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 |
|---|---|
| multicomp-mcp cameroncoats/multicomp-mcp Enables control of the Multicomp Pro MP711134 bench power supply and multimeter over USB serial, allowing an LLM agent to power-cycle boards, measure current profiles during boot, run custom voltage/current profiles, and wait for conditions | |
| shopify-admin-mcp-server camerone05/shopify-admin-mcp-server Enables Shopify store management through the Admin GraphQL API, offering 54 scope-aligned tools for orders, products, inventory and location fulfilment by SKU, customers, collections, discounts, content, metafields, and analytics. | |
| productive-mcp cameronfairbairn/productive-mcp An MCP server for Productive.io that enables users to log time, inspect projects, and manage time entries using natural language commands. It features fuzzy project matching, local caching, and remembers default services per project for str | |
| ASCII Motion MCP cameronfoxly/ascii-motion-mcp Enables AI assistants to create, animate, and export ASCII art using natural language, with live browser sync. | |
| Google Earth Engine MCP Server cameronking4/google-earth-engine-mcp MCP server for interacting with Google Earth Engine, enabling geospatial analysis such as dataset visualization, statistics computation, and search via AI assistants. | |
| Next.js MCP Server cameronking4/nextjs-mcp-use A sample MCP server implementation for Next.js projects that uses the Vercel MCP Adapter to handle protocol requests across different transport methods. | |
| MCP SSE Server POC cameronking4/spawn-mcp Enables creating and managing MCP server configurations with SSE streaming endpoints via a UI, deployable on Render with zero infrastructure. | |
| AT Protocol MCP Server cameronrye/atproto-mcp Enables LLMs to interact with the AT Protocol ecosystem, including Bluesky, through natural language. Supports public data access without authentication and full write operations with authentication. | |
| MCP Server Template cameronsjo/mcp-server-template A production-ready TypeScript template for building MCP servers with dual transport support (stdio/HTTP), OAuth 2.1 foundations, SQLite caching, observability, and security features including PII sanitization and rate limiting. | |
| Disney Parks MCP Server cameronsjo/mouse-mcp Provides access to Disney parks data including attractions, dining locations, height requirements, Lightning Lane status, and other park information for Walt Disney World and Disneyland resorts through structured queries and fuzzy search. | |
| Obsidi MCP cameronsjo/obsidi-mcp Exposes Obsidian vault tools via Model Context Protocol (MCP) server over stdio, HTTP, or SSE transports, enabling AI assistants to read, write, search, and manage vault notes with 28+ built-in tools and CLI bridge integration. | |
| bare-mcp camerontofer/bare-mcp A minimal, general-purpose implementation of the Model Context Protocol (MCP) for Node.js and Bare runtime, enabling creation of AI-interactive servers with tools, resources, and multiple transport options. | |
| homestack cameronwu421/homestack MCP server that exposes personal device data from sources like Oura into a unified SQLite store, allowing Claude to answer questions across metrics (sleep, activity, etc.) with a set of read-only tools. | |
| stellar-x402-mcp camesenin/stellar-x402-mcp Enables autonomous AI agents to access paid MCP tools and APIs by handling HTTP 402 payment challenges automatically, signing and settling Stellar/Soroban micropayments with budget ceilings and anti-replay verification. | |
| imessage-mcp camfortin/imessage-mcp A local MCP server that enables reading iMessage conversations and sending new messages through Claude Desktop. It provides secure, read-only access to your Mac's iMessage database and AppleScript-based message sending capabilities. | |
| Shared Whiteboard camfung/shared-whiteboard Enables Claude to create, open, and edit persistent tldraw whiteboards in real-time, with live collaboration between human and AI. | |
| ws-mcp camggould/ws-mcp MCP server that gives LLMs full visibility into your ws-cli workspace tree, enabling queries about workspaces, git status, tasks, and saved browser tabs. | |
| Instagram DM MCP server camila00740/instagram_dm_mcp Enables sending Instagram Direct Messages from your account and managing chats, messages, media, users, stories, followers, and related interactions through MCP tools. | |
| slop-guard camila02800/slop-guard Enables agents to analyze text strings or files for formulaic AI writing patterns, returning a 0–100 score, band label, specific violations with context, and concrete advice. It performs this rule-based linting locally without LLM judges or | |
| Langfuse Prompt Management MCP Server camila74285/mcp-server-langfuse Enables users to list, retrieve, and compile Langfuse prompts with provided variables, and access this through both MCP prompt and tool interfaces. | |
| tradingview-chart-mcp camilakaplan0412/tradingview-chart-mcp Enables users to retrieve chart snapshot images for specified symbols and timeframes through natural-language prompts, with browser pooling for faster concurrent requests and built-in performance statistics. | |
| Taskade MCP Server camilam044/mcp Connects AI assistants and IDEs to Taskade workspaces, projects, and tasks, enabling natural-language management of workspaces, projects, tasks, and AI agents, along with generating MCP tools from any OpenAPI spec. | |
| CVE-Search MCP Server camille54359/cve-search_mcp Enables querying the CVE-Search API to browse vendors, list products for a vendor, retrieve vulnerabilities for a vendor and product, fetch individual CVE records, get the latest CVEs with CAPEC/CWE/CPE expansions, and inspect current datab | |
| Android Source Explorer MCP Server camillej33/android-source-explorer-mcp Enables on-demand, precise exploration of AOSP and AndroidX source code, including class and method lookup, inheritance inspection, regex search, and optional cross-file navigation via LSP. | |
| web3-research-mcp camillej33/web3-research-mcp Enables deep cryptocurrency token research by pulling live market data, exchange listings, protocol TVL and fees, plus web search results from CoinGecko, CoinMarketCap and DeFiLlama. Runs entirely locally over stdio with no API key required | |
