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 |
|---|---|
| scibot-mcp cyberash-dev/scibot-mcp Enables MCP clients to interact with sci-bot.ru by submitting scientific questions to a queue, monitoring their generation, retrieving completed answers with bibliographies, and managing user account data. | |
| OpenSearch MCP Server cyberbalsa/mcp-opensearch-js A Model Context Protocol server that enables querying and analyzing Wazuh security logs stored in OpenSearch, with features for searching alerts, getting detailed information, generating statistics, and visualizing trends. | |
| GBrainMCP cyberbird2048/gbrainmcp-clean A privacy-cleaned MCP server with hybrid retrieval, multimodal support, and code intelligence, enabling natural language interaction with knowledge bases and tools. | |
| pinescript-mcp-server cyberbob07/pinescript-mcp-server Enables validation, fixing, and generation of PineScript code for TradingView, providing tools for syntax checking, error correction, and template generation. | |
| StockScreen MCP Server cyberbobjr/mcp-stockscreen A Model Context Protocol (MCP) server providing comprehensive stock screening capabilities through Yahoo Finance. Enables LLMs to screen stocks based on technical, fundamental, and options criteria, with support for watchlist management and | |
| Atomic Red Team MCP cyberbuff/atomic-red-team-mcp Provides access to Atomic Red Team tests, enabling search, validation, and execution of atomic tests via natural language. | |
| Scrapling Fetch MCP cyberchitta/scrapling-fetch-mcp An MCP server that helps AI assistants access text content from websites that implement bot detection, bridging the gap between what you can see in your browser and what the AI can access. | |
| MCP Coordinator cyberclash/mcp_coordinator Acts as a proxy for multiple MCP servers, reducing context window usage from 15,000+ tokens to ~500 tokens by dynamically loading servers on-demand and exposing only 3 tools instead of all tool definitions. | |
| THU Agent by CyberCraze cybercrazetech/thu-deepseek-glm-api-mcp-server An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like Deep | |
| AlienGate AI MCP cybercrewinc/aliengate-ai-mcp Enables AI agents to plan and run authorized offensive security assessments across 150+ integrated tools, with full activity logging of every scan. | |
| CogniLayer cyberdaemonai/cognilayer Provides persistent cross-session AI memory, code graph analysis, and subagent context compression so coding agents can resume work instantly and avoid re-reading the codebase. | |
| opsecforge-mcp cyberdroid2077/opsecforge-tools Local stdio MCP server (in packages/opsecforge-mcp, built on @modelcontextprotocol/sdk) that keeps secrets out of coding-agent context: redact_file returns only redacted file content, scan_secrets checks staged changes before commit, plus o | |
| CyberEdu MCP Server cyberedu-cyber-range/cyberedu-mcp Official MCP server for the CyberEdu CTF platform that automatically discovers and exposes all CyberEduClient methods as tools, enabling seamless interaction with the platform through MCP-compatible clients. | |
| x-search cyberelar/magpie-x-search Enables any calling model to search public X content through Grok's native search using an existing local OAuth login, returning summaries, structured posts, source URLs, and search counts while sharing cached and concurrent searches across | |
| Xiaobao MCP cyberelar/xiaobao-mcp Enables MCP clients to query school assignments, exams, schedules, grades, and statistics, along with Microsoft Teams education assignments and Outlook calendar events, and to perform limited write actions such as uploading or submitting as | |
| mcp-hayabusa cybergirl0810/mcp-hayabusa Connects Claude to Hayabusa for Windows event log forensics and threat hunting, enabling natural language queries and analysis of EVTX files. | |
| gramps-remote-mcp cybergitjul/gramps-remote-mcp Enables MCP clients to read and edit a Gramps family tree hosted on Gramps Web, with guarded write operations that tag new records as unconfirmed for review. | |
| booklore-mcp cyberglitchlabs/booklore-mcp Enables AI assistants to interact with BookLore self-hosted libraries, allowing natural language queries to search books, manage reading status, ratings, series, authors, and highlights. | |
| Filesystem MCP Server with .mcpignore cyberhaveninc/filesystem-mcpignore Enables secure filesystem access with privacy controls using .mcpignore files to block MCP clients from reading or writing sensitive files and directories while allowing directory browsing and search. | |
| godot-mcp cyberice2077/godot-mcp Lets AI agents launch a Godot 4 project, then observe and interact with the running game — capturing screenshots, inspecting the live scene tree, pressing Input Map actions, and reading stdout/stderr and script errors. | |
| Pixelorama MCP cyberice2077/pixelorama-mcp Enables AI agents to draw and edit pixel art inside a live Pixelorama editor by sending character-grid and palette commands, reading pixels back, managing layers and frames, and exporting PNGs or sprite sheets. Every operation acts on the a | |
| Basic MCP Server cyberimaginationsi-gif/mcp-takeoff A minimal template MCP server demonstrating basic tools, resources, and prompts functionality. Includes example implementations like a hello tool, history resource, and greet prompt for learning MCP development. | |
| jj-mcp-server cyberistic/jj-mcp-server Model Context Protocol server for Jujutsu (jj) version control, enabling natural-language repository operations like status, log, diff, and commits, with optional jjCoW workspace support. | |
| ReVa cyberkaida/reverse-engineering-assistant A Ghidra MCP server that enables AI language models to interact with Ghidra for reverse engineering tasks, providing small, context-efficient tools to reduce hallucination and handle large binaries. | |
| mcp-sofascore cyberkillua/mcp-sofascore Provides live football match data from Sofascore, including formations, injuries, betting odds, and league positions, enabling natural language queries about matches. | |
