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 |
|---|---|
| x402-mcp-demo catena-oss/x402-mcp-demo An MCP server that charges real testnet USDC per tool call using x402 pay-per-request protocol, transparently handled by a paying proxy for any standard MCP client. | |
| pubmed-mcp-server catherineabdullah69668/pubmed-mcp-server Enables searching PubMed and Europe PMC, fetching article metadata and full text via PMC/Europe PMC/Unpaywall, formatting citations, resolving partial references and identifiers, and grounding queries in MeSH vocabulary. Runs over stdio or | |
| engram-serve catherinec630/engram Exposes a local structural code graph and selected project memory through MCP so AI coding agents can retrieve focused entities, relationships, and recorded mistakes before reading full files. | |
| Finnhub MCP Server catherinedparnell/mcp-finnhub This server provides an interface with the Finnhub API, enabling users to obtain the latest market news, stock market data, basic financials, and recommendation trends for specific stocks. | |
| Langfuse MCP Server catherineh0509/langfuse-mcp Enables AI agents and developers to query Langfuse telemetry locally, fetching traces, sessions, observations, and exceptions, inspecting route decisions, and running metrics, prompt, dataset, and annotation-queue operations. Supports selec | |
| Zendesk MCP Server catherinejuncker99386/zendesk-mcp-server Enables users to retrieve and manage tickets and comments, analyze tickets and draft responses, and access Help Center articles as a knowledge base through per-operator OAuth-authenticated access. | |
| vivado-mcp catherinekato75/vivado-mcp Enables AI coding agents such as Claude Code, Cursor, and Codex to safely drive a locally installed Xilinx Vivado through 32 curated tools covering sessions, synthesis, implementation, timing and CDC analysis, XDC/IP debugging, offline VCD | |
| Codexless catherinep81673/codexless Enables ChatGPT to use a reviewed set of local Codex-backed tools for project inspection, file editing, bounded commands, Chrome/Edge browsing, and Excel control from normal Chat, while calling the Codex model only when explicitly needed. | |
| jevcore-mcp catherinestavrou94306/jevcore Enables any MCP host to pose typed yes/no, choice, and score questions and receive calibrated probabilistic judgments instead of prose, over stdio and offline by default. | |
| whoop-ai-mcp catherineweiss219/whoop-mcp Enables AI assistants such as Claude, Codex, and GitHub Copilot to query your WHOOP recovery, sleep, HRV, strain, and workout history read-only, including personal baselines, trends, sleep debt, and HYROX or triathlon performance reviews. I | |
| Liturgical Calendar MCP Server catholicos/liturgical-calendar-mcp Provides access to Roman Catholic Liturgical Calendar data, enabling retrieval of liturgical calendars for any year, nation, or diocese via MCP tools. | |
| MCP Bỏ Túi cathophile/mcp-bo-tui Enables Claude to ingest WhatsApp chat exports and shared files, search messages without diacritics, read conversations and documents or images, and draft WhatsApp replies via wa.me links while keeping data in the user's own Cloudflare acco | |
| Tally MCP Server cathrynlavery/tally-mcp-server A comprehensive Model Context Protocol server that enables Claude Desktop users to manage Tally forms with 23 powerful tools for creating, editing, and analyzing forms, submissions, questions, webhooks, and conditional logic. | |
| LLX Agent MCP Implementation cathylixi/llx-agent-mcp-implementation A minimal MCP server with a sample search_news skill that demonstrates how Claude Code can automatically call a skill over the MCP protocol. | |
| claude_mcp catid/claude_mcp Bridges Codex to a local Claude Opus 5 collaborator via Claude Code, enabling controlled read-only consultation or write-capable tasks on allowed workspaces with independent verification. | |
| Kimi K3 MCP catid/k3mcp A read-only MCP server that gives Codex and other clients a Kimi K3 second opinion through OpenRouter, enabling algorithm review, code review, and project planning. | |
| Ydris catinahat85/ydris An open-source, vendor-agnostic MCP governance proxy that sits between AI clients and tool servers to apply response projection, metering, and retry policies, reducing token bloat and providing per-tool cost visibility. | |
| YingDao RPA MCP Server catinair/aipower-rpa-mcp-server Enables AI to execute RPA applications and workflows through the Model Context Protocol, supporting both local and cloud modes. | |
| htb-mcp cativist/htb-mcp Enables assistants to interact with Hack The Box by wrapping HTB API operations as MCP tools for querying and operating HTB resources. | |
| Claude Flow MCP catlog22/claude-flow-mcp Integrates with Claude Code to execute AI-powered code analysis and workflow automation, supporting pre-defined scenarios like code review and security audit. | |
| codexlens catlog22/codexlens-search Semantic code search engine for Claude Code with hybrid search combining vector, FTS, AST graph, and ripgrep regex, with RRF fusion and reranking. | |
| Read-only Analytics MCP Server catom8/readonly-analytics-mcp-server Enables MCP clients to execute validated read-only warehouse queries through a guarded SQL API, with enforced row limits and secret-safe audit metadata. | |
| notion-local-ops-mcp catoncat/notion-local-ops-mcp Enables Notion AI to interact with local files, execute shell commands, and delegate complex tasks to local AI agents. Provides file operations, command execution, and task delegation capabilities for local workspace management. | |
