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 |
|---|---|
| apollo-mcp dyngai/apollo-mcp Provides 45 MCP tools to search, enrich, and manage Apollo.io B2B data (people, companies, CRM, deals, tasks, sequences, etc.) via stdio or HTTP transport. | |
| foolfuuka-mcp-server dynmie/foolfuuka-mcp-server MCP server for querying 4chan archives (Desuarchive, 4plebs, b4k, archived.moe) via the FoolFuuka API, enabling AI agents to search and retrieve historical archived posts. | |
| Zentao MCP Server dyno-nexsoft/zentao_mcp An MCP server that integrates with Zentao API to provide tools for accessing tasks, bugs, and attachments from project management. | |
| ai.dynsoft/sac dynsoft-lab/software-as-content-sdk Enables AI agents to respond to users with live, persistent, interactive web apps served at a single URL that evolve in place as the conversation continues. It exposes UI generation and evolution tools over MCP so agent responses can includ | |
| Figma Dash MCP Server dynstat/figma-dash-mcp Connects IDE to Figma Desktop App, enabling AI assistants to generate and manipulate layouts, shapes, and designs directly inside the Figma canvas. | |
| MCP Server Demo dynstat/mcp-demo A simple demonstration project for the Model Control Protocol (MCP) server that provides tools for AI assistants to fetch news articles, perform calculations, retrieve weather data, and generate personalized greetings. | |
| @dinko/adonis-mcp dyoma3/adonis-oauth-mcp Enables AdonisJS applications to expose MCP endpoints secured by OAuth 2.1, handling requests, tool contracts, and token-protected resource registration. | |
| swagger-mcp-tools dyq086/swagger-mcp-tools A Swagger/OpenAPI query tool for MCP clients like Cursor, enabling AI assistants to browse, search, and retrieve detailed API type information. | |
| Ableton MCP dysron/ableton-mcp Enables AI assistants to control Ableton Live through natural language by querying tracks, analyzing sessions, and exporting stems via AbletonOSC integration. | |
| MCP Password Generator dytavan/mcp-password Generates secure random passwords and memorable passphrases with customizable options including length, character types, emojis, and automatic strength evaluation using zxcvbn scoring. | |
| Tailscale MCP Server dytavan/tailscale_mcp Enables interaction with the Tailscale API to manage devices, ACLs, keys, and DNS configurations directly from MCP clients like Claude Desktop or Raycast. | |
| dy-mcp-demo (dy-mcp) dyuhaus/dy-mcp-demo A public demo of a personal-context MCP server that exposes six typed contexts (project, idea, preference, writing_style, skill, general) and twelve tools for managing personal data, with an hourly data reset. | |
| MCP Starter dyxbenjamin/filesearch-mcp An agent-ready TypeScript template for building Model Context Protocol (MCP) servers with standardized discovery flows and permission-aware tools. It provides pre-configured core and operable profiles to help developers quickly implement, t | |
| mcp-proxy dyy-fq/mcp-proxy Bridges LLM clients with existing RESTful microservices by converting MCP tool calls into REST requests, enabling any REST API to be used as an MCP tool without modifying the microservices. | |
| Knowledge Base MCP dyyz1993/knowledge-base-mcp A cross-project knowledge base MCP server supporting three-layer search (text matching, TF-IDF, and semantic vectors) with a Web UI for management. | |
| Sovereign Code Runtime dz20000/sovereign-code-runtime-public Enables ChatGPT Web conversations to operate a Windows computer through MCP with local tools, permissions, task state, and audit evidence. | |
| MCP Toolkit Pro dzachref/mcp-toolkit-pro Enables AI agents to interact with GitHub (search repos, read files, issues, PRs), analyze code for quality and issues, and manage tasks with priority sorting. | |
| Courses MCP Server dzendys/courses-mcp Enables LLMs to interact with FIT CTU course materials, including listing subjects, navigating subpages, reading content as Markdown, and performing keyword searches. | |
| fitwiki-mcp dzendys/fitwiki-mcp Scrapes course materials, exam variants, and notes from Fit-Wiki, converting them to Markdown and PDF for integration with LLM clients. | |
| KNMI MCP Server dzgnnl/knmi-mcp Enables AI assistants and applications to access Dutch weather information, including current conditions, forecasts, alerts, historical data, and automatic resolution of Dutch location names to grid identifiers. | |
| gsc-mcp-connector dzhitnitsky/gsc-mcp-connector Self-hosted MCP server for Google Search Console. Enables natural language queries to list sites, analyze search analytics, inspect URLs, and check sitemaps through AI assistants. | |
| Sugar dzhou56350/sugar Gives AI coding agents direct, local-first read/write access to persistent memory — project decisions, preferences, error patterns, research, and cross-project guidelines — retrieved by semantic search backed by SQLite with no API keys or n | |
| mcp-app-boilerplate dzhunka/mcp-app-boilerplate Provides a deployable remote MCP server that serves interactive HTML widgets alongside tool results, enabling agent plugins for Cursor, Codex, and Claude Code. | |
| LinkedIn Automation MCP Server dzigi00/linkedin-claude-automation Enables automated LinkedIn growth by posting, commenting, and managing connections through Claude Code, with daily scheduled tasks for inbox replies and connection requests. | |
| Polymarket MCP Bot Analyst dzimash/polymarket-mcp-bot-analyst MCP server for analyzing successful trading bots on Polymarket, enabling discovery of top traders, AI-powered strategy classification, and bot detection. | |
