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 |
|---|---|
| Spring AI MCP Weather Server amanhogan/k3s-mcp Exposes tools for retrieving weather forecasts and alerts using the National Weather Service API. | |
| MCP Docs Assistant amanjain200/official-docs-mcp An MCP server that retrieves documentation from official sources (LangChain, LlamaIndex, OpenAI, uv) using Serper API, extracts page content, and provides context for LLM-based answers. | |
| LinkedIn Profile Data Mining amankale376/profile-researcher Enables comprehensive LinkedIn profile search, data extraction, and contact enrichment using Google Search, Apollo.io, and AI-powered analysis. Includes automated data mining workflows with database storage and CSV export capabilities. | |
| calculator-mcp-server amankhan1009/calculator-mcp-server Exposes basic calculator operations (add, subtract, multiply, divide, power, square root, modulus) through the Model Context Protocol. | |
| Postgres MCP Server amankhan1009/postgres-mcp-server An AI database assistant that connects AI clients to a PostgreSQL database for schema exploration, safe querying, and LLM-powered SQL generation and reasoning. | |
| AI Weather MCP Server amankhan1009/weather-mcp-server Combines real-time weather data with LLM-powered reasoning to deliver intelligent weather insights like clothing recommendations and travel advice. | |
| mcp-connector-for-akamai amankrokx/mcp-connector-for-akamai An unofficial MCP server that connects AI assistants to Akamai APIs, providing tools for edge diagnostics, debugging, and network analysis. | |
| acctmux amankroy/acctmux Enables coding-agent clients to use one local MCP endpoint that routes calls to isolated per-account workers, shares a single tool surface across sessions, and applies per-account policies and key pools. | |
| Tailor amanktyr/tailor Unified AI coding-agent framework combining Spec-Driven Development (SDD), AST semantic code reuse, and progressive project memory (.ai/) for Claude Code, Cursor, Windsurf, and Zed. | |
| Weather MCP Server amann001/weather-mcp-server Provides weather alerts and forecasts via MCP tools, supporting both STDIO and SSE transports. | |
| DoorDash MCP Server amannm/doordash-mcp Enables interaction with the DoorDash Drive API to create, manage, and track delivery requests including quotes, delivery creation, status checks, and cancellations. | |
| MCP Qdrant Server with OpenAI Embeddings amansingh0311/mcp-qdrant-openai This server enables semantic search capabilities using Qdrant vector database and OpenAI embeddings, allowing users to query collections, list available collections, and view collection information. | |
| Employee MCP Server amansinghbawa/employee_mcp Enables querying and managing an employee directory through MCP tools and resources, including listing, searching, adding, updating, and deleting employees. | |
| LibreLink MCP Server amansk/librelink-mcp-server Enables Claude Desktop to securely access FreeStyle LibreLink continuous glucose monitoring data, providing real-time readings, historical analysis, and health insights through natural language queries. | |
| Meetgrid MCP Server amansk/meetgrid Enables AI agents to create and manage no-login scheduling polls, collect Yes/No availability, and set or close final decisions through MCP tools. | |
| StackRadar MCP amantebriwal4321/stackradar-mcp Enables any MCP client or voice assistant to ask which developer tools are heating up, ranking and comparing them by a 0-100 momentum score derived from GitHub stars, forks, and community mentions. Returns structured breakdowns alongside sh | |
| GitHub Repository Manager MCP Server amanueltefera843110/mcp-repo-manager- Enables AI assistants to create and delete GitHub repositories with customizable settings through the Model Context Protocol, supporting both public and private repositories with secure token-based authentication. | |
| moomoo-market-data-mcp amao69904/moomoo-market-data-mcp Provides read-only real-time market data, including snapshots, quotes, candlesticks, order book, tickers, and security search, from the Futu OpenAPI to MCP clients like Codex. | |
| shared-skill-mcp amar-p6/shared-skill-mcp Enables claude.ai custom connectors to run SQL-like gviz queries against Google Sheets through a shared AWS-hosted MCP server protected by Cognito Google login, with room to add more tools over time. | |
| ishari-mcp-server amar-tya/ishari-sholawat-mcp Enables AI agents to search and retrieve read-only ISHARI shalawat content from Supabase, including verse translations, full chapters, audio recitations, reciters, and per-user bookmarks through MCP tools. | |
| readonly-postgres-mcp amar141989-dev/readonly-postgres-mcp Readonly PostgreSQL MCP server with SQL guardrails for analytical queries and schema introspection. | |
| wrave-mcp amara-khaled/wrave Enables direct, low-latency automation of Brave Browser tabs, clicks, typing, and page inspection through MCP, including compound actions like click_and_read and type_and_submit. | |
| UnknownCheats MCP amaralkaff/mcp-unknowncheat Enables programmatic interaction with the UnknownCheats forum by bypassing Cloudflare protection using a headed Chrome browser. Supports searching forums, reading threaded discussions with pagination, extracting code blocks in multiple lang | |
| MCP RAG Server amaralphp/mcp-rag-server Enables document ingestion, semantic search, and retrieval-augmented generation via MCP tools and REST API, using vector embeddings and intelligent chunking. | |
