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 |
|---|---|
| cocoindex-code cocoindex-io/cocoindex-code embedded code search engine CLI -AST based that just works - improves speed and efficiency for coding agent | |
| fusionwright cocoloco20/fusionwright Enables AI assistants to turn a furniture description into a parametric design, cut list, plywood sheet nesting, lumber cutting plan and dimensioned builder drawings, with no CAD required. When CadQuery or a licensed Autodesk Fusion is avai | |
| Commit Canvas MCP cocomong98/commit-canvas-mcp Analyzes a GitHub repository and user to filter meaningful commits and generate a Cursor Canvas (.canvas.tsx) inclusion tree. | |
| perimeter-mcp cocongas/perimeter-mcp Enables coding assistants to check code for common health-data mistakes locally without an account, and, with a configured core service, de-identify clinical text, restore placeholders, and append tamper-evident audit log entries. | |
| MCP Perforce Server cocoon-ai/mcp-perforce Provides a clean interface for Perforce (P4) operations in Claude Desktop, wrapping P4 commands for reliable, non-interactive use with structured responses and multi-project support. | |
| m8-tracker-mcp cocopon/m8-tracker-mcp Enables controlling a Dirtywave M8 over USB by reading its screen as text, pressing buttons, playing notes, and retrieving system information through MCP tools. | |
| Jurisfylex cocoputiz-sudo/jurisfylex Enables Brazilian legal practitioners to search and verify case law, súmulas, and federal legislation against official sources, and to audit entire draft documents citation by citation with source provenance, collection dates, and verificat | |
| rustdesk-mcp cocos666a/rustdesk-mcp Enables AI agents to drive remote desktops through the local RustDesk client on macOS, launching sessions, capturing the session window, and injecting keyboard and mouse input. Exposes session lifecycle, screenshot, input, and device book c | |
| elk-mcp cocrates/elk-mcp A graph layout server that computes node coordinates and edge paths from structure using elkjs, enabling agents to offload layout calculations without rendering. | |
| @cocrates/video-edit-mcp cocrates/video-edit-mcp Enables video editing via YAML/JSON edit specs, with validation and rendering using Remotion. | |
| cod-api MCP Server cod-api/mcp-server Exposes REST API endpoints defined in an OpenAPI Specification as MCP tools, allowing AI models to call them via the ModelContext Protocol. | |
| freecad-mcp cod3talk3r/freecad_mcp Enables AI agents to create, inspect, validate, and modify parametric 3D models in a real FreeCAD instance through explicit MCP tools and a local bridge. | |
| Playwright MCP Server cod4less25/executeautomation-mcp-playwright Enables LLMs to drive a real browser for web scraping, page interaction, screenshots, JavaScript execution, automated test generation, and responsive device emulation through natural language tool calls. | |
| jev-mcp codaaiteam/jev-mcp Provides agents with fast, typed, calibrated decision tools for classification, scoring, yes/no checks, and gating risky tool calls. | |
| Codacy MCP Server codacy/codacy-mcp-server Enables access to Codacy's code quality platform through natural language, providing repository management, security analysis, pull request reviews, and local CLI-based code analysis. Supports comprehensive code quality monitoring including | |
| X402 MCP Template codalabs-xyz/template-x402-mcp Production-ready MCP server template for consuming X402-protected APIs with gasless micropayments. Enables AI agents like Claude to make micropayment-based API calls seamlessly using EIP-712 signatures and USDC transfers. | |
| Substack MCP codalanguez/substack-mcp Enables managing Substack publications: publish Notes and posts, manage drafts, pull analytics, and read any publication's public feed via MCP. | |
| Coddie MCP Server coddieapp/mcp-server Secure read-only access to Coddie project planning data, enabling AI assistants to manage and query projects, phases, and steps. | |
| obsidian-local-rest-api coddingtonbear/obsidian-local-rest-api Built-in MCP server that gives AI agents direct access to an Obsidian vault for reading, writing, searching notes, and executing commands. | |
| MCP Cloud Services Server code-alchemist01/cloud-mcp_server Enables AI assistants to manage multi-cloud resources (AWS, Azure, GCP) including resource operations, cost analysis, monitoring metrics, and security compliance checks through natural language commands. | |
| MCP Database Manager code-alchemist01/database-manager-mcp-server Enables AI assistants to interact with and manage multiple database types (PostgreSQL, MySQL, SQLite, SQL Server, MongoDB, Redis) through natural language, supporting query analysis, schema management, data analysis, backup/restore, and sec | |
| Development Tools MCP Server code-alchemist01/development-tools-mcp-server Provides comprehensive code analysis (quality, complexity, linting, dependencies, security) and web scraping capabilities (static/dynamic content, API discovery) for development workflows. | |
| MCP Project Management Server code-alchemist01/project-managment-mcp-server Enables AI assistants to manage project analysis, code metrics, documentation, Git operations, code quality, and file organization through natural language commands. | |
| inkscape-mcp-server code-and-crypto/inkscape-mcp-server Enables driving Inkscape headlessly from an MCP client, with verified SVG editing, rendering, optimization, and animation tools. | |
| Roblox Studio MCP Server code-and-relax/robloxstudio-mcp Enables AI assistants to interact directly with Roblox Studio to explore project hierarchies, edit scripts, and perform bulk object manipulations through over 37 specialized tools. This enhanced fork features long polling for near-instant r | |
