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 |
|---|---|
| Firecrawl MCP Server amokorg/firecrawl-mcp-server-1 Integrates with Firecrawl for web scraping, enabling capabilities like scraping, crawling, searching, extracting, deep research, and batch scraping with JavaScript rendering and smart content filtering. | |
| mcp-server-chatsum amokorg/mcp-server-chatsum Enables querying and summarizing chat messages from a local database. | |
| mcp-server-chatsum amokorg/mcp-server-chatsum-1 MCP server to summarize chat messages from a local database. | |
| cloudflare-mcp-server amokorg/mcp-server-cloudflare Enables natural language management of Cloudflare services including Workers, KV, R2, D1, Queues, and more via the Model Context Protocol. | |
| Cloudflare MCP Server amokorg/mcp-server-cloudflare-1 Manage Cloudflare resources such as Workers, KV, R2, D1, Durable Objects, and more using natural language via the Model Context Protocol. | |
| Neon MCP Server amokorg/mcp-server-neon Enables managing Neon projects, databases, and running SQL queries through natural language via Model Context Protocol. | |
| Neon MCP Server amokorg/mcp-server-neon-1 Enables natural language interaction with Neon PostgreSQL databases, supporting project management, SQL execution, and database migrations through MCP. | |
| Playwright MCP amokorg/playwright-mcp-aztp A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. | |
| skrape amokorg/skrape-mcp Converts any webpage into clean, LLM-ready Markdown, removing noise and supporting JavaScript rendering. | |
| skrape amokorg/skrape-mcp-1 Converts any webpage into clean, LLM-ready Markdown using the skrape.ai API. Enables easy integration of web content into LLMs like Claude. | |
| wp-mcp amolb1986/wp-mcp Enables direct interaction with WordPress sites via Claude using the REST API, allowing reading, creating, updating, and deleting content securely with application passwords. | |
| code-search amolchanov/mcp-code-search Enables semantic code search across indexed code folders using vector embeddings, with support for multiple embedding providers and automatic file watching. Provides an admin UI and integrates with MCP clients for natural language code quer | |
| users amoljagtap17/2026-typescript-mcp-server MCP server that serves tools for interacting with a users API over stdio, supporting operations like finding users. It provides a validated configuration and structured logging for building MCP-based user management workflows. | |
| agent-voice amolkekan/agent-voice Enables macOS users to hear short spoken summaries of agent replies using the built-in say command, while keeping full details in the chat. Works with any MCP-compatible host and requires no cloud or API key. | |
| agent-archive amoncon/agent-archive Publishes an MCP server that lets other AI agents browse a project's unified cross-agent session archive: list projects, view timelines, run full-text searches, read existing digests and session summaries, read session bodies in bounded chu | |
| Lore amond-ai/kennen Enables MCP-compatible AI assistants to save, recall, and reason over a persistent, shared memory vault stored as Notion pages, so conversations, decisions, tasks, and entities survive session resets, new branches, and handoffs between team | |
| a2a-meta-clones amondieu/a2a-meta-clones Deployable MCP clone services for A2A-Meta, hosting pending clones via a multiplexer for Railway deployment. | |
| gitea-mcp amonstack/gitea_mcp MCP server for managing Gitea repositories via the Gitea API, enabling operations on issues, comments, labels, milestones, and repository info. | |
| jev-answers amooebrahim/jev-answers Enables MCP clients to send files, globs, directories, and typed yes/no, choice, or score questions to TypeSafe's Jev decision model, returning the provider's raw probabilistic answer unchanged. Each request is stored in its own session fol | |
| loci amoon627/loci Enables AI agents to search and query a local knowledge base of scattered notes and docs through hybrid vector plus BM25 retrieval with section-level citations, and to store, retract and explore durable memories, note links and agent harnes | |
| db-mcp amor216/db-mcp-server An MCP server that exposes the Deutsche Bahn public transport API to any MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.). Five tools cover station search, departures, journey planning, trip details, and nearby stations | |
| super-productivity-mcp amorem/super-productivity-mcp An MCP server that connects ChatGPT Desktop or Codex to Super Productivity's local REST API, enabling explicit task selection, planning, timer control, and completion via natural language. | |
| BDNS MCP Server amorfeu86/bdns-mcp Enables searching and querying Spanish public subsidies and aids using the BDNS API, with filters for region, beneficiary type, and more. | |
| Tubask amorizz/tubask-mcp Youtube, readable in AI chats. | |
| Google Calendar MCP Server amornpan/py-mcp-gcalendar Model Context Protocol server that provides seamless access to Google Calendar API with asynchronous operation support, enabling efficient calendar management through a standardized interface. | |
| Python LINE MCP Server amornpan/py-mcp-line Enables language models to read and analyze LINE Bot conversations through a standardized MCP interface. Supports text, sticker, and image messages with webhook event handling and message storage in JSON format. | |
| Python MSSQL MCP Server amornpan/py-mcp-mssql Enables Language Models to interact with Microsoft SQL Server databases by inspecting table schemas, executing SQL queries, and reading table data through a standardized Model Context Protocol interface. | |
