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 |
|---|---|
| arguseye darkworldcoder/arguseye Enables coding agents to render React, browser-renderable Next.js, and Vue components from source, then inspect cropped screenshots and structured visual/accessibility evidence without starting the application. | |
| github-universal-mcp darl33/github-universal-mcp Gives any MCP client read-only tools for private GitHub repositories, with OAuth-based authentication and an allowlist of GitHub logins. | |
| cory-mem darland6/cory-mem Provides persistent memory for AI assistants, enabling context retention across sessions through hybrid search and memory management tools. | |
| port-emissions-mcp darlianecunha/port-emissions-mcp Enables Claude to estimate at-berth CO₂ for tanker calls and to query Brazilian port statistics, including cargo volumes, berthings, waiting times and hours at berth across ANTAQ installations from 2010 to 2026. Every answer carries its sou | |
| wsl-bridge-mcp darling209/wsl-bridge-mcp A Model Context Protocol server that lets Windows-side AI agents operate on WSL distributions like a local environment, providing file read/write/edit, command execution, process management, log streaming, and content search via UNC paths a | |
| paperclip-mcp darljed/paperclip-mcp MCP server for the Paperclip AI agent orchestration API, enabling management of AI companies, agents, projects, and tasks through any MCP-compatible client. | |
| Claude MCP for Codex daron4ever/claude-mcp-for-codex Enables Codex to consult Claude Code for a second opinion through a local stdio MCP server, exposing the ask_claude tool for text-only reviews and recommendations using existing Claude Code authentication. Codex can request findings and tra | |
| DARPEngine darpai/darp_engine Stores metadata for MCP servers and provides smart search capabilities, allowing users to find appropriate MCP servers for their queries and route requests to the most suitable server. | |
| apples-tracker darqula/apples-tracker Enables AI assistants to manage job applications and companies in a local SQLite-backed tracker, including searching, creating, updating, and deleting postings and companies, plus reading and updating shared job-search context. | |
| manufacturing-defect-mcp darrellathaya/manufacturing-defect-mcp MCP server for manufacturing defect investigation using knowledge graphs and graph analytics. Enables LLM agents to retrieve context, find similar cases, and generate investigation reports from manufacturing data. | |
| mcp-context-receipts darren-2000/mcp-provenance-capsules Privacy-first, tamper-evident receipts for MCP tool calls. It hashes and signs arguments/results so you can verify what ran, when, without storing raw payloads. | |
| fsastore-mcp darrengruber/fsastore-mcp Enables AI agents to search FSA-eligible products on fsastore.com, add them to cart, and place orders only after user confirmation. | |
| obsidian-mcp darrenlopez/obsidian-mcp Enables MCP-compatible AI hosts to read, search, link, and write notes in a local Obsidian vault with sandboxed file access. | |
| DAZ Command MCP Server darrenoakey/daz-command-mcp An MCP server that provides session-based shell command execution and file management with intelligent LLM-powered summarization. It enables users to manage isolated workflows and track progress through automated event logging and session h | |
| Hostaway MCP Server darrentmorgan/hostaway-mcp Enables AI assistants to interact with Hostaway's property management platform through standardized MCP tools. Provides access to listings, bookings, guest communication, and availability checking for vacation rental management. | |
| DingTalk MCP Server darrenyao/dingtalk-mcp-server Enables Claude to interact with DingTalk workspaces to search for users, retrieve detailed employee information, and send private messages. It bridges the Model Context Protocol with DingTalk's internal enterprise APIs for seamless workspac | |
| Otter MCP darrenzal/otter-mcp Enables AI assistants to search and retrieve meeting transcripts from Otter.ai, supporting full-text search, speaker identification, and transcript retrieval. | |
| Hermes MCP Server darrenzwchan/hermes-mcp Transforms internal Hermes documents (PRDs, RFCs, specs) into agent tools for relevance search, metadata, and full content retrieval, plus a skill to cross-check specs against code. | |
| Gmail MCP Server darrinm/gmail-mcp A comprehensive MCP server providing 24 tools for full Gmail management, including email operations, label organization, and batch filtering. It features multi-account support and secure OAuth authentication for interacting with mailboxes v | |
| Bridge darrobcker/cogobridge Enables people's AI assistants to find each other across communities and match on what each person is looking for, revealing names and contact details only after both sides agree. It supports invite-based joining and self-hosted deployments | |
| Bridge Chats darrobcker/cogobridgechats Enables a user's AI to exchange messages with people they already know and those people's AIs in DMs and group chats, handle routine communication, and flag only items needing attention. It supports OAuth sign-in and private invite-based co | |
| Octopus Energy MCP Server darronz/octopus-mcp-server Enables retrieval of electricity and gas consumption data from Octopus Energy accounts through their API, with support for date range filtering, pagination, and grouping by time periods. | |
| mcp-gateway darrshangovender/mcp-gateway Enables secure exposure of internal tools to LLM clients with API-key authentication, tenant isolation, per-tool guardrails, PII scrubbing, rate limiting, audit logging, and telemetry over stdio and HTTP/SSE. | |
| ServiceNow MCP Demo — Incident Assistant darrylsarkisian-debug/servicenow-mcp-demo An end-to-end Model Context Protocol demo that connects Claude to ServiceNow Incident Management. | |