| Knight FortiGate Multi-Device MCP cyberknightlabs/knight-fortigate-multi-device Enables managing FortiGate firewalls from an MCP-compatible AI client, with local multi-device enrollment, OS credential storage, connectivity checks, and AI client integration. | |
| vmware-knight cyberknightlabs/vmware-knight-mcp Enables AI-assisted management of vCenter Server and standalone ESXi hosts, including lifecycle, deployment, guest operations, cluster management, datastore browsing, alarms, and investigations through natural language. | |
| NinjaOne MCP cyberkoder/ninjaone-mcp A local MCP server that enables searching, reading, creating, updating, and commenting on NinjaOne tickets through natural language. | |
| Agile Planner MCP Server cyberlife-coder/agile-planner-mcp-server Automatically generates structured agile backlogs including epics, features, and user stories from natural language descriptions within AI-powered IDEs. It streamlines project management by creating AI-optimized markdown files and directory | |
| Cyber Master MCP Server cybermaster000/cyber-master-mcp AI-powered cybersecurity automation platform with 155+ security tools for network, web, cloud, and binary analysis, controllable via natural language through MCP-compatible AI assistants. | |
| Context Engine MCP cybernuki/context-engine-mcp Enables MCP clients to index code repositories and run AST-aware semantic and hybrid keyword search across files, commits and branches, returning relevant code snippets with expanded file context. It handles incremental re-indexing with loc | |
| RootApp Documentation MCP Server cyberofficial/mcp-server-for-rootapp-dev-docs Serves RootApp documentation files with search and retrieval capabilities, enabling users to access specific docs, browse directory structure, and search across file names and content. | |
| CO2 Sensor MCP Server cyberomusubi/mcp-server-for-sensor-device A Node.js application that provides a JSON-RPC interface to interact with CO2 sensor data, working in both simulation mode and with real Raspberry Pi Pico hardware connections. | |
| whatsapp_MCP cyberpixelmarketing/whatsapp_mcp Enables linking a WhatsApp number via QR code and then sending, reading, listing chats, and checking status through MCP tools, with per-account API key authentication. | |
| PyJHora 6-MCP Vedic Astrology Server Suite cyberpunk-71/jhora-mcps Provides 32 JSON-RPC 2.0 stdio tools exposing PyJHora's Vedic astrology calculations, including panchanga, ephemeris, divisional charts, dasha timings, yogas, doshas, transits, and horoscope matching. | |
| adb-ai cyberpunk2183/adb-ai Enables AI agents to control Android TVs, TV boxes, phones, and tablets over ADB through MCP tools for scanning and connecting devices, pressing keys, launching apps, opening URLs, searching YouTube, setting alarms and timers, managing volu | |
| PGAutoPilot cyberreinxy/pgautopilot Enables AI assistants to interact with PostgreSQL databases through natural language, with schema-aware query generation and enterprise safety controls. | |
| MCP Exploit-DB Server cyberroute/mcp_exploitdb Provides access to the Exploit-DB database through the searchsploit tool, enabling AI assistants to search for exploits by keywords or CVE identifiers, retrieve exploit content, and manage the local exploit database. | |
| tokenlife-mcp cybersealnull/tokenlife-mcp Enables AI to autonomously play the TokenLife text-based life simulation game, from birth to death, experiencing events like censorship and era changes, and sending letters to the user. Users just ask the AI to start and it plays itself. | |
| OpenVAS-MCP cybersecauto-labs/openvas-mcp Self-hosted MCP server that gives AI agents structured access to OpenVAS vulnerability scanning without sending data externally. | |
| pycodemath cybersora9/pycodemath Provides a token-efficient exact math engine for AI agents, enabling computation of derivatives, integrals, equations, and optimized Python/NumPy code via a single MCP tool. | |
| mcp-filesystem-extended cybert33n/mcp-filesystem-extended Enables bounded local filesystem inspection, comparison, and mutation with search and resume capabilities. | |
| MCP Server cybertcode/mcp-server Provides SMTP integration for sending HTML emails and specialized prompts for intent detection and client information extraction. It enables LLMs to automate personalized email workflows and structure user communication data. | |
| computer-use cybertonton/opencode-computer-use Enables a constrained subagent to perform foreground GUI actions on Hyprland—observing, focusing windows, clicking, typing, scrolling, dragging, and managing the clipboard—under per-action approval with lease, audit log, and kill-switch gat | |
| tradingview-mcp cybertraderx/tradingview-mcp Enables AI assistants to connect to a locally running TradingView Desktop app via Chrome DevTools Protocol, allowing chart analysis, Pine Script editing and compilation, drawing, alerts, and workflow automation. | |
| reflens cybertronayush/reflens An MCP server that indexes reference repositories and provides tools for AI coding agents to retrieve lossless code context, enabling reasoning over codebases larger than the agent's context window. | |
| detection-debt cyberttopic/detection-debt Enables security teams to determine which ATT&CK techniques lose detection coverage when telemetry sources are removed, by computing set differences over a Sanity content graph and consulting a knowledge base via two Context MCP endpoints. | |
| cyber-figma cyberuni/cyber-figma Local MCP server exposing Figma REST API tools to AI agents, enabling file reads, comments, variables, and other resource operations. Works with personal access tokens and integrates with Claude, Cursor, Codex, and more. | |
| cyber-slack cyberuni/cyber-slack MCP server for Slack that enables AI agents to interact with Slack workspaces, including listing channels, reading and posting messages, searching, managing users, reactions, and user groups. | |
| BotIndex MCP Server cyberweasel777/botindex-mcp Provides predictive crypto market intelligence synthesized from whale positions, developer activity, and behavioral demand signals. Enables convergence scoring, whale divergence detection, and risk radar through MCP tools. |
41,351–41,400 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.