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 |
|---|---|
| Obsidian MCP Server bazylhorsey/obsidian-mcp-server Enables comprehensive access to Obsidian vaults through MCP, supporting multi-vault management, knowledge graph analysis, canvas manipulation, dataview queries, template rendering, and periodic notes creation. Provides both local filesystem | |
| bitbank-api MCP Server bb-sdk/bb-api-mcp Exposes the bitbank-api TypeScript SDK source code and documentation to AI assistants via the Model Context Protocol. It enables assistants to search, list, and read SDK files to better understand and integrate with the bitbank API. | |
| The Living Handbook bb-soil/the-living-handbook Enables agents to read the published article and individual sections, with optional Russian or English language selection and revision pinning. | |
| Korea Trip Concierge bb4rjfl/korea-trip-concierge An MCP server that helps foreign tourists in Korea find places, shops, transportation, and payment solutions in English. | |
| Saju Concierge bb4rjfl/saju-concierge MCP server that calculates saju (four pillars) from birth date/time and provides entertaining interpretations of daily fortune, yearly luck, compatibility, name analysis, and tarot using MIT-licensed manseryeok-js. | |
| WeatherSafetyOS MCP bb4rjfl/weathersafetyos-mcp Provides personalized weather safety alerts and actions based on location, occupation, and age using real-time Korea Meteorological Administration data. | |
| Prepcast MCP bbadhub/prepcast-mcp A comprehensive framework for building and deploying commercial MCP servers with integrated billing, usage metering, and Stripe payment processing. It enables developers to monetize AI tools through a complete ecosystem including API key ma | |
| MCPO - MCP over HTTP Proxy bbajor/mcpo Exposes Cursor IDE's MCP tools (codebase search, file operations) as an HTTP API for integration with Open WebUI, n8n, and other automation tools. | |
| Figma MCP Server bbalakriz/figma-mcp-server Enables integration with Figma through the Model Context Protocol, allowing users to interact with Figma designs and files using their Personal Access Token. Provides containerized deployment options and Server-Sent Events endpoint for real | |
| Red Hat API MCP Server bbalakriz/rh-kcs-mcp Integrates with Red Hat APIs to enable searching Knowledge Centered Support (KCS) solutions, retrieving solution details, searching support cases, and obtaining case details through LLM applications. | |
| ha-exception-debug bbangert/ha-exception-debug A live post-mortem debugger MCP server for Home Assistant that lets AI agents list captured exceptions, walk traceback frames, read local variables, and optionally evaluate Python in the context of a captured frame for true post-mortem debu | |
| MCP Installer bbangjooo/mcp-installer Enables finding, configuring, and installing Model Context Protocol (MCP) servers from the Smithery registry directly into Cursor or Claude Desktop applications. | |
| 3105-mcp bbaobaob/3105-extract Lets agents inspect, unlock, extract, verify, and create encrypted .3105 patch packages over stdio, including password-based unlocking and workspace packing without jailbreak or network access. Runs locally on Termux, Linux, and macOS via N | |
| AwardWallet MCP bbarabe/awardwallet-mcp Enables users to query loyalty balances, expiring points and certificates, account history, trips, and AwardWallet API operations through MCP clients like Claude and ChatGPT. It runs locally, keeps the AwardWallet API key on the user's comp | |
| cursor-mcp-server bbarney7/cursor-mcp-server An MCP server wrapping the Cursor CLI agent, enabling Claude Code and other MCP clients to delegate tasks to Cursor's AI agent for file writing, bash commands, and codebase queries. | |
| mechabrain bbarrosdavi/mechabrain MCP server that provides agentic memory management for markdown vaults, enabling hybrid search, governed writing, and maintenance of episodic, semantic, procedural, and working memories for LLM agents. | |
| MCP Log Analyzer bbashh/log_file_mcp Analyzes log files using AI-powered tools to detect errors, patterns, and anomalies through natural language queries in Cursor IDE. | |
| chrome-bridge bbauersjt/sjt-chrome-bridge Provides a direct bridge between Claude and an authenticated Chrome session, enabling fetch requests with session cookies and JavaScript execution within live web pages. | |
| x-mcp bbbfishhh/x-mcp Provides MCP tools to fetch, filter, curate, and summarize high-quality content from X (Twitter), reducing noise and focusing on high-signal posts, threads, and accounts. | |
| apple-log-mcp bbc6bae9/apple-log-mcp Local MCP server for Apple platform console, unified, and diagnostic logs. Enables listing devices and capturing live logs from simulators and real devices. | |
| Remote MCP Server (Authless) bbchina2023-creator/bbc-quote-mcp-server Deploys a remote MCP server on Cloudflare Workers without authentication, enabling tool use via remote MCP clients like Cloudflare AI Playground or Claude Desktop through a proxy. | |
| Music MCP bbdaniels/music-mcp Enables AI assistants to control Apple Music on macOS through AppleScript, providing tools for playback management, library searching, and playlist organization. It supports detailed track metadata retrieval and enhanced queue management fo | |
| obsidian-mcp bbdaniels/obsidian-mcp Enables Claude Code read/write access to an Obsidian vault, including creating, editing, searching, and browsing notes. | |
| Skills Manager MCP Server bbeierle12/skill-mcp-claude A visual web interface and MCP server for managing Claude MCP Skills, enabling users to create, edit, browse, and load skill sets through a browser UI or directly from Claude Desktop. | |
| LacyLights MCP Server bbernstein/lacylights-mcp Provides AI-powered theatrical lighting design capabilities for the LacyLights system, allowing users to generate lighting scenes, analyze scripts, manage cues, and optimize lighting effects based on artistic intent. | |
