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 |
|---|---|
| squadco-mcp abdushakurob/squadco-mcp Provides your AI coding assistant with direct, structured access to the full SquadCo API documentation for payments, transfers, virtual accounts, VAS, and webhooks. | |
| mcp-scaffold abduznik/mcp-scaffold Enables you to create and run your own custom MCP tools using plain Node.js, then connect them to AI clients like Claude, Cursor, or Windsurf. | |
| pi-session-recall abdwhb-png/pi-session-recall Provides read-only access to local Pi coding-agent session transcripts, enabling literal text search, exact session lookup by UUID, deterministic focused context extraction, and stable paginated reading of past conversations. All operations | |
| Trello MCP Server abdwyer/trellomcp Provides seamless integration with Trello's API to manage boards, lists, and cards through natural language. It supports full CRUD operations, card movement, and the ability to load Trello resources directly into an LLM's context for analys | |
| TDengine Query MCP Server abeautifulsnow/tdengine-mcp A Model Context Protocol (MCP) server that provides read-only TDengine database queries for AI assistants, allowing users to execute queries, explore database structures, and investigate data directly from AI-powered tools. | |
| remote-mcp-server-authless abeclark19/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling connection to clients like Cloudflare AI Playground and Claude Desktop. | |
| VisualQ MCP Server abecms/visualq-mcp Enables running visual regression tests, polling results, and reading structured failure reports via MCP clients like Cursor or Claude Desktop. | |
| Frontend Guru MCP abedell-g2/frontend-guru-mcp Transforms design inputs (URLs, screenshots, descriptions) into production-ready React components following G2's Elevate 2.0 design system, providing both an MCP server for Claude Code and a web interface. | |
| MCP Enterprise Tools Lab abedk21/mcp-enterprise-tools-lab Enables read-only access to synthetic, tenant-scoped knowledge, tickets, and runbooks, plus draft handoff generation, through four MCP tools and a workspace metadata resource. | |
| Mini CRM abeer-fatima-dev/mini-crm-mcp-client-manager Enables managing client records with tools for adding, listing, retrieving, updating, and deleting clients, plus a read-only resource for viewing all clients. | |
| YApi MCP Server abeixiaolu/yapi-mcp Enables access to YApi interface documentation by retrieving API details through interface IDs or direct YApi URLs. | |
| mermaid-mcp-server abekdwight/mermaid-mcp-server Provides MCP tools to validate Mermaid diagram syntax, render diagrams to SVG, and get documentation links. | |
| Oura Ring MCP Server abekek/oura-mcp-python A Python-based Model Context Protocol server that provides AI assistants with access to Oura Ring health and fitness data across 15+ endpoints. It enables querying metrics like sleep, activity, readiness, and cardiovascular health through s | |
| Personal Intelligence System abekek/personal-intelligence-system Captures AI-assisted work into a searchable ledger and exposes it via MCP for querying past conversations and decisions. | |
| blog-mcp abel-castro/blog_mcp Enables creating draft posts and listing published posts on abelcastro.dev directly from Claude. | |
| Fermi abel30567/fermi-mcp Provides a portable AI control plane with shared memory, permissions, and skills across multiple MCP hosts and unattended channels, enabling consistent agent behavior. | |
| Fermi abel30567/orch-bench-fermi-mcp A portable AI control plane that lets connected MCP hosts, chat clients, and messaging channels share persistent memory, versioned skills, unified search, permission-gated tools, sandboxed code execution, browser automation, and queued task | |
| MariaDB MCP Server abel9851/mcp-server-mariadb An MCP server implementation that enables Claude to execute read-only queries against MariaDB databases and explore database schemas through natural language. | |
| agente-ecommerce-mcp-memoria abelcierto/agente-ecommerce-mcp-memoria An MCP server that exposes a LangChain agent with short-term memory to analyze real e-commerce data through predefined SQL tools, enabling natural language queries on sales, customers, and logistics. | |
| gimp-mcp abelduarte/gimp-mcp Control GIMP from AI assistants via the Model Context Protocol, enabling image editing automation through natural language commands. | |
| sansan-chrome-mcp abelllee/sansan-chrome-mcp Enables AI assistants to control Chrome browser operations such as navigation, reading pages, taking screenshots, managing tabs, and more via a Chrome extension and native messaging. | |
| quantity-engine abellmugano/quantity-engine MCP server (stdio, official Python SDK) exposing a single tool: quantity_execute. Performs dimensional calculation and unit conversion with evidence. Solves silent unit errors in LLM agent chains: 20 m/s × 3 h returns 216 km. | |
| California Restaurant Concierge abellucido/restaurant-concierge-mcp Enables an LLM agent to search and filter California restaurants by cuisine, city or neighborhood, vibe, maximum price, and minimum rating, fetch full details and customer reviews for individual restaurants, and retrieve an overview of avai | |
| memorepo abelmaro/memorepo Read-only, cross-repository code intelligence for coding agents. Captures GitHub repositories as immutable commit snapshots, indexes their shared code graph, and exposes space-scoped search and verified source through MCP. | |
| web-revive abelo9996/web-revive Enables an agent to locate embedded Flash or Java games (on live pages or in the Internet Archive), inspect whether they can run, fetch the Ruffle or CheerpJ runtime, package a self-contained static site, and verify playback in a real headl | |