| ros2-mcp-server darshan-kt/ros2-mcp-server Enables natural language control and monitoring of ROS 2 robots through standardized MCP tools, with a deterministic safety layer and automatic capability discovery. | |
| satellite-conjunction-mcp darshan0548/satellite-conjunction-mcp Tracks real satellites and screens close approaches using live TLE data and SGP4 propagation, exposing tools for fetching positions and conjunction checks. | |
| SonarQube REST API MCP darshan1005/sonarqube-mcp Enables VS Code's AI assistant to query and manage SonarQube projects, quality gates, measures, issues, hotspots, branches, and system status through the SonarQube REST API over stdio. | |
| KeepContext darshanbajgain/keepcontext A self-hosted MCP server that gives every connected AI app (ChatGPT, Claude, Gemini, Cursor, Codex, Copilot) one shared memory of ideas, decisions, todos, notes and standing instructions to read and write. It also lets apps start multi-step | |
| Jira Context MCP Server darshancisco/appd_jira_context_mcp Integrates Jira with Cursor IDE for AI-powered issue management, sprint tracking, library vulnerability analysis, and MySQL database queries through natural language. | |
| MCP Agent & Server Ecosystem darshanhegdep/mcp An autonomous agent ecosystem that leverages Groq for high-performance reasoning and Playwright for web automation via the Model Context Protocol. It features an interactive CLI and a custom server providing a run_task tool for orchestratin | |
| Hedwig darshankrishna-dk/hedwig An MCP wallet server that lets an AI agent hold, send, and spend USDC on Hedera, using the x402 standard for HTTP payments. | |
| MCP Server Suite darshika0712/mcp-server A production-ready suite of Model Context Protocol servers enabling AI agents to access AWS resources, perform SQLite database operations, and scrape web pages through natural language. | |
| qa-touch-mcp darshitpipariya/qa-touch-mcp Enables AI assistants to interact with the QA Touch test management API, including browsing projects, managing test cases, running tests, recording results, and filing defects. | |
| Pitwall F1 darshjoshi/pitwall-f1 Enables Claude to answer Formula 1 questions using real public data: race, sprint and qualifying results back to 1950, lap and sector times, 4 Hz car telemetry, tyre stints, pit stops and undercut strategy, plus locally drawn speed-trace an | |
| cronjob-org-mcp darshk07/cron-job-org-mcp Enables MCP-compatible clients to manage cron-job.org cron jobs and folders via natural language, including creating, inspecting, updating, and deleting jobs, and reading execution history. | |
| Google Flow Browser MCP darthadry/google-flow_mcp Lets an AI agent drive Google Flow (flow.google.com) through a locally logged-in Chrome profile to generate images, videos, characters, and scenes. Uses browser automation via the Chrome DevTools Protocol, so Google credentials are never sh | |
| TTCraft MCP darthgelum/ttcraft-mcp Enables AI assistants to build and script browser-watched game tables, including arranging objects, managing cards and templates, uploading assets, and writing, compiling, and debugging Lua. | |
| fossa-mcp darthzen/fossa-mcp Enables AI assistants to inspect FOSSA organizations and answer software composition analysis questions through a read-only MCP server. | |
| jev-mcp darthzen/jev-mcp Enables typed evaluation requests to TypeSafe Jev (System One) through a single evaluate tool over streamable HTTP. | |
| neuvector-mcp darthzen/neuvector-mcp MCP server for SUSE NeuVector container security, exposing inventory, vulnerability, compliance, event, and policy data as 72 typed tools. Read-only by default, with optional mutating toolsets behind a confirmation handshake. | |
| ollama-code-mcp darthzen/ollama-code-mcp An MCP server that lets Claude Code delegate coding tasks such as code generation, review, refactoring, and test writing to a local Ollama instance running a Qwen3 model. | |
| dartpoint-mcp dartpointai/dartpoint-mcp MCP Server for public disclosure information of Korean companies, powered by the dartpoint.ai API. | |
| Yarah MCP Server darts7u7/yarah-oos-mcp Turns coding agents into full-stack builders by enabling backend features like auth, databases, file storage, serverless functions, and LLMs to be added to apps in seconds. | |
| typer-mcp darussalamnoor/typer-mcp Automatically converts any CLI built with Python's Typer into an MCP server without changing code. Gives AI agents instant access to thousands of CLI tools. | |
| groww-mcp darved2305/groww-mcp An MCP server that enables users to manage equity holdings, execute trades, and track market data on Groww using natural language. It supports mutual fund investments and SIP management, including a mock mode for risk-free testing. | |
| Bitrix24 MCP Bridge darwim/bitrix24-mcp-bridge Локальный MCP-сервер, дающий ИИ-агенту read-only доступ к задачам, проектам и чатам Bitrix24 в объёме прав пользователя — через браузерное расширение, переиспользующее живую сессию. Без прав администратора и без официального REST-вебхука. | |
| Darwin MCP server darwin-studios/darwin-integrations Enables read-only Search and Action mutations through a dynamically advertised seven-tool MCP contract. | |
| WorkMail MCP Server darwinz/workmail-mcp-server Enables Claude Desktop to securely access Amazon WorkMail email and calendar functionality through a local MCP server. Provides tools for reading, searching, and sending emails, as well as managing calendar events with built-in security pro | |
| daryl-memories darylandrian/mnemosyne Enables multiple Hermes agents to persist and retrieve shared knowledge via a local graph-based memory system, supporting hybrid search, entity context exploration, and memory management. | |
| varta-mcp darynafor/mcp-varta Spam classification MCP server for AI agents that classifies messages as SPAM, SUSPICIOUS, or SAFE based on real Telegram moderation data and multi-layer detection. |
42,401–42,450 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.