| mcp-vector-memory bberthod/mcp-vector-memory Gives multiple AI coding agents a shared, persistent memory by indexing your code and documentation into a vector database with AST-aware chunking and hybrid semantic/keyword search. Agents can search across projects and store, update, or f | |
| X64Dbg MCP Server bbgouzi123/x64dbg-mcp Enables AI-assisted reverse engineering and debugging through x64dbg integration. Provides 40+ tools for breakpoint management, memory operations, register manipulation, code analysis, process control, and advanced debugging features. | |
| Flint MCP Server bbigger004/my-flint-chart-api-mcp-skill Enables agents to compile a semantic chart description (data, semantic types, chart intent) into native specs for five charting libraries and headlessly render three of them to SVG or PNG, delivered inline or as signed, expiring artifact UR | |
| mfds-mcp bbiyakfather/mfds-mcp Enables searching and retrieving current Korean Food and Drug Administration (MFDS) legal notices and guidelines with version grouping, currency status, and source trustworthiness. | |
| CST MCP bbl21/cst-runtime-cli An MCP server that integrates CST Studio Suite with the Model Context Protocol to enable automated electromagnetic simulation workflows. It provides specialized tools for material definition management and direct interaction with the CST St | |
| Monad MCP bble/monad-mcp An MCP server that allows querying MON token balances and NFT counts on the Monad testnet, enabling Claude Desktop to interact with the Monad blockchain. | |
| brs-docs-mcp bblietz/brs-docs-mcp MCP server for Roku BrightScript documentation and device control, enabling doc search, device introspection, keypress/keysequence input, app launch, and sideloading. | |
| brs-mcp bblietz/brs-mcp An MCP server that scaffolds runnable Roku channels from a validated AppSpec, zips them, and optionally sideloads to a Roku device. | |
| pdns-mcp-server bblrlo/pdns-mcp-server MCP server for managing PowerDNS DNS records through the PowerDNS-Admin API. Supports listing zones, getting zone details, and creating, updating, deleting DNS records. | |
| CineLock bbo777/cinelock This MCP server enables clients and agents to validate, compile, inspect, audit, and export hash-locked video production context packs and evidence-chain job records, with optional ComfyUI or HTTP API generation when explicitly invoked. | |
| BookMind bbookmind/mcp An intelligent bookkeeping MCP server for QuickBooks Online that enables natural language control over categorization, reconciliation, monthly close, and anomaly detection. | |
| Semantic Search MCP bborbe/semantic-search Enables semantic search over markdown files to find related notes by meaning rather than keywords, and automatically detect duplicate content before creating new notes. | |
| MCP PJe Pernambuco bbpropulse/mcp-pje-tjpe-dist Enables local MCP clients to securely use the court's digital systems—public process lookup, fee calculation, CNJ metadata queries, and the CAP1G chat—without exposing credentials to the MCP protocol. | |
| Idra Photo bbrainfuckk/idra-photo Enables Codex to generate finite image batches using its built-in image tool, managing jobs, saving outputs, and supporting pause/resume. | |
| stac-eo-mcp bbrauzzi/stac-eo-mcp It enables AI agents to search public STAC catalogs and compute Sentinel-2 NDVI, NDWI, and NBR statistics over a bounding box without downloading whole images, with cloud masking and optional map or GeoTIFF outputs. | |
| GitHub MCP Server bbsbrezz/gitlab-mcp Enables comprehensive interaction with the GitHub API for managing repositories, issues, pull requests, commits, and GitHub Actions workflows through natural language. | |
| vision-mcp bbsong123/vision-mcp Enables text-only models to perceive images via a vision-language model, supporting image analysis with simple descriptions or structured JSON for technical diagrams. | |
| Turbo C MCP Server bbsrguy/turboc-mcp-server Gives AI assistants a genuine Borland Turbo C 3.0 toolchain via MCP, enabling compile and run of real 16-bit DOS C programs with diagnostics and classic examples. | |
| apple-docs-mcp-server bbssppllvv/apple-docs-mcp-server Search and retrieve information from Apple's complete developer documentation, including API references, code examples, and Human Interface Guidelines, across all Apple platforms and versions. | |
| Look At Pic MCP bbsteel/look-at-pic-mcp Enables image analysis using GLM-4V multimodal model, supporting local files and base64 images with optional custom prompts. | |
| Docset Agent MCP bbsvip/docset-mcp Enables AI coding agents to discover, download, index, and search offline Dash/Zeal-format API documentation through MCP tools, including symbol search, page reading, catalog management, and optional full-text search. | |
| mcp-server-TLD bbsyaya/mcp-server-tld An MCP server for AI agents to interact with the JustLend DAO lending protocol on TRON, plus general TRON chain utilities like balances, transfers, and staking. | |
| remote-ssh-mcp bbt567/remote-ssh-mcp Connects an MCP client to a remote Linux/Unix host over SSH, enabling remote shell commands, file access, port forwarding, and VS Code Remote-SSH URI generation. | |
| EcoOracle bbuchsbaum/eco-oracle EcoOracle is an MCP server that retrieves canonical usage recipes and API cards from a registry of R/Python packages, enabling users to build scripts using ecosystem packages. | |
| Personal MCP Server bburgess42/personal-mcp-server Enables AI agents to answer questions about a personal site straight from its published JSON bundle — profile, posts, case studies, pages, projects, stats and small datasets — through seven read-only tools for listing, full-text search, fet |
33,251–33,300 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.