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 |
|---|---|
| discord-dm-mcp 0xshaito/discord-mcp A tiny MCP server that lets Claude send Discord direct messages through a bot with nothing to host. | |
| Docker MCP Server 0xshariq/docker-mcp-server A comprehensive MCP server that provides advanced Docker operations through a unified interface with 16 MCP tools and 25+ CLI aliases, enabling secure container lifecycle management, multi-container orchestration, registry publishing, and s | |
| email-mcp-server 0xshariq/email-mcp-server Cross-platform MCP server and CLI for email operations, including send, read, search, and contact management, compatible with Gmail, Outlook, Yahoo, and any IMAP/SMTP providers. | |
| GitHub MCP Server 0xshariq/github-mcp-server Provides 29 Git operations and 11 workflow combinations for AI assistants and developers, enabling comprehensive Git repository management through a standardized interface. | |
| nibble 0xshubhs/nibble Enables LLMs to search, retrieve, and store local memory captures, manage reminders, and access memory statistics via MCP. | |
| rubric-attested-mcp 0xsims/rubric-attested-mcp Enables MCP-wired agents to fetch live, historical, or proof-backed Base-mainnet asset prices signed with ML-DSA-65 and anchored to Hedera, automatically handling x402 USDC payments; it also lists the provider's available x402 services. | |
| Mini+ Agent Kit MCP Server 0xsoftboi/mini-plus-agent-kit Enables driving a BitRobot-compatible ground robot (e.g., Earth Rover Mini+ or Waveshare UGV) through high-level verbs like move, turn, look, and capture work, with optional on-chain recording of verifiable robotic work. | |
| zenvoy-mcp 0xsonu/zenvoy MCP server for the Zenvoy Markdown notes app, providing 26 tools for vault operations like reading, creating, searching notes, and managing tasks, templates, and comments. | |
| Splits MCP Server 0xsplits/splits-cli Enables managing Splits transactions, accounts, signers, and authentication through natural language or AI assistants. | |
| pentest-ai 0xsteph/pentest-ai Autonomous pentests from one command: real security tools, working PoCs, and audit-ready reports, all driven via MCP. | |
| codeintel 0xstubbs/code-intel MCP server that provides code intelligence by indexing configured repositories, extracting deterministic facts, and enabling graph queries, drift checks, and maps via Kuzu-backed MCP tools. | |
| MCP Server Template 0xstyles/mcp Minimal template for building Model Context Protocol servers with Bun and TypeScript, including schema-based state validation, YAML persistence, and tool registration. | |
| nft-farm-mcp 0xsyncroot/nft-farm-mcp MCP server that scans EVM chains to identify profitable free-mint NFT collections and wallets farming them, ranking by on-chain secondary PnL. Supports multiple chains via Seaport and offers tools for scanning collections, wallets, and job | |
| Grafana MCP Server 0xteamhq/mcp-grafana Enables AI assistants to interact with Grafana dashboards, datasources, alerts, incidents, and monitoring data through 43 comprehensive tools. Supports querying Prometheus metrics, Loki logs, managing incidents, and dashboard operations wit | |
| coolify-mcp 0xtlt/coolify-mcp MCP server for managing Coolify instances, enabling control of applications, databases, services, servers, and more via natural language. | |
| MyMCPs 0xtlt/mymcps Self-hosted MCP gateway that exposes a single MCP URL to AI agents and routes tools/resources to many upstream MCP servers behind it. | |
| SMSBulk MCP Server 0xtolgadegen/smsbulk-mcp Enables AI clients and assistants to order virtual phone numbers and disposable email addresses, and retrieve verification codes (OTPs) from SMS and email messages for account verification workflows. | |
| LeechCore MCP 0xtracepacket/leechcore-mcp Enables read-only physical memory inspection through MCP, providing tools to read, search, hash, and decode memory from live LeechCore targets or offline raw files with configurable ranges and limits. | |
| buzz-mcp 0xtsotsi/buzz-mcp A TypeScript MCP server for the CorePrt Nostr relay, enabling MCP-compatible clients to publish and read Nostr events. Currently a scaffold with planned tools for event publishing, fetching, searching, and subscribing. | |
| technocore-mcp 0xwarg2/technocore-kit Enables MCP-capable runtimes to read agent message rooms, sign and post public messages, and create or verify Ed25519 contribution proofs for Technocore. | |
| Token Info MCP Server 0xwuchuan/token-info-mcp Provides comprehensive smart contract analysis for EVM tokens, including proxy contract detection, ownership chain discovery, and OpenZeppelin AccessControl role management across multiple blockchain networks. | |
| mcp-instagram-dm 0xx7c00/mcp-instagram-dm MCP server for Instagram Direct Messages. Read inbox, send messages, search conversations, react to messages, manage pending requests, and more. 15 tools with cookie-based authentication. | |
| Roblox MCP Server 0xxrer/mcp Bridges AI assistants with Roblox game environments in real-time via a Lua client and WebSocket connection. Enables AI tools like Claude to navigate instances, execute scripts, monitor remote events, and interact with the Roblox API through | |
| claude-c2 0xyg3n/claude-c2 Enables natural language command and control of remote systems across multiple platforms through Claude AI using the Model Context Protocol. | |
| Ripple-MCP 0xyubo/ripple-mcp A field-level semantic change impact analysis MCP server for Claude Code, enabling natural language queries to find affected code when modifying fields, strings, or functions across multiple languages. | |
