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 |
|---|---|
| Freedcamp MCP Server bluepointdigital/freedcamp-mcp-server A Model Context Protocol server that enables seamless integration with Freedcamp API for enterprise-level project management with advanced filtering, full CRUD operations, and extensive customization options. | |
| blueprint-modular blueprint-master/blueprint-modular Read-only catalog of the @blueprint-modular/core design system (104 components). Four tools — list/search/get components and suggest compositions. Public, no auth, Streamable HTTP. | |
| @blueprintaix/blueprint-mcp blueprintaix/blueprint-mcp Enables AI assistants to discover, evaluate, and execute DeFi yield strategies across EVM and Solana chains through natural conversation, with transactions signed locally. | |
| Heavy Metric MCP Server blueprintstudioco/heavymetric-mcp Provides access to 50+ battle-tested home service business strategies for pricing, marketing, sales, operations, and hiring. | |
| linda-mcp blueqwertz/linda-mcp Enables AI models to search and retrieve legal documents, magazine issues, comments, and related references from the Linde database (linda.lindeverlag.at) using the Model Context Protocol. | |
| project-analysis-mcp blues-web/roject-analysis-mcp MCP server for persistent project knowledge management, enabling AI assistants to store, search, and reuse project analysis insights with freshness checking and impact analysis. | |
| mcp-mssql-server blueshiftlabs-ai/mcp-mssql-server Enables Claude Code and other MCP clients to interact with Microsoft SQL Server databases through standardized tools for query execution, schema exploration, table management, and stored procedure execution. | |
| tianyan-mcp-server bluesky050/tianyan-mcp-server A read-only MCP server that enables querying available quantum computers and simulators from Tianyan Cloud, with tools to list running backends and retrieve detailed resource information. | |
| Coda MCP Server bluestemso/coda-io-mcp Provides full access to the Coda API v1, enabling AI agents to interact with Coda docs, tables, rows, formulas, and more through 51 tools. | |
| contacts-mcp bluesun-networks/contacts-mcp Enables AI assistants to manage contacts with full CRUD, dedup, merge, import/export, sync with Google/Apple/CardDAV, and git-backed rollback. | |
| @bluesun-networks/huly-mcp bluesun-networks/huly-mcp MCP server for Huly project management — enables managing issues, documents, people, and labels through natural language. | |
| MCP Sentinel bluetomlee/codegeist-mcp-sentinel Enables Rovo agents and external MCP clients to scan MCP server tool definitions for poisoning, hidden instructions, parameter smuggling, exfiltration, shadowing, and rug pulls. It returns risk-scored findings and can file remediation issue | |
| 13flow bluetouff/13flow MCP server that reconstructs hedge-fund/superinvestor portfolios from SEC EDGAR 13F filings, offering tools to query fund holdings, consensus activity, and quarter-over-quarter changes through a read-only API. | |
| Codebase RAG MCP Server bluewings1211/codebase-rag Enables AI agents to chat with codebases by indexing local directories or GitHub repositories into a vector database for semantic search and code retrieval. | |
| dingjie-erp-mcp bluewms/mcphub-erp Enables AI assistants to query and operate Dingjie ERP system via natural language, covering procurement, sales, and material management. | |
| PrecisionContextEngine bluezeamer/precisioncontextengine Enables AI coding agents to efficiently navigate and understand large codebases by providing tools for entry point location, call chain analysis, and impact assessment, reducing context consumption and model costs. | |
| mcp-mc-agent blueziii/mcp-mc-agent Gives any MCP client (Claude Desktop, Cursor, and others) a Minecraft character it can actually play, exposing 34 mc_* tools for joining servers, pathfinding, mining, crafting, smelting, chest access, combat, building, chat, first-person sc | |
| ds-mcp-sync blumaa/ds-mcp-sync Syncs design tokens and components from Figma to a Design System codebase, enabling automated generation of React components and Storybook stories. | |
| dsbridge blumaa/dsbridge Enables asking a consuming app in plain language to audit its design system usage, returning tables that sort every value and component by origin—design system, app-named, or none—along with token and contrast checks. | |
| Excel MCP Server blumenkuebel/excel-mcp-server Enables AI assistants to upload, access, and manipulate Excel files through MCP tools over HTTP, including file listing, downloading, and deletion with optional API-key protection. | |
| PowerPoint MCP Server blumenkuebel/ppt-mcp-server Enables AI assistants to create, open, and manipulate PowerPoint presentations through MCP, with HTTP file upload and download for use in Docker environments. | |
| sap-dm-pod2-mcp-server blumenkuebel/sap-dm-pod2-mcp-server Enables AI assistants to build, review, and migrate SAP Digital Manufacturing POD 2.0 plugins by providing access to pattern documentation, API references, REST and UI5 API specs, code examples, and validation workflows. | |
| Word MCP Server blumenkuebel/word-mcp-server Enables AI agents to create, edit, and manage Word documents through MCP tools, with HTTP-based file upload and download for use in Dockerized environments. | |
| EasyMCP blundberg042/easy-mcp Enables developers to build TypeScript MCP servers that expose tools, prompts, resources, and resource templates with minimal boilerplate via Express-like or decorator APIs. | |
| MaxForge MCP bluntman-420/maxforge-mcp Enables AI agents to control a live 3ds Max session directly, including creating and editing objects, materials, animation, and scene inspection, with undo support. | |
