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 |
|---|---|
| continuity-orchestrator awslew/continuity-orchestrator Enables MCP chat clients to read explicitly shared local source files and search results without spending local model quota, while also providing an experimental quota-relay workflow for extended modes. | |
| Web Search MCP Server awslew/web-search-mcp Enables AI coding assistants to perform multi-engine web searches, site-specific searches, and structured webpage content extraction via MCP stdio, without requiring any API keys. | |
| mcp-swagger awssam/mcp-swagger Exposes Swagger/OpenAPI API documentation to AI models, enabling exploration, search, and interaction with endpoints, schemas, and execution of API calls. | |
| Pingfusi awu870/pingfusi Enables AI coding agents to request real human reviews mid-task, receiving pinned feedback and approval verdicts so they can iterate until approved. | |
| index01-mcp-alexa awwaiid/index01-mcp-alexa An MCP server that enables an Index 01 wearable to control Alexa devices by sending natural-language commands to an Echo, such as setting alarms or timers. | |
| MCP Server for Alloy Modeling Language awwaiid/mcp-server-alloy Enables LLM-powered agents to generate, execute, and analyze Alloy modeling language code for software modeling and formal verification. Provides tools to run Alloy models, access documentation and examples, and generate models from system | |
| gutenberg-mcp awzy11/gutenberg-mcp Enables search and reading of Project Gutenberg books with tools for searching by title/author/subject and fetching word-range slices of book text. | |
| mit-classics-mcp awzy11/mit-classics-mcp An MCP server that gives LLMs direct read access to the MIT Internet Classics Archive, allowing them to list authors, list works, and fetch word-range slices of texts. | |
| ATAS MCP Bridge ax3lsk3r3/atas-mcp Enables AI agents to access real-time market data, order book depth, positions, orders, trades, and order routing from the ATAS platform through the Model Context Protocol. | |
| QuantVibe ax3lsk3r3/quantvibe Read-only FastMCP server providing machine learning stock selection scores, Alpha158 signals, and SHA-256 checksums from Qlib. | |
| Odds API MCP Server axc9000/odds-api-mcp-server An MCP server that connects Claude Desktop to The Odds API, giving Claude real-time access to sports odds, scores, and schedules across 80+ sports and leagues worldwide. | |
| VirtualBox MCP axcel-blade/virtualbox-mcp Enables AI applications and agents to manage Oracle VirtualBox virtual machines and run commands inside Linux and Windows guests through Bash, POSIX sh, PowerShell, and CMD. | |
| Public Gateway MCP axcient/public-gateway-mcp Connects AI assistants to Axcient for real-time data retrieval and actions through natural conversation. | |
| @axd/browser-mcp axd-dev01/axd-browser-mcp A high-performance MCP server for browser automation via Chrome DevTools Protocol, enabling fast, low-cost, and anti-bot web interactions. | |
| MCP Forensic Toolkit axdithyaxo/mcp-forensic-toolkit A secure, AI-ready local server that provides digital forensics tools for analyzing logs, verifying file integrity, and generating audit-grade reports. | |
| wwall axdvdv/wwall-mcp Enables AI agents to propose wallet payments while a local, human-authored policy decides whether each transaction is approved, requires human confirmation, or is refused, and records every decision in a signed, append-only ledger. | |
| Quest Browser MCP Server axe-work/quest-browser-mcp Controls Oculus Browser via WebSocket CDP protocol, enabling full browser automation with Playwright-like API for navigation, interaction, content extraction, and more. | |
| adb-mcp axe01010/adb-mcp Enables AI agents to control Android devices via ADB, providing tools for screen capture, tap/swipe/input, app management, and diagnostics. Works locally over USB or WiFi and integrates with MCP clients like Claude and Cursor. | |
| Stealth Browser MCP Server axe240-commits/stealth-browser-mcp Provides stealth web browsing using dual browser engines (Chromium and Firefox) with automatic bot-detection bypass, enabling AI agents to browse, interact, and extract content from websites without being blocked. | |
| mcp-1c-helper axel-avb/mcp-1c-help Enables AI agents to search and retrieve 1C:Enterprise 8.3 syntax documentation, including quick references, detailed syntax info, and object members, through MCP tools backed by an Elasticsearch index. | |
| 1c-configuration axel-avb/mcp-1c-metadata Enables LLM agents to explore and search a 1C:Enterprise configuration codebase, including metadata objects, module procedures, call graphs, and semantic similarity search. | |
| BSL MCP Analyzer axel-avb/mcp-bsl-analyzer Enables agents to run project-wide 1C/BSL diagnostics and per-method cyclomatic/cognitive complexity analysis, returning a ranked refactor triage of what to fix first alongside 25 navigation, search, format and fix tools. Deployed over Stre | |
| lego-mcp axel-jalonen/lego-mcp An MCP server that enables LLMs to build physically valid Lego models by enforcing catalog-only parts, no overlaps, stud-to-tube connections, and other real-world constraints. | |
| Express REST API and MCP Server Framework axel2998/express-rest-api-and-mcp-server-framework Enables LLMs to discover and invoke CRUD operations and read-only data resources for generated services through the Model Context Protocol, alongside traditional REST endpoints. | |
| freellmpool axelcook/freellmpool Pools enabled free-tier LLM chat routes behind a single OpenAI-compatible endpoint, enabling coding agents and OpenAI-compatible apps to run on free models with automatic failover, latency-aware routing, keyless start when available, and lo | |