| Cocos MCP Kit abelsdf/cocos-mcp-kit Enables development assistants to inspect and work with Cocos Creator projects through a local MCP server. | |
| docmost-mcp-oss abelsr/docmost-mcp-oss Enables AI assistants to search, read, create, and modify Docmost pages, spaces, and comments via REST and Yjs WebSocket collaboration. | |
| Plane MCP Server abelsr/plane-mcp-oss Enables AI clients to read and manage Plane projects, work items, states, labels, cycles, modules, members, and comments via the Plane REST API. | |
| mcp-explorer abeltramo/mcp-explorer A controllable, observable MCP server for dynamically setting tools and intercepting calls in real time, useful as a mock/MITM harness for testing MCP clients. | |
| zar-jobs-ai-connector abelvalle/zar-jobs-ai-connector MCP server that enables AI assistants to search and normalize job offers from portals like InfoJobs, while keeping the user in control of decisions. It provides read-only tools and respects official APIs and credentials. | |
| mcp-mysql-service abenassi/mcp-mysql-service An MCP server that enables Claude to execute SQL queries on MySQL databases with automatic connection management and error handling. | |
| MCP Calculator abenitez573/mcp_calculator An MCP server that enables AI models to perform mathematical calculations and other tasks like email operations and knowledge search through a bidirectional communication protocol. | |
| Google Tasks MCP Server abenke/gtasks-mcp Enables LLMs like Claude to manage Google Tasks by listing, creating, updating, completing, and deleting tasks and task lists, including setting due dates and notes. | |
| Spotify MCP abenke/spotify-mcp Enables searching and managing Spotify playlists, tracks, and user information through the Spotify Web API. | |
| Code Executor MCP Server aberemia24/code-executor-mcp Universal MCP server for executing TypeScript and Python code with progressive disclosure, reducing token usage by 98% by enabling on-demand access to all other MCP tools through code execution rather than loading tool definitions directly. | |
| MCP-Discord aberg565/mcp-discord Enables AI assistants to interact with Discord by logging in as a bot and managing servers, channels, roles, members, messages, forum posts, reactions, and webhooks. | |
| ical-mcp aberhamm/ical-mcp MCP server for Apple Calendar and CalDAV providers. Enables listing, creating, updating, deleting events, and checking free/busy status with per-calendar write protection. | |
| SEAF MCP Server aberkromb/seaf-mcp Provides Model Context Protocol access to the SEAF ArchTool REST API, enabling agents to inspect sections and entities, navigate relations, query datasets, and run JSONata expressions against a SEAF portal. | |
| code-vector-sync abernaughty/code-vector-sync Enables semantic code search over a local codebase using Qdrant vector embeddings and OpenAI embeddings, allowing natural language queries from MCP-compatible clients like Claude Desktop. | |
| DeepSeek MCP Sample aberry-h/mcp A Node.js + TypeScript MCP server that proxies to DeepSeek's Chat, Image, and TTS APIs for conversation, image generation, and text-to-speech. | |
| VSCode MCP Server abertrand450/vscode-mcp Enables AI coding agents and MCP-compatible clients to pull real-time language-server data from a running editor instance, including diagnostics, hover/definition/signature info, symbol references, file opening, and workspace-wide renames. | |
| LinkedIn MCP Server abetoluwani/linkedin-mcp-server Enables AI assistants to read LinkedIn profiles, company pages, jobs, messages, and feed through a user's logged-in browser session. | |
| codex-app-mcp abetoots/codex-app-mcp Enables MCP clients to start new Codex conversations and continue existing threads, exposing codex and codex-reply tools over stdio via the Codex app-server protocol. | |
| tokensift abetoots/tokensift Enables read-only token due-diligence by querying keyless public APIs for honeypot checks, rug-pull risk reports, DexScreener pair/token data, and Solana prices, returning standardized envelopes with caching and rate-limit handling. | |
| webadb-agent abewartech/webadb-agent Enables AI agents to control a physical Android device or Docker-hosted emulator over ADB by taking screenshots and performing taps, swipes, key presses, text input, shell commands, app launches, and device info queries. It runs as a local | |
| WP MCP Server abhalani648/mcp Hosted MCP server that bridges Claude.ai with one or more WordPress sites. | |
| Content Evidence Studio abharadwaj-cell/content-evidence-studio Provides deterministic editorial tools over MCP for creating briefs, reviewing citations and drafts, comparing revisions, suggesting internal links, and planning content refreshes using supplied evidence. | |
| Marketing Ops MCP abharadwaj-cell/marketing-ops-mcp Enables evidence-first marketing analysis through ChatGPT-compatible MCP tools for funnel metrics, transaction reconciliation, experiment design and analysis, and UTM campaign URL building, with portable JSON, CSV, Markdown, and HTML report | |
| Search Evidence MCP abharadwaj-cell/search-evidence-mcp Enables ChatGPT-compatible MCP clients and OpenAI agents to run static HTML audits, analyze Search Console exports, and perform opt-in bounded same-origin crawling with explicit review queues and portable reports. | |
| RetellAI MCP Server abhaybabbar/retellai-mcp-server A Model Context Protocol server implementation that enables AI assistants to interact with RetellAI's voice services for managing calls, agents, phone numbers, and voice options. |
23,001–23,050 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.