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 |
|---|---|
| my-mcp-server devashish234073/my-mcps A simple Node.js MCP server that exposes three tools: greet for personalized messages, calculate for basic math operations, and weather_info for mock weather data retrieval. | |
| OpenRouter LangChain MCP Server devashishkumar/openrouter-langchain-mcp-server Enables an OpenRouter-powered chatbot to query MongoDB collections through MCP tools such as get_collections and query_collection. | |
| MCP-Powered-AI-Job-Recommendation-Engine devashishpandey1103/mcp-powered-ai-job-recommendation-engine Enables AI assistants to recommend jobs, parse candidate profiles, compute semantic skill match scores, and filter opportunities by location through standardized MCP tools. | |
| Ads MCP Server devastion/ads-mcp Enables AI clients to search and retrieve advertising data such as ads and niches through MCP tool calls that forward to the REST API. Each tool call is a billable, rate-limited read authenticated with scoped API keys. | |
| eve-mcp-handshake-repro devasur/eve-mcp-handshake-repro Serves a stateless Streamable-HTTP endpoint with an echo tool, letting users observe exactly how many HTTP requests are involved in a single MCP tool call. | |
| AI-Code-Reviewer devatraj/ai-code-reviewer An installable MCP server that reviews diffs/PRs against a target repository's own coding conventions, learned via RAG over its code, docs, and lint config, citing specific file:line sources. | |
| LLM Router MCP devatva24/llm-router-mcp Route prompts intelligently across Claude, Gemini, and GPT-4o, automatically picking the best model for every task while minimizing token cost. | |
| mcp-carousel-engine devauthentic/mcp-carousel-engine Enables AI coding agents to generate ultra-creative, non-overflowing 4:5 vertical carousels with native Chromium rendering, using modular React primitives, strict design rules, and curated creative archetypes. | |
| Cityflo on-time performance MCP devbathani/cityflo-internal-mcp Answers operational questions about route on-time performance, such as lateness rates and trip evidence, using structured tools for route summary, trip lateness, and data quality. | |
| Apple RAG MCP devbifta/appler Provides AI agents with instant access to official Apple developer documentation, Swift programming guides, design guidelines, and Apple Developer YouTube content including WWDC sessions. Uses advanced RAG technology with semantic search an | |
| parking-recommendation devbluelemony-creator/malhaebwa-parking Provides destination-based public parking lot recommendations in Seoul. It converts destinations to coordinates, finds nearby public parking lots, and estimates wait times using real-time availability and historical statistics. | |
| image-generator devbrother2024/mcp-generate-image image-generator | |
| TypeScript MCP Server Boilerplate devbrother2024/mcp-server-251215 A starter template for quickly developing Model Context Protocol (MCP) servers using the TypeScript SDK and Zod for schema validation. It includes example implementations for custom tools and resources like calculators, weather services, an | |
| TypeScript MCP Server Boilerplate devbrother2024/mcp-server-260212 Provides a starting template for building MCP servers with TypeScript, including examples of tools and resources to accelerate development. | |
| TypeScript MCP Server Boilerplate devbrother2024/mcp-server-test-251209 A boilerplate project for quickly developing MCP servers using TypeScript, featuring calculator and greeting tools as examples, plus resource management capabilities. | |
| TypeScript MCP Server Boilerplate devbrother2024/mcp-server-test2-251209 A boilerplate project for quickly developing Model Context Protocol servers using TypeScript, featuring example tools (calculator, greeting) and resources (server info) with Zod schema validation. | |
| TypeScript MCP Server Boilerplate devbrother2024/my-mcp-server-251027 A boilerplate project for quickly developing MCP servers with TypeScript, featuring example tools (calculator, greeting, time) and resources with Zod schema validation. | |
| TypeScript MCP Server Boilerplate devbrother2024/my-mcp-server-251127 A boilerplate project for quickly developing MCP servers using TypeScript SDK, featuring example tools (calculator, greeting) and resources with Zod schema validation. | |
| TypeScript MCP Server Boilerplate devbrother2024/my-mcp-server-251209 A boilerplate project for quickly developing Model Context Protocol (MCP) servers using TypeScript SDK, with example tools (calculator, greeting) and resources (server info) included. | |
| TypeScript MCP Server Boilerplate devbrother2024/my-mcp-server-260402 A foundational project for quickly developing Model Context Protocol servers using the TypeScript SDK and Zod for schema validation. It features pre-implemented examples for tools like a calculator and greeting service, along with templates | |
| my-mcp-server devbrother2024/my-mcp-server-260730 A TypeScript MCP server boilerplate with Streamable HTTP support, providing tools for greeting, calculation, time, geocoding, weather, and image generation, plus a server-info resource and code-review prompt. | |
| subq-snap-mcp devbux/subq-snap-mcp Enables MCP clients to obtain typed, probabilistic decisions from text or structured state and up to four images—choosing among labeled options, scoring on ordered scales, and estimating whether propositions are true—for routing, triage, mo | |
| typesafe-mcp devbux/typesafe-mcp Enables agents to ask TypeSafe AI's Jev decision model typed questions — choices, scores, true/false propositions, and image bounding boxes — about a text or JSON state, returning structured answers with calibrated probabilities and confide | |
