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 |
|---|---|
| mcp-auth-kit bradburch/mcp-auth-kit A production-minded MCP server kit that provides OAuth 2.1/PKCE authentication, rate limiting, scope-gated tools, and two-phase confirmation for building secure MCP servers with custom tools, identity, and storage. | |
| Copilot Studio Agent Direct Line MCP Server bradcstevens/copilot-studio-agent-direct-line-mcp Enables interaction with Microsoft Copilot Studio Agents directly from VS Code through the Direct Line 3.0 API. Supports starting conversations, sending messages, retrieving history, and managing conversation lifecycle with your custom agen | |
| Google Ads MCP Server bradenpan/mcp-google-ads Enables comprehensive management of Google Ads accounts by allowing users to create campaigns, manage keywords, and generate performance reports through a context-aware interface. It features a three-layer architecture that integrates produ | |
| Cline Personas MCP Server bradfair/mcp-cline-personas An MCP server for managing and activating persona templates and components by writing to .clinerules files, supporting version tracking and file-based storage. | |
| mouser-mcp bradford-tech/mouser-mcp Enables searching Mouser Electronics parts, reviewing BOMs, managing carts, and checking order history through natural language. Order placement is opt-in and requires typing APPROVE into a server-shown confirmation prompt before any order | |
| @bradford-tech/npm-package-readme-mcp-server bradford-tech/npm-package-readme-mcp-server Fetches npm package READMEs, metadata, and search results for MCP-compatible AI clients. | |
| CSG Portal MCP Server bradgriffith/csg-portal-mcp Enables access to Columbus School for Girls Veracross portal features including directory search for students/parents/staff, calendar events, and Lower School lunch volunteer scheduling through secure browser authentication. | |
| mister-clean bradheitmann/mister-clean Provides read-only access to the skill's canonical references, templates, examples, and closeout prompts, enabling agents to perform repository completion and closeout tasks. | |
| KingWorkbook MCP bradkingme/kingworkbook-mcp Enables read-only profiling, comparison, total reconciliation, and formula integrity review of local Excel .xlsx and CSV files within a configured workspace, without modifying files or executing formulas. | |
| cryptofort bradley-t-t/cryptofort Encrypted-at-rest credential vault with MCP server for agent credential lookup and management. | |
| LeetCode MCP Server bradley21048/leetcode-mcp-server Enables automated access to LeetCode problems, official editorials, user-submitted solutions, contests, and user data—including notes, problem lists, and submission history—with optional authentication for private features, across both leet | |
| FCPXML MCP bradley24034/fcp-mcp-server Lets Claude read, edit, and generate real Final Cut Pro timelines from exported XML — trims, splits, silence removal, transcript- and beat-based markers, rough cuts, keyframes, speed ramps, and cross-NLE export. Can also push a finished tim | |
| things-turbo bradleyallandavis/things-turbo Composite MCP server for Things 3 on macOS that bundles multiple read calls into single requests, enables batch writes, and provides a self-healing read path to handle TCC protection issues. | |
| AutoDocs MCP Server bradleyfay/autodoc-mcp Automatically provides AI assistants with contextual, version-specific documentation for Python project dependencies by scanning pyproject.toml files. Eliminates manual package lookup and enables more accurate coding assistance through seam | |
| HexDocs MCP bradleygolden/hexdocs-mcp Provides semantic search capabilities for Hex package documentation using AI embeddings. Automatically fetches, processes, and searches Elixir package documentation to help developers find relevant information through natural language queri | |
| mcp_hello-world bradleylacroix/mcp_hello-world A minimal MCP server that responds with 'hello' at the /hello endpoint, serving as a scaffold for building MCP-style services. | |
| Vivint Security System MCP Server bradmb/vivint-mcp Provides read-only access to Vivint home security systems through an unofficial API. Enables monitoring of system status, devices, sensors, cameras, locks, thermostats, and recent events through natural language. | |
| tuskledger-mcp bradmorphsters/tuskledger-mcp Enables AI assistants to query and analyze local personal finance data from Tusk Ledger through tools for transactions, accounts, investments, and more, without sending data to the internet. | |
| FusionReactor MCP Server bradmusolff/mys-fusionreactormcp Enables AI assistants to query FusionReactor Cloud metrics, logs, and alerts via MCP tools. | |
| agent-product-catalog bradraylucas-eng/ai-agent-product-catalog Read-only MCP catalog server for bradray2's Gumroad line of AI-agent tools and datasets. Tools: list_products, get_product, purchase_info (returns Gumroad URLs + checkout instructions for live products; coming-soon items carry no links). No | |
| kanban-mcp bradrisse/kanban-mcp Enables AI assistants to manage Planka kanban boards, including creating, updating, and organizing tasks, lists, and cards via MCP. | |
| mail-smtp-mcp bradsjm/mail-smtp-mcp A TypeScript MCP server that enables LLMs to send outbound emails via SMTP with support for attachments and HTML content. It includes outcome-oriented tools for account validation and enforces strict security policies like recipient allowli | |
| nl2sql-mcp bradsjm/nl2sql-mcp A production-ready MCP server that transforms natural language into safe, executable SQL queries with multi-database support and intelligent schema analysis. | |
| CodeRabbit MCP Server bradthebeeble/coderabbitai-mcp Enables LLMs to retrieve, analyze, and programmatically implement CodeRabbit AI code review suggestions on GitHub pull requests, with automated workflows for processing and resolving review comments. | |
| mcp-macos-cua bradthebeeble/mcp-macos-cua Enables AI agents to control macOS desktop apps via screenshots, mouse clicks, keyboard input, accessibility queries, and AppleScript. | |