| workspace-agent-relay-mcp catoncat/workspace-agent-relay-mcp A local relay and dashboard that enables ChatGPT Workspace Agents to stream real-time updates—plan, progress, tool calls, and results—back to the user's machine via MCP and SSE. | |
| apc-mcp catrinmdonnelly/apc-mcp MCP server for APC Overnight. Book, label, track and cancel UK parcel shipments from any MCP-compatible AI. | |
| NOVA MCP Server cats70/dolibarr-mcp Enables read-only investigation of NOVA's Dolibarr accounting and commercial data through an AI assistant, with privacy protection and deterministic accounting rules. | |
| Sugar cattaneo58/sugar Enables AI coding agents to store, search, and recall project-specific and global memory through MCP, using local SQLite and semantic search. It also optionally supports autonomous task execution powered by the same memory layer. | |
| Zotero MCP cattaneo58159/zotero-mcp Enables AI assistants to search a Zotero library, retrieve complete metadata for individual items, and read the full text of attached PDFs, connecting through either the desktop app's local API or the Zotero Web API. | |
| mcp-image cattaneo959/mcp-image Enables MCP clients to generate and edit images from natural-language requests, automatically enriching prompts with details like composition, lighting, and camera angle. It supports quality presets and multiple providers, including Gemini, | |
| mcpBPMSoft catter58/mcpbpmsoft Enables natural language interaction with BPMSoft CRM by handling OData complexity, lookup resolution, and safe CRUD operations through 32 MCP tools. | |
| SkillForge catvinci-studio/skillforge An MCP server that makes your AI agent learn and evolve by capturing feedback as reusable, persistent skills that improve over time. | |
| claude-session-bus catweazle74/claude-session-bus Enables coordination and communication between multiple Claude Code sessions across machines via a chat server, providing tools for sending messages, waiting for responses, and managing session status. | |
| Honeypot Detector MCP catwhisperingninja/honeypot-detector-mcp Detects potential honeypot tokens on Ethereum, BNB Smart Chain, and Base using the honeypot.is API. | |
| Uniswap Trader MCP catwhisperingninja/uniswap-trader-mcp Enables AI agents to automate token swaps on Uniswap DEX across multiple blockchains including Ethereum, Optimism, Polygon, Arbitrum, and more, with real-time price quotes, swap execution, and multi-hop route optimization. | |
| packet-pigeon catwithlover/packet-pigeon Email capabilities for AI agents to receive, read, reply, and send through MCP. | |
| Sight Cache catwithlover/sight-cache Exposes a protected, stateless MCP endpoint over a Cloudflare-hosted camera pipeline, letting agents list active devices and pull hour- or minute-level JPEG contact sheets for any time window. Agents can also enumerate exact capture timesta | |
| CLARA MCP Server catxp0/clara-mcp-server A hybrid pulmonary radiology diagnostic backend that provides MCP agent skills for vision inference, clinical RAG, report synthesis, and escalation, with multi-layer security. | |
| Connector MCP catzpro01/connector-mcp-agent Enables AI coding agents to run shell commands, spawn persistent background tasks, and read/write files inside isolated remote container sandboxes on a VPS. It also provides project workspace listing, task attach/kill controls, and a search | |
| DataGate caucus-race/copilot-datagate Provides a secure, policy-driven read-only gateway that exposes multiple databases to AI tools via MCP, with governed select, search, and aggregate operations and no free-form SQL. | |
| Google Calendar MCP Server caue397/google-calendar-mcp Enables LLMs to read, create, and manage Google Calendar events through a standardized interface, including features like listing calendars, managing events, and processing calendar information from screenshots and images. | |
| EspoCRM-MCP cauldr0nx/espomcp Open source MCP server for EspoCRM | |
| Expo MCP Server caullenomdahl/expo-mcp-server Enables programmatic interaction with Expo/React Native projects and EAS (Expo Application Services) for managing builds, publishing OTA updates, submitting apps to stores, and accessing comprehensive documentation. | |
| MM Query caullenomdahl/mm-query Enables querying and comparing products from MM's retail (B2C) and wholesale (B2B) platforms in Vietnam, including price comparisons, stock availability checks, and multi-store support with Vietnamese language integration. | |
| Pexels MCP Server caullenomdahl/pexels-mcp-server Enables AI models to search and retrieve photos, videos, and collections from Pexels via the Pexels API. | |
| Tailwind Svelte Assistant caullenomdahl/tailwind-svelte-assistant Provides access to SvelteKit and Tailwind CSS documentation, code snippets, and component examples with secure file operations and caching for building modern web applications. | |
| YouTube Music MCP Server caullenomdahl/youtube-music-mcp-server Enables AI assistants to search YouTube Music, manage playlists, and create smart recommendations using natural language. | |
| MCP CorelDRAW 2023 caumodascdp-bot/mcp-corel Enables AI clients using the Model Context Protocol to automate vector design on Windows 10, including creating and editing documents, applying prepress checks, exporting previews, and producing final PDF/CDR deliverables, with optional rem | |
| Memclaw caura-ai/caura Governed shared memory platform for AI agents and agent fleets. Provides persistent memory, cross-agent knowledge sharing, permissions, audit trails, and multi-tenant isolation through a Model Context Protocol (MCP) server. | |
| azure-devops-server-mcp causercode/azure-devops-server-mcp Connects MCP-compatible AI coding agents to self-