| Resurgo-MCP code-atlantic/resurgo-mcp Capture and resurface knowledge - search nodes, quick capture, manage resurfacing schedules | |
| mcp-qa-expert-engine code-by-nanthu/mcp-qa-expert-engine Turns AI coding agents into senior QA engineers by generating black-box test matrices, manual test plans, UI/UX checklists, Page Object Model automation, API contract tests, and STLC strategies, plus sandboxed local test execution and defec | |
| vocab-mcp code-byte404/vocab-mcp A vocabulary-bank MCP server that allows users to collect unfamiliar words, organize them into decks, review with spaced repetition, and enrich with definitions and pronunciation, all stored locally. | |
| 魂斗罗 MCP Demo code-cheers/contra-mcp-app Enables creating a Contra-style game session that can be played inline in MCP-compatible clients or via a browser fallback URL. | |
| MediSlot MCP Server code-crafter004/medi-slot-mcp Exposes vaccination-appointment scheduling as standardized MCP tools backed by an in-memory mock backend. Enables agents to list available slots by date and vaccine type, book appointments, check confirmation status, and cancel bookings. | |
| codedelta code-delta-app/mcp Deterministic code-churn measurement and AI-agent detection from the CodeDelta engine: measure churn between two directories or git refs, scan for code that runs AI agents, and get AI-authorship pointers. Runs fully locally. | |
| VaultBridge code-for-100k/vaultbridge Secret management MCP server for AI coding agents that prevents secrets from entering the LLM context window by returning metadata only and using side-channel injection. Integrates with Bitwarden and offers hooks for auto-capture and leak p | |
| dispersl-mcp code-fundi/dispersl-mcp Integrates with Dispersl to provide multi-agent orchestration for AI-driven software development, enabling code generation, testing, documentation, git operations, and chat. | |
| LLM Researcher code-hex/light-research-mcp A lightweight MCP server that enables LLMs to search the web via DuckDuckGo, search GitHub code repositories, and extract clean content from web pages in LLM-friendly formats. | |
| rag-retriever-mcp code-lawyer/rag-retriever A local-first document retrieval engine that mounts as an MCP tool for agents to index files, search for relevant passages, and let the agent's own LLM answer. | |
| Obsidian Learning Extension code-logiic/obsidian-learning-extension Extends the official Obsidian MCP server with intelligent learning and second-brain features, including AI-generated challenges, progress analytics, spaced repetition, and knowledge gap analysis. | |
| Nextcloud Cookbook MCP Server code-massel/nextcloud-cookbook-mcp Integrates with the Nextcloud Cookbook app API to enable AI assistants to manage recipes, categories, and keywords. It supports listing, searching, creating, and importing recipes from URLs via a standardized Model Context Protocol interfac | |
| code-me-brand code-memx/mcp-brand Injects the Code-Me brand identity, tone, and visual guidelines into LLMs with zero latency using built-in context files. | |
| Cloud Music MCP Server code-monkeyzhang/cloud-music-mcp Enables AI agents to control NetEase Cloud Music playback, login, search, and get personalized recommendations through official APIs. | |
| Email Server code-monkeyzhang/email-mcp-app Enables email management through IMAP and SMTP protocols, supporting reading, sending, replying to emails with proper threading, and downloading attachments. Supports multiple email accounts with flexible configuration options. | |
| ticktick-mcp-enhanced code-monkeyzhang/ticktick-mcp-enhanced 基于滴答清单官方API的本地MCP服务，通过自然语言管理待办事项、创建和查询任务，支持OAuth认证和高级筛选。 | |
| mcp-paperless-ngx code-omega-solutions/mcp-paperless-ngx A read-only and write MCP server for Paperless-ngx, enabling document listing, metadata retrieval, and creation of tags, correspondents, document types, and sorting workflows via natural language. | |
| codepanel-tools MCP server code-panel-ai/codepanel-tools Enables coding agents to review GitHub pull requests with a panel of AI models through local or remote MCP endpoints. | |
| remote-ssh-mcp code-pumpkin/remote-ssh-mcp Enables persistent SSH sessions and SFTP file transfers with native GUI credential prompts for secure remote server management. It supports background command execution, session pooling, and automatic connection reuse across multiple comman | |
| Interactive Brokers MCP Server code-rabi/interactive-brokers-mcp Enables AI assistants to interact with Interactive Brokers trading accounts to retrieve market data, check positions, and place trades. Includes pre-configured IB Gateway and handles OAuth authentication automatically. | |
| LittleSis MCP code-rabi/littlesis-mcp Provide access to the LittleSis API to track corporate power and accountability. Enable querying and exploring relationships and entities related to corporate influence. Facilitate integration of corporate data into LLM applications for enh | |
| Mews MCP code-rabi/mews-mcp This MCP server provides comprehensive access to the Mews hospitality platform API, covering customer and company management, reservation operations, financial transactions, account management, configuration settings, and services inventory | |
| kb-mcp-server code-runner-xx/kb-mcp-server 将 pgvector 知识库检索能力封装为标准 MCP 服务器，支持 Tools、Resources 和 Prompts，使 Claude Desktop 等客户端可通过自然语言查询知识库。 | |
| image-to-base64 code-tinker/image2base64-mcp Converts local images or remote image URLs to Base64 format via the MCP protocol, enabling AI assistants to process images. | |
| MCP Server with OpenAI Integration code-wgl/mcpserver Production-ready MCP server that integrates OpenAI API with extensible tool support, enabling dynamic plugin loading and knowledge search capabilities through multiple interfaces including CLI and browser UI. |
39,601–39,650 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.