| OpenHaus Engineering MCP Server bluntsupremaci/openhaus-mcp Enables AI assistants to index, search, and retrieve engineering documentation, architecture, standards, and knowledge from the OpenHaus Engineering System via the Model Context Protocol. | |
| BlurHook MCP blurhook/blurhook-mcp Enables Robinhood Chain trading agents to obtain quotes, policy-checked unsigned public-swap calldata, simulations, hook information, prices, and deployment discovery without holding keys or signing transactions. | |
| tradingagents-mcp blurryface1/tradingagents-mcp MCP server that exposes TradingAgents multi-agent financial research as async tasks, generating research reports and non-executive decisions for LLM hosts without touching trading accounts. | |
| offthemode blurryvisions/offthemode Serves instructions and templates that make any AI coding tool plan before building, work through a project checklist in the right order, and hold a consistent standard, while all reading and writing of your code stays on your machine. | |
| py-exec-mcp blurxy/py-exec-mcp Enables MCP clients to execute Python code directly via stdin, preserving quotes, f-strings, and backslashes exactly as written, and returns stdout, stderr, and exit codes. | |
| DiscordMCP bluscream-vencord-plugins/mcp A Vencord plugin that provides MCP server capabilities for inspecting Discord's internal state, executing JavaScript code, accessing Flux stores, discovering webpack modules, and inspecting DOM elements within Discord's context. | |
| ai-history bluscream/ai-history-mcp Enables searching, indexing, and recovering past AI chat sessions and agent actions from local AI coding tools, with optional vector database semantic search and direct filesystem access. | |
| solidworks-mcp blussyya/solidworks-mcp Drives SolidWorks 2022 on Windows via COM to perform CAD operations like sketching, features, dimensioning, and mass property inspection from AI assistants. | |
| mcp-server-custody blvck-mamba-6/custody-alexa-mcp Enables voice-first shared object memory for Alexa+, letting users record where items were last reported, retrieve authorized locations, correct stale records, check shared items in and out, run guided Lost Mode searches, and manage privacy | |
| MemoVault blvckjs96/memovault A personal memory system that provides AI assistants with long-term memory capabilities through semantic search and vector storage. It enables Claude Code to store, retrieve, and manage personal context and project preferences using flexibl | |
| Resend MCP Server blw10210/resend-mcp-server Enables sending emails via the Resend API from Claude, with tools for sending, checking delivery status, listing recent emails, and managing domains. | |
| lo-mcp blwfish/libreoffice-mcp A stdio MCP server for LibreOffice Writer that enables creating, editing, and exporting Writer documents via natural language commands. | |
| GATEKEEPER MCP blxnkl1/gatekeeper-mcp Enables coding agents to gate code modifications behind an evidence check, preventing unnecessary edits by requiring reproduction of the problem before allowing changes. | |
| tea-planner blyatman996/tea-chay-advisor MCP server for tea enthusiasts to get daily tea recommendations, manage tea inventory, and fine-tune brewing parameters based on taste feedback. | |
| tokensStudioMCP blyawon/tokensstudiomcp MCP server that reads Tokens Studio design tokens from Figma and makes them available to Claude Code, enabling token-aware code generation. | |
| Asana MCP Server blzvi/asana-mcp-server Enables AI assistants to fully interact with Asana, including creating and managing tasks, projects, time tracking, and search, all through natural language. | |
| zammad-mcp bm1-de/zammad-mcp MCP server for Zammad that focuses on workflows the standard Zammad API tooling does not cover well — primarily shared drafts with strict reply-HTML validation, fresh signature rendering and German-localised quote blocks. | |
| social-mcp bmachek/social-mcp A self-hosted MCP server for managing Instagram and Facebook Page content, including posting, scheduling, analytics, and autopilot features. | |
| Cloudflare Remote MCP Server bmage8923/obsidian-mcp Enables deployment of a Model Context Protocol (MCP) server on Cloudflare Workers without authentication. Allows users to create custom tools and connect them to AI clients like Claude Desktop or Cloudflare AI Playground. | |
| MCP Boilerplate bmandalcusat/mcp_boilerplate A boilerplate for building and deploying remote MCP servers on Google Cloud with authentication, providing a foundation to experiment with MCP tools and capabilities. | |
| LangGraph Agent MCP Server bmaranan75/mcp-shopping-assistant-py Provides a standardized interface to interact with LangGraph agents through ChatGPT Enterprise, enabling conversational AI workflows with tools for agent invocation, streaming responses, and thread management. | |
| boss-cli-mcp bmbbms/boss-cli-mcp Enables AI assistants to automate Boss直聘 recruitment workflows via local Chrome, including candidate queries, messaging, batch replies, resume previews, and position management. | |
| mcp-dropbox-sign bmbouter/mcp-dropbox-sign MCP server for the Dropbox Sign API supporting signature requests, templates, teams, accounts, events, documents, signers, reports, bulk operations, and workflows. | |
| Gmail & Calendar Multi-Account MCP Server bmccreativedeveloper/google-mcp-server-claude A local MCP server that connects multiple Google accounts to Claude Desktop, enabling unified email search and send, calendar events, and full CRUD on Google Docs, Sheets, and Forms. | |
| MCP Discovery Server bmcgauley/mcp-discovery-server A meta-MCP server that discovers and explores other MCP servers using progressive disclosure patterns to reduce token usage by up to 99%. |
34,801–34,850 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.