| Roblox Executor MCP Server devbydev99/sspy-roblox-executor-mcp Enables AI agents to interact with a running Roblox game client, including executing Lua code, inspecting scripts, searching instances, intercepting remote events via Sigma Spy, and controlling the GUI. | |
| search-console-mcp devbyray/search-console-mcp MCP server for Google Search Console, enabling querying site performance, URL inspection, sitemaps, and more via typed tools with OAuth authentication. | |
| MCP-MEmu devbysatyam/mcp-memu AI-powered Android emulator control via Model Context Protocol, enabling agents to manage VMs, install apps, automate UI, and more. | |
| PaperTrail devcaos/duly Enables users to turn household paperwork into answers about upcoming deadlines, warranties, and plain-language explanations, and to draft related messages such as payment extension requests. | |
| open-payments-mcp devcer/open-payments-mcp Enables Open Payments operations such as creating incoming payments, quotes, and outgoing payments via the Interledger protocol. Supports wallet address retrieval, grant management, and payment flow automation. | |
| FileMCP devcheyannagraham/filemcp Minimal MCP file server for safe file operations under a local AgentFiles directory. | |
| CodeNav MCP devchux/codenav-mcp CodeNav MCP is a remote Model Context Protocol server for exploring a codebase, exposing tools to list files, read source, search text, inspect imports/exports, find functions/classes, detect unused code, and summarize project structure. | |
| tds-mcp devcmss/tds-mcp Enables AI assistants to compile AdvPL/TLPP sources, generate and apply patches, and inspect the RPO of TOTVS Protheus servers. | |
| MCP Notes Server devcodehub2004/mcpserver Enables users to create and manage notes through Claude Desktop using MCP tools. | |
| mcp-playwright devcodingskill/playwright-mcp-tools Enables browser automation for AI assistants via Playwright, supporting multiple browsers, sessions, and tools for web interaction and testing. | |
| SIEMen devcraftxcoder/sieme Enables AI agents to read, write, and search security findings, engagement memory, and semantic triage via MCP tools on Cloudflare Workers. | |
| Math MCP Server devcraftyaseen/mathmcp Provides four fundamental arithmetic operations (add, subtract, multiply, divide) as MCP tools with zero-division protection. | |
| LogiSwarm AI MCP Server devcrazy2812/logistic-agent-mcp Enables autonomous multi-agent logistics operations through MCP tools, resources, and prompts for routing, inventory, cargo inspection, disruption recovery, and conversational dispatch. It supports both modern and legacy MCP specs over stdi | |
| cdmx-mcp devcsar/cdmx-mcp Provides direct access to Mexico City's open data including crime, 911 calls, air quality, ECOBICI bike sharing, and business registries through Claude without requiring data ingestion code. | |
| mysql-mcp devcy0922/mysql-mcp Enables safe read-only SQL queries on MySQL/MariaDB databases with multi-domain support, strict selection controls, and audit logging. | |
| OpenFeature MCP Server devcyclehq-sandbox/openfeature-mcp Provides OpenFeature SDK installation guidance through MCP tool calls. Enables AI clients to fetch installation prompts and setup instructions for various OpenFeature SDKs across different programming languages and frameworks. | |
| @context-anchor/mcp-server devdario/context-anchor Git-native MCP server for managing AI context across sessions. Enables LLMs to access project and feature context via markdown files, preserving decisions and constraints. | |
| Oath Wallet Knowledge devdasx/oath-wallet Read-only MCP server for Oath Wallet. Provides public product documentation, supported-network information, security guidance, release notes, app-screen references, and Journal content without wallet access. | |
| gmail-mcp-server devdattatalele/gmail-mcp-server Enables AI-powered inbox management with natural language commands through Claude Desktop. Supports sending, reading, searching, organizing emails, and managing labels using Gmail API with automatic authentication. | |
| yunxin-console-mcp devdengchao/yunxin-console-mcp Enables users to manage NetEase Yunxin console applications, app configuration, IM settings, and statistics through MCP tools. | |
| Perplexity Web MCP devdotbo/perplexity-web-mcp MCP server providing 22 tools to query Perplexity AI's premium models (GPT-5.4, Claude 4.7 Opus, etc.) with citations, source discovery, and rate limit checking for AI agents. | |
| agents-control devedbox/agents-control Enables one coding agent to inspect, configure, debug, and repair another agent over stdio MCP, with redacted reads and confirm-gated writes and restarts. | |
| Planner MCP develop-bg/dijkman-planner-mcp A remote Model Context Protocol server that enables Claude to read, create, assign, and close Microsoft Planner tasks for a small team, using Microsoft Graph with app-only authentication. | |
| Banana developer-akademie-youtube/banana_mcp_tutorial A simple MCP server that provides tools for adding numbers, creating text files, and logging entries. | |
| Leave Manager MCP Server developer-ashish31/leavemanagermcp-js MCP server for managing employee leave requests, balances, and types with natural language, using a dummy in-memory database. | |
| linkedin-mcp developer-tusharchauhan/linkedin-mcp Controls the user's LinkedIn account through a logged-in browser session, enabling post publishing, profile viewing and editing, job searching, and Easy Apply submissions from chat. | |
| bricks-mcp developer2013/bricks-mcp-open Comprehensive MCP server for Bricks Builder with 100+ tools to manage pages, templates, styles, SEO, and content directly from AI assistants like Claude Code. |
43,951–44,000 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.