| Firecrawl MCP Server 0xzapata/firecrawl-mcp-server Integrates Firecrawl for web scraping, crawling, search, and content extraction capabilities. Supports single/batch scraping, URL discovery, structured data extraction, deep research, and AI-powered web analysis with automatic retries and r | |
| garment-cad-mcp 0xzoharhuang/garment-cad-mcp Agent-facing garment CAD control plane providing local stdio MCP servers, a shared Python SDK, preview/commit transactions, and GarmentCode-compatible serialization for designing garments programmatically. | |
| DeepL MCP Server 1-arijits/deepl-mcp-proffessional Enables translation and text rephrasing using DeepL's API through a cloud-deployed MCP server. Provides translation between multiple languages, text rephrasing, and language detection capabilities with professional deployment features. | |
| Weather MCP Server 1-zym/weather-mcp-server Enables real-time weather queries for 12 supported Chinese cities and global cities via wttr.in, including current temperature, humidity, condition, wind speed, and visibility. It also provides tools to list supported cities and retrieve se | |
| Nexus MCP 10-gaurav-01/nexus-mcp Enables Claude to orchestrate tasks across 27 AI providers, run multi-agent plans, and conduct multi-model councils for decision-making. | |
| DentOps Copilot 100-mitra/dentops-copilot An MCP-native agentic copilot for dental practices that orchestrates multiple MCP tools to analyze X-rays, pull patient history, generate drafts, and propose recalls, streaming results live to a React dashboard. | |
| dek-mcp 1000bath/dek-mcp Local MCP server exposing the dek-memory hybrid memory engine over stdio, with optional ChatGPT tools for managing account memories via a browser profile. | |
| Playwright MCP 1000carlospena-prog/playwright-mcp-render-mthnzbdq Enables LLMs to drive a hosted headless Chromium browser over HTTP, performing navigation, clicks, typing, and page reading through accessibility snapshots, protected by bearer-token authentication. | |
| Playwright MCP 1000carlospena-prog/playwright-mcp-render-mtho1eft Enables AI tools to drive a hosted headless-Chromium browser over HTTP, letting them navigate, click, type, and read web pages through accessibility snapshots. | |
| Playwright MCP 1000carlospena-prog/playwright-mcp-render-mthoinc7 Enables AI assistants to control a hosted headless Chromium browser over HTTP via the Model Context Protocol, allowing them to navigate pages, click, type, and read structured accessibility snapshots. | |
| Stagehand MCP Server - Local Mode 1000ml-io/stagehand-mcp-local Enables local browser automation using Stagehand without cloud services. Supports navigation, data extraction, and autonomous agent tasks through natural language. | |
| notion-gpt-image-mcp 1000ssam/notion-gpt-image-mcp A Notion custom MCP server that uses OpenAI's gpt-image-2 to generate images and insert them directly into Notion pages. | |
| 100Hires MCP Server 100hires/mcp-server Official Model Context Protocol server for 100Hires — the applicant tracking system for recruiting teams. Exposes the full 100Hires API v2 as 130 MCP tools, enabling AI assistants to manage candidates, jobs, applications, interviews, messag | |
| SF Express MCP Server 100kgforest/sf-express-mcp-server Enables integration with SF Express shipping and logistics APIs for order management, shipment tracking, route queries, and logistics services through natural language interactions. | |
| Drive-Time Plotter MCP 100shpaik/mcp-gmap-time Analyzes traffic patterns throughout the day using Google Maps API and provides visual insights and recommendations for optimal commute times. | |
| pop-pay 100xpercent/pop-pay-python Project Point One Percent - Agent Pay \[pop-pay] is a payment guardrail and one-time flow protocol specifically designed for Agentic AI (e.g., Claude Code, OpenClaw). It enables agents to handle financial transactions safely without risking | |
| Boardstate MCP Server 100yenadmin/boardstate Enables AI agents to compose and edit dashboards through MCP tools, allowing them to manage tabs, widgets, layout, and data bindings via a unified control plane. | |
| tts-hub 1010323691/tts-hub Enables AI agents to manage voices and generate speech, multi-character dubbing, and batch audio through a local TTS service, including health checks and job polling. | |
| Urumi MCP Gateway 1012aaditya/urumi-mcp-gateway Enables teams to access every enabled MCP tool through one authenticated URL, with per-user attribution and audit logging, from MCP clients or a dashboard chat agent. | |
| boss-cli 1013503897/boss-cli MCP server for searching BOSS直聘 (Boss Zhipin) job listings. It provides a boss_search tool that supports multi-city queries, keyword filtering, and JSON output for AI agents. | |
| sse-email-mcp-server 1018053166/sse-email-mcp-server Provides email sending and receiving via SMTP/IMAP/POP3, supporting major email providers and dynamic authentication for AI assistant integration. | |
| stock-mcp-server 1018053166/stock-mcp-server A MCP server that fetches real-time Chinese stock data from East Money, supporting quotes, K-line charts, rankings, shareholder data, and more. | |
| ArchNav MCP Server 1020911401/archnavmcpserver Architecture-aware code navigation system for AI agents, providing line-level symbol location, layered architecture detection, and dual-engine hybrid analysis with 22 MCP tools. | |
| discord-ai-mcp 1036007003-wq/discord-ai-mcp A free MCP server for growing Discord communities, offering tools to search public servers, analyze engagement, and draft messages, with optional premium AI features powered by DeepSeek. | |
| github-stars-mcp 1036007003-wq/github-stars-mcp Analyzes and compares GitHub repositories, tracks star growth, and offers AI-powered README optimization to help grow open-source projects. |
21,651–21,700 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.