| Blender Open MCP axeldiaz678/blender-open-mcp Enables AI agents to control a live Blender session through the Model Context Protocol, including scene and object operations, rendering, PolyHaven asset integration, and prompt-driven workflows. It supports multiple local or OpenAI-compati | |
| Headquarter axeldotdev/headquarter-mcp An AI-first business and project management tool that stores data locally in Markdown and JSON files, exposed via the Model Context Protocol (MCP). Enables project, issue, client, contact, and note management through natural language. | |
| GymCam Analytics axelfreeman/gymcamanalytics Enables AI agents to query gym analytics—class attendance, trainer performance, and revenue insights—from existing CCTV camera feeds without new hardware. | |
| TAPAC MCP axelfreeman/tapac-mcp A native MCP server for real-time B2B contact finding and SMTP email validation, scraping company websites, Discord, and Telegram to deliver live, verified contacts that AI agents like Claude and Cursor can query directly. | |
| Bitbucket MCP axelgomez23487/bitbucket-mcp Enables AI assistants to interact with Bitbucket repositories, repository details, and pull requests through the Bitbucket Cloud and Server APIs. It supports listing and retrieving repositories, fetching and creating pull requests, and navi | |
| chatgpt-web-agent axelhu/chatgpt-web-agent Enables ChatGPT web to use local tools like file reading, command execution, and patch application through an MCP server over OpenAI Secure MCP Tunnel. | |
| Federal Reserve Economic Data MCP Server axelmattsson/fred-mcp-server Enables users to browse, search, and retrieve over 800,000 economic time series, with transformations, date ranges, and filters, via MCP tools. | |
| tradingview-chart-mcp axelmoreno451/tradingview-chart-mcp Enables fetching TradingView chart images for any ticker and interval, with browser pooling for concurrent performance and built-in request statistics. | |
| hopp axelpaul/hopp-cli Enables querying car-sharing vehicles, scooters, taxi quotes and bookings, account, wallet, invoices, parking, and support through recovered customer operations, with optional write tools that preview unless explicitly confirmed. | |
| Hreyfill axelpaul/hreyfill-cli Lets MCP clients calculate taxi fare quotes, review upcoming and past bookings, fetch receipts, driver images and trip routes, check nearby taxis and live trip status, and resolve addresses or directions with a Google Maps key. Read tools a | |
| NotebookLM MCP Server axelshah99685/notebooklm-mcp Enables citation-backed Q&A, source-grounded research, and generation of audio, video, reports, presentations, data tables, study aids, and mind maps from notebook sources. Supports multi-account rotation with auto-reauth and exposes a loca | |
| HubSpot MCP Server axelsingh3150/mcp-hubspot Enables AI assistants to interact with HubSpot CRM data, including creating contacts and companies, retrieving active records and recent conversations, and performing semantic search over previously retrieved HubSpot data through built-in v | |
| Snyk MCP REST axelspringer/snyk-mcp-rest Provides security scanning capabilities through Snyk CLI tools and REST API, enabling AI assistants to test projects for vulnerabilities, retrieve security issues, and manage Snyk projects with comprehensive SAST, container, and infrastruct | |
| Lidarr MCP Server axelterrier/lidarr-mcp Enables interaction with Lidarr music collection management through natural language. Provides tools to list, get, create, update and delete artists, albums and tracks via Lidarr's API. | |
| Plex Assistant MCP axelterrier/plex-assistant-mcp Enables users to manage and control their Plex media library through natural language commands in MCP-compatible AI clients. It supports searching content, managing playlists, tracking library statistics, and monitoring live viewing session | |
| threadflow-mcp axelvernebooks/threadflow-mcp Enables AI agents to validate and register X/Twitter threads, enforce that only drafted threads can be scheduled or posted, and optionally refuse preflight offers scoring below 45/100. | |
| trello-mcp axgrid/trello-mcp A Trello MCP server that enables searching cards by custom field values and managing board data with compact responses. | |
| KushBitx MCP agent axhadzbel-ui/kushbitx-mcp-agent Enables keyless interaction with KushBitx token-risk APIs: free token previews, advisory SpendGuard policy evaluations, and discovery of unsigned x402 payment challenges, without requiring LLM keys, wallets, or payments. | |
| IL2CPP Frida MCP Server axhlzy/il2cpp-frida-mcp Enables AI assistants to analyze and manipulate Unity IL2CPP applications via Frida, supporting disassembly, class/method listing, and heap analysis. | |
| VaultMCP axiler-lab/vaultmcp An encrypted secret vault and MCP gateway that securely stores API keys and injects them into upstream MCP servers, so AI IDEs never see raw credentials. | |
| IBKR MCP Server axiom-iq-labs-mark-franco/ibkr-mcp-server Enables algorithmic trading with Interactive Brokers, including market data, order management, and risk analysis, with special support for 0DTE SPX options. | |
| EVE-NG MCP Server axiom-works-ai/eveng-mcp-server An MCP server that gives Claude and other LLM agents programmatic access to EVE-NG network labs, enabling creation, configuration, and management of virtual network topologies through natural language. | |
| axiomatic-mcp axiomatic-ai/ax-mcp MCP server enabling AI assistants to access the Axiomatic_AI Platform for scientific computing, document processing, and photonic circuit design. | |
| dameng-mcp axiomflow-zh/dameng-mcp MCP server for Dameng database that enables querying and managing database objects via JDBC, including tools for schemas, tables, views, indexes, and more. | |
| Axiom axiomhq/mcp-server-axiom A Model Context Protocol server implementation for Axiom that enables AI agents to query your data using Axiom Processing Language (APL). |
32,101–32,150 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.