| candlestick-chart-mcp dzintars2/candlestick-chart-mcp Renders OHLCV data as candlestick chart PNGs and returns inline images. It is a pure renderer with no network access, allowing models to view charts generated from provided data. | |
| roo-mcp dzisner/roo-mcp Enables AI clients to create, manage, and configure Roo smart shortlinks and their add-ons, such as QR codes, scheduled redirects, and webhooks, through MCP tools. | |
| atlassian-proxy dzmhub/atlassian-proxy Enables Claude Code to use a filtered subset of Atlassian Rovo MCP tools for Jira and Confluence, automatically injecting required parameters and stripping noisy fields to reduce token usage. | |
| damonzucconi-mcp dzucconi/damonzucconi-mcp Enables managing the site's API via natural language, with tools for artworks, exhibitions, tags, nested entities, and ordering, while protecting the endpoint with a bearer token and caching admin JWT. It supports Cursor and ChatGPT desktop | |
| human-loop-mcp dzulfiikar/human-loop-mcp Enables AI agents to ask human operators questions through polished browser dialogs, supporting text/choice/confirmation inputs and file attachments. | |
| Shopify MCP dzunglaviet/shopify-mcp Enables natural language management of Shopify stores, including orders, customers, products, and inventory, with support for multiple stores and both static and OAuth authentication. | |
| Boards with MCP dzunnnnn-crypto/excalidraw-boards-portal Enables AI agents to discover and work with a user's permitted Excalidraw boards through a single MCP endpoint, reading and adding elements, images, and snapshots while respecting owner, view, edit, and guest-link access controls. | |
| dzzk Job Search OS Browser Bridge dzzk-r/execution-delivery-harness Lets an MCP client list and read pages a user has explicitly shared from a running Firefox session, including visible job listings and recruiter conversations, and search for text within those pages. Access is read-only, granted per page fo | |
| ToolSmith Agent MCP Server e-akgul/toolsmith-agent A multi-tool task agent MCP server with file search, SQLite query, calculator, and report writing tools. Enables Claude Code, Claude Desktop, or Cursor to control the same tools used by the agent, with guardrails for safety. | |
| claude-design-mcp e-brokenc0de/claude-design-mcp An MCP server that drives Anthropic's Claude Design from agentic coding CLIs, providing tools to create, generate, iterate, and export design systems without a browser. | |
| Network MCP Lab e-conners-lab/first_mcp_server MCP server for executing show commands and managing Cisco IOS-XE network devices via async SSH using Scrapli. | |
| network-mcp e-conners-lab/mcp-demo-lab Provides AI assistants with direct access to multi-vendor network devices for tasks like configuration management, health checks, and topology discovery through 35 specialized tools. It enables natural language control over platforms includ | |
| packet-coders-mcp e-conners-lab/packet-coders-demo A local MCP server for interacting with a network lab, supporting read-only and configuration tools for devices like Arista EOS switches. | |
| typesafe-as-a-judge e-fl/typesafe-as-a-judge Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations. | |
| goofish-z-mcp e-r-butch/goofish-z Provides MCP interface to Xianyu (Goofish) for searching items, managing price watches, and monitoring prices via CLI, HTTP API, or MCP. | |
| injection-firewall e-v-a-l-i/prompt-injection-firewall Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the pres | |
| turbocontext e-x-h-i-b-i-t/turbocontext Enables AI coding agents to intelligently index and search codebases with sub-20ms retrieval, 8x memory compression, and cross-encoder reranking via MCP stdio. | |
| E0N-MCP-FOR-ETH e00n777/mcp_hijack just a simple test for education | |
| Kommo CRM MCP Server e0duar/kommo-mcp Enables AI agents to manage Kommo CRM (formerly AmoCRM) entities including leads, contacts, companies, tasks, notes, pipelines, and products through natural language commands via the Model Context Protocol. | |
| Drupal Bridge MCP e0ipso/drupal-bridge-mcp Enables AI assistants to interact with Drupal sites through MCP tools, with automatic discovery, OAuth-based authentication, and scope validation. | |
| AgenSysAdmin e13ctr0n/aisysadmin MCP server for remote Linux server administration via SSH, integrating with Claude Code to manage Ubuntu/Debian servers. | |
| MCP Message Bridge e1ainaqwq/mcp-message-bridge Enables authenticated, explicit-text message exchange between independent clients through a durable queue with idempotent sends, replay-safe inbox reads, bounded conversations, pause/reset controls, and client-driven polling. | |
| Project Customization MCP e1imba/project-customization-mcp An open-source MCP server that automates project customization by analyzing your codebase and generating AI-ready configuration files based on industry best practices. | |
| graphrag-local e2its/myrmion-graphrag Connects Claude Code to a local GraphRAG knowledge base (LightRAG + Ollama) for private, offline document retrieval. Provides tools to search, add documents, and check the RAG status, enabling Claude to reason over user's own notes, code, a | |
| factory-floor-mcp e37dey/factory-floor-mcp Provides read-only access to manufacturing plant data from Excel or SAP S/4HANA, enabling natural-language queries for OEE, downtime Pareto, late work orders, scrap, and inventory alerts. It enforces data classification, masking, row limits |
46,651–46,700 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.