| MySQL MCP Server amornpan/py-mcp-mysql Enables secure interaction with MySQL databases, allowing AI assistants to list tables, read data, and execute SQL queries through a controlled interface. | |
| py-mcp-qdrant-rag amornpan/py-mcp-qdrant-rag Enables semantic search and retrieval-augmented generation (RAG) using Qdrant vector database. Supports indexing documents from URLs and local directories, with flexible embedding options using Ollama or OpenAI. | |
| TMD Earthquake MCP Server amornpan/tmd-weather-mcp-stdio-2025-10-07 Provides access to earthquake data from the Thai Meteorological Department (TMD) API. Enables querying recent earthquakes, filtering by location and magnitude, and obtaining statistics. | |
| Ariadna amorozov1310/ariadna-mcp Enables fast search and analysis of 1C configuration metadata and BSL code through MCP tools, including objects, attributes, procedures, call graphs, full-text code search, and support for multiple projects and extensions. | |
| log-mcp amos666/log-mcp-python Enables remote log searching, tailing, and file reading across servers via MCP tools, with pluggable execution via SSH, pyinfra, or local commands. | |
| my-github-mcp-server amotarao/amon-github-mcp-server Provides tools for managing GitHub sub-issues and milestones, including adding/removing sub-issues, getting parent issues, and setting milestones. | |
| Web Content MCP Server amotivv/cloudflare-browser-rendering A server that leverages Cloudflare Browser Rendering to extract and process web content for use as context in LLMs, offering tools for fetching pages, searching documentation, extracting structured content, and summarizing content. | |
| cloudflare-browser-rendering-mcp amotivv/cloudflare-browser-rendering-mcp This MCP server provides tools for interacting with Cloudflare Browser Rendering, allowing you to fetch and process web content for use as context in LLMs directly from Cline or Claude Desktop. | |
| Memory Box MCP Server amotivv/memory-box-mcp Cline MCP integration that allows users to save, search, and format memories with semantic understanding, providing tools to store and retrieve information using vector embeddings for meaning-based search. | |
| protonmail-mcp amotivv/protonmail-mcp This MCP server provides email sending functionality using Protonmail's SMTP service. It allows both Claude Desktop and Cline VSCode extension to send emails on your behalf using your Protonmail credentials. | |
| SoulverCore MCP Server amotivv/soulver-mcp-server A comprehensive MCP server that integrates SoulverCore with Claude Desktop, enabling natural language mathematical calculations, unit conversions, date arithmetic, and financial computations. | |
| Canva MCP OAuth amoureuxid/canva-mcp Enables a stdio-capable MCP client to connect through a local OAuth bridge to Canva's official MCP server, forwarding tool and resource requests using read-only scopes and per-user credentials. | |
| mcp-jira-python amovfx/mcp-jira-python MCP server for JIRA integration enabling issue management, search, comments, and linking via natural language. | |
| Ampersand MCP docs server amp-labs/mcp-docs-server Access Ampersand's documentation through MCP; this repo is deprecated, use the hosted server at https://docs.withampersand.com/mcp. | |
| MCP Server Template amp-rh/mcp-router A production-ready FastMCP server template with modular architecture for building MCP servers with organized tools, resources, and prompts, featuring container support and AI agent documentation system. | |
| Airbnb Search & Listings ampcome-mcps/airbnb-mcp Enables users to search Airbnb listings with advanced filtering options and retrieve detailed property information through an MCP server interface. | |
| Aiven MCP Server ampcome-mcps/aiven-mcp Provides access to Aiven's PostgreSQL, Kafka, ClickHouse, Valkey and OpenSearch services, enabling LLMs to build full stack solutions by interacting with the Aiven ecosystem. | |
| Apify Model Context Protocol Server ampcome-mcps/apify-mcp Enables AI assistants to use Apify Actors as tools to perform specific tasks like web scraping, data extraction, and searching across various platforms through the Model Context Protocol. | |
| MCP Server for Asana ampcome-mcps/asana-mcp Enables Claude to interact with Asana workspaces, tasks and projects through the Asana API, allowing users to search, create, update, and manage Asana tasks and projects using natural language. | |
| athena-mcp ampcome-mcps/athena-mcp Enables users to execute SQL queries, manage workgroups, databases, tables, and named queries in AWS Athena through natural language. | |
| Playwright Browserbase MCP Server ampcome-mcps/browserbase-mcp An MCP server that enables LLM applications to control web browsers via Browserbase, supporting features like web navigation, screenshots, cookie management, and persistent contexts. | |
| Chargebee MCP Server ampcome-mcps/chargebee-mcp A server that integrates with AI-powered code editors to provide immediate answers about Chargebee products and API services, offering context-aware code snippets and access to Chargebee's knowledge base. | |
| CircleCI MCP Server ampcome-mcps/circleci-mcp Enables natural language interactions with CircleCI through Model Context Protocol, allowing users to retrieve build logs, find flaky tests, check pipeline statuses, and manage workflows without leaving their IDE. |
28,251–28,300 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.