| FastAPI Database MCP Server amararun/shared-fastapi-database-mcp Provides read-only SQL query access to Postgres and DuckDB databases via MCP tools, with extensive security hardening for public endpoints. | |
| Guarded MCP Agent amardeeplakkuntla/guarded-mcp-agent Enables note management (create, read, update, delete) with a policy engine for blocking tools, human approval, and prompt injection detection. | |
| github-mcp-server amardiyab/github-mcp-server Enables AI assistants to interact with GitHub issues, pull requests, and Actions workflows through MCP tools. | |
| wolf-ms-ppt-mcp amareca/wolf-ms-ppt-mcp Enables AI agents to create, edit, and manage Microsoft PowerPoint presentations locally, including slides, text, and images, without requiring Microsoft Office. | |
| MCP CRUD Tools amareshwarvarma/mcp-mcp-crud-tools Enables interaction with Users and Products through a CRUD service REST API, providing tools for listing, creating, reading, updating, and deleting records via HTTP transport. | |
| AI Admin API MCP Server amaretto-software-labs/ai-admin-api-mcp A read-only MCP server for querying AI provider administration APIs, providing normalized usage, cost, and dashboard data for OpenAI and Anthropic. | |
| unity-agent-gateway amarinoa/unity-agent-framework Enables AI agents to access Unity Editor project information, scene hierarchies, object inspection, selection state, and console logs through MCP. | |
| Discord Cloud MCP amarisaster/discord-cloud-mcp Provides full Discord API access via the Model Context Protocol, allowing users to manage servers, messages, channels, and webhooks through MCP clients. It is specifically designed for deployment on Cloudflare Workers to facilitate remote b | |
| Lovense Cloud MCP amarisaster/lovense-cloud-mcp Enables remote control of Lovense toys through Claude using natural language commands. Supports vibration patterns, presets, and intensity control from any device via Cloudflare Workers. | |
| Synesthesia amarisaster/synesthesia Downloads audio from YouTube, analyzes with Essentia for BPM, mood, energy, spectrograms, and fetches synced lyrics from LRCLIB. | |
| Tempo amarisaster/tempo An MCP server for Spotify control and synchronized lyrics retrieval that enables playback management, queue navigation, and music search capabilities. It also features perception tools for real-time track analysis, including BPM, key detect | |
| Sensei MCP amarodeabreu/sensei-mcp Multi-persona engineering mentor with 64 specialized AI personas that injects engineering standards before Claude reasons, transforming passive documentation into active collaborative guidance. | |
| cursor-talk-to-figma-mcp amarpaniwork/custom-talk-to-figma-mcp Enables Cursor AI to read and modify Figma designs via the Model Context Protocol, allowing programmatic control over documents, components, styles, and more. | |
| Vendor Risk Assessment MCP Server amarshikhar/mcp-demo Enables AI-powered vendor risk assessment using AWS Titan, allowing users to evaluate individual vendors, compare multiple vendors, and get industry risk benchmarks through natural language queries. | |
| P12 SRE Ops MCP Server amarshiv86/p12-sre-mcp Enables SRE operations through natural language, providing tools to query SLO status, fetch runbooks, query alerts, and manage incidents with audit logging and latency tracking. | |
| Universal Architecture Context MCP Server amaru221/mcp-architecture-context Enables AI assistants to retrieve a project's architecture overview and file structure, auto-detecting monolith or multiproject layouts and exposing module listings to reduce token consumption. | |
| Lavka MCP Server amateurenv/d8t2_mcpcore_team_integration Enables AI agents to check merchandise stock, user balances, and order status, and to create, cancel, and issue shop orders while enforcing the shop's rules and transactional consistency. | |
| Plugin Health Auditor MCP Server amatsugi-120/plugin-health-auditor Provides audit_plugin_health and prepare_semantic_review tools for deterministic inspection of Codex plugins and Agent Skills, generating evidence-backed reports without executing or transmitting target code. | |
| todoist-mcp amattas/todoist-mcp Enables Claude Desktop and other MCP clients to manage Todoist tasks, projects, and labels through natural language. | |
| jira-mcp-server amattu2/jira-mcp-server Integrates Jira tickets with GitHub Copilot Chat, fetching ticket details, linked tickets, and metadata to enhance context for AI-driven code suggestions. | |
| MCP Ops Brief Agent amatvictoriacoram1994-spec/mcp-ops-brief-agent Enables agencies to generate deterministic, ranked operational briefs by combining delivery status, financial performance, and recent client communication from ClickUp, QuickBooks, and Gmail. | |
| MCP-TEST amayawang/amayawang.github.io my github website | |
| PCAP-Analyzer MCP Server amaze-with-ai/pcap-analyzer Enables natural language analysis of network packet captures, including protocol detection, flow analysis, and security threat identification, integrated with AI assistants. | |
| doubao-tools amazing1102/doubao-tools-mcp 一个MCP视觉分析工具，将本地图片交给豆包视觉模型分析，帮助Claude Code和DeepSeek理解截图内容。 | |
| mcp-demo amazing129/mcp-demo A minimal MCP server example demonstrating Tools, Resources, and Prompts. It enables calculations, time queries, note management, and code review prompts via stdio transport. | |
| skills-mcp-server amazingashis/mcp-deployment Exposes Cursor-style skill packs (SKILL.md trees) via MCP resources, tools, and prompts, enabling any MCP client to list, get, search skills, and retrieve skill context. |
27,951–28,000 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.