| vite-plugin-mcp braylon-dunn/nuxt-mcp-dev Enables models to better understand a local Vite or Nuxt application by exposing development server context to AI tools. It provides a Nuxt module and a Vite plugin for adding MCP support to local dev servers. | |
| Helios brazaoo4/helios Enables AI coding agents to persist atomic, token-budgeted facts across sessions via SQLite-backed full-text search, automatically superseding outdated entries and flagging memories as stale when Git webhooks detect changes to anchored repo | |
| mcp-staffing-demo brbousnguar/mcp-staffing-demo Enables consulting-firm staffing tasks: searching consultants by skills and availability, viewing profiles, analyzing mission coverage, and booking reservations via four MCP tools. | |
| tabkit brbousnguar/tabkit Enables AI agents to read Jira and Confluence by routing requests through an already logged-in Chrome Atlassian tab, with no API token and read-only access. | |
| mcp-pymilvus-code-generate-helper brcarry/mcp-pymilvus-code-generate-helper An MCP server that retrieves relevant code snippets and documents to assist in generating pymilvus code, converting between ORM and client, and translating Milvus code between programming languages. | |
| LettuceMeet MCP brchn6/lettucemeet_cli Unofficial MCP tools for LettuceMeet to create polls, view responses, and find meeting overlaps via CLI or MCP server. |
35,401–35,450 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.