| Intervals MCP bradyap/intervals-mcp Enables chat to query cycling training data from Intervals, including athlete profiles, activities, wellness, and calendar events, via read-only tools. | |
| screenshot-mcp bradydouthit/screenshot-mcp Enables AI assistants to take screenshots of localhost development servers for visual verification of UI changes, reducing manual debugging cycles. | |
| docx-mcp-server bradygaster/docx-mcp-server Enables natural language interaction with local .docx files, allowing users to find, read, search, and summarize Word documents using friendly names and location hints. | |
| jarvis-trading-mcp bradylandry/jarvis-trading-mcp Enables Claude to access a remote research API for options screening, AI-driven trade thesis generation, earnings analysis, macro risk signals, and implied volatility lookup. | |
| Godot MCP bradypp/godot-mcp A Model Context Protocol server that enables AI assistants to manage Godot projects, scenes, and editor operations through natural language commands. | |
| MCP Gateway bradzw0917/mcpgateway A proxy service that connects Claude Code to Alibaba Cloud International OpenAPI MCP Server, supporting services like ECS and OSS. It provides secure multi-user authentication via OAuth 2.1 and allows for dynamic configuration of MCP servic | |
| MCP-summarization-functions braffolk/mcp-summarization-functions Provides intelligent summarization capabilities through a clean, extensible architecture. Mainly built for solving AI agents issues on big repositories, where large files can eat up the context window. | |
| Mail.ru MCP Server braflovskikyle40-debug/mailru-mcp Gives MCP clients access to a Mail.ru mailbox for reading, searching, and filtering messages, creating folders, moving, archiving, and deleting mail, and preparing or sending replies, with mass operations preceded by dry runs and deletions | |
| atlas-mcp-doc-search bragabruno/atlas-mcp-doc-search Enables hybrid document search (BM25 + vector) with Reciprocal Rank Fusion over the Atlas corpus, returning ranked chunks from documents. | |
| Shopify Store MCP Server brahim-benzarti/shopify_store-mcp Enables AI agents to interact with live Shopify stores through Admin and Storefront APIs for tasks like GraphQL execution, bulk operations, and file uploads. It includes built-in rate limiting and operation logging to manage store data and | |
| MS 365-21V MCP Server brahim86034/ms-365-21v-mcp-server Enables MCP-compatible AI clients to access and manage the authenticated user's 21Vianet Microsoft 365 mail, calendar, OneDrive, SharePoint, and related Graph data while respecting tenant permissions, confirmations, and audit boundaries. | |
| Zettelkasten MCP Server brahimaguilar/zettelkasten-mcp Enables users to create, link, explore, search, and synthesize atomic Markdown notes through Claude and other MCP-compatible clients, with tagging, semantic link types, and dual Markdown/SQLite storage. | |
| BioLab MCP Server brahimbattou/biolab-mcp-server Unified MCP server providing AI-agent-ready access to AlphaFold, PubMed, ChEMBL, Ensembl, and 37+ scientific databases. | |
| Augments MCP Server brahimd621/augments-mcp-server Delivers real-time, intent-aware documentation for any npm package, returning TypeScript signatures, prose docs, and code examples directly to AI coding assistants with minimal token usage. It also enables concept-based API search, version | |
| MultiZen brahimf3305/multizen-browser Exposes a localhost MCP endpoint that lets AI agents drive isolated browser profiles — navigating, clicking, typing, extracting, screenshotting, evaluating JS, and managing tabs and cookies — so real authenticated workflows can be completed | |
| locklens brahimflores/locklens Enables auditing npm, Yarn, and pnpm lockfiles in local project directories or remote Git repositories, including private ones, and returning unified vulnerability reports. Supports configurable severity thresholds, dependency scope, npm re | |
| Siri Shortcuts MCP Server brahimg954/mcp-server-siri-shortcuts Enables LLMs to list, open, and run any shortcut available in the macOS Shortcuts app, passing optional text or file input and returning shortcut output. Dynamically generates a callable tool for each installed shortcut so assistants can in | |
| Typst MCP Server brahimn78686/typst-mcp Enables AI models to convert LaTeX snippets into Typst, validate Typst syntax, browse Typst documentation, and render Typst code to PNG images. | |
| Codex Control Plane MCP brahimr85534/codex-control-plane-mcp Enables MCP clients to submit long-running Codex Desktop automation as durable async operations, returning operation IDs immediately for status polling, Plan Mode approval, and final report retrieval without blocking for hours or duplicatin | |
| CamoFox MCP brahimzakharov6324/camofox-mcp Connects MCP-compatible AI agents to a separate anti-detection browser server, providing tools for navigation, interaction, search, extraction, downloads, multi-tab workflows, and session reuse. | |
| Brainbase MCP brainbasehq/brainbase-mcp Enables management of Brainbase agents, components, evals, tasks, and more via a remote MCP connection with OAuth authentication. | |
| FlowLink AI Governance braincreator/flowlink AI Governance and SecOps platform for remote servers | |
| Quick-start Auto MCP braincrew-lab/mcp-usecase A tool that helps easily register Anthropic's Model Context Protocol (MCP) in Claude Desktop and Cursor, providing RAG functionality, Dify integration, and web search capabilities. | |
| firefly-iii-mcp braindaamage/firefly-iii-mcp Enables AI agents to manage Firefly III personal finances directly through 114 tools across 13 resource categories, supporting both stdio and HTTP transports. | |
| MCP-ABI braindao/mcp-abi Enables interaction with Ethereum-compatible smart contracts through their ABI, allowing both read operations (querying state) and write operations (executing transactions) dynamically based on the contract's interface. |
35,301–35,350 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.