| WooCommerce MCP Server camillek04/woocommerce-mcp-server Enables interaction with WooCommerce stores through the WordPress REST API, providing comprehensive tools for managing products, orders, customers, shipping, taxes, discounts, and store configuration via JSON-RPC 2.0. | |
| Typst MCP Server camillekumar70062/typst-mcp Enables AI models to interact with Typst by converting LaTeX to Typst, validating Typst syntax, accessing Typst documentation, and rendering Typst code as PNG images. | |
| Vectorize MCP Server camillekumar70062/vectorize-mcp-server Enables vector search and document retrieval, text extraction and chunking into Markdown, and private deep research generation using configured pipelines. | |
| ReActMCP Web Search camillestavrou/reactmcp Enables AI assistants to perform real-time web searches through the Exa API, with basic queries and advanced filtering by domain, required text, and date ranges. Returns Markdown-formatted results including titles, URLs, publication dates, | |
| WhatsApp MCP Server camilloborges/whatsapp-mcp-docker Enables AI agents to send and receive WhatsApp messages, search chats, share media, manage approvals, and get activity summaries through MCP. | |
| linear-mcp-server camillodev/linear-mcp-server Provides full CRUD operations for Linear issues, projects, cycles, teams, labels, and workflow states through 15 tools, enabling natural language management of Linear workspaces. | |
| vitela-bridge camilochs/vitela-bridge Enables coding agents to securely work with a Vitela editor tab via MCP, running tools like checks, compilation, and verification inside the tab while proposing changes as revisions the author can accept or reject. | |
| Semantic Search MCP Server camilojourney/holusight Provides hybrid semantic and keyword code search for Claude Code using BM25 and vector retrieval. It enables indexing and searching local codebases with language-aware chunking and local embeddings. | |
| Roam Research MCP Server camiloluvino/roammcp Enables AI assistants to interact with Roam Research graphs through comprehensive API access, supporting page/block operations, markdown import, search, memory storage, and complex batch actions for managing knowledge graphs. | |
| Microsoft Project MCP Server camilop19/msproject-mcp Enables AI assistants to control, automate, and query desktop project-management schedules in real time via native Windows COM, including task/WBS management, resource and cost assignment, baselines, critical path, status reporting, and PDF | |
| aware-connector camilopiedra92/aware-connector MCP server for Autodesk's Aware employee directory, enabling search for people by name, email, or title, fetching individual records, viewing org reporting lines, and reading your own profile. It uses your own logged-in session to access th | |
| Knowledge Graph MCP Server camilothorne/mcp_server Exposes SPARQL-backed tools that let users run arbitrary SPARQL queries against DBpedia and search DBLP publication titles by topic to retrieve citation-count results. It serves these capabilities over Streamable HTTP, so MCP clients can ca | |
| Sequential Thinking MCP Server camilovelezr/server-sequential-thinking Enables AI assistants to work through complex problems step-by-step with dynamic thought processes, allowing for revision of previous steps, exploration of alternative approaches, and flexible planning as understanding deepens. | |
| academic-remote-mcp camir24/academic-remote-mcp Enables clients to retrieve random study tips remotely via a stateless MCP server deployed on Google Cloud Run. | |
| CamMicGo SEO Agent cammicgo/cammicgo-seo-agent Connects Google Search Console and Google Analytics to AI assistants for SEO analysis, though the current public preview only exposes a service_info tool and does not yet enable Google account access. | |
| UniFi Network MCP Server camorageaholic1/unifi-mcp-server Enables AI assistants to manage and monitor UniFi network infrastructure through natural language, providing 46 management tools across device, client, WiFi, network, firewall, port forwarding, monitoring, and site management. | |
| mcp-rules-server camoran89/mcp-code-review MCP server that provides code validation rules and analysis for various stacks/frameworks, enabling automated code reviews and reporting directly from VS Code and other editors. | |
| mcp-commits camoran89/mcp-commits MCP server providing commit rules with SemVer and conventional commits format for development teams. | |
| Satrack Documentation Generator MCP camoran89/mcp-docs MCP server for automatic technical documentation generation of Satrack projects. | |
| satrack-create-project camoran89/mcp-scaffold Enables project creation with validated flow and automatic registration via MCP, supporting scaffold, bootstrap, and validation tools. | |
| storybook-renderer camoran89/mcp-storybook-render MCP server to query and render the Doggie UI design system's Storybook documentation, enabling component search, URL rendering, and natural language questions. | |
| whoop-ai-mcp campbell24764/whoop-mcp A read-only WHOOP MCP server that lets Claude Desktop, Claude Code, Codex and GitHub Copilot answer questions about your own recovery, sleep, HRV, strain and workouts, comparing days against your personal baselines without exporting data yo | |
| RyanNg campfirein/byterover-cli Cipher is an opensource memory layer specifically designed for coding agents. Compatible with Cursor, Windsurf, Claude Desktop, Claude Code, Gemini CLI, AWS's Kiro, VS Code, and Roo Code through MCP, and coding agents, such as Kimi K2. | |
| @byterover/umami-mcp campfirein/umami-mcp A read-only MCP server for Umami analytics, enabling natural language queries of website stats, traffic trends, events, sessions, and analytics reports. | |
| knowledgeplane camplight/knowledgeplane MCP server that gives AI agents and teams persistent, shared memory using a knowledge graph with vector embeddings, automatic consolidation of related facts, and hybrid search. |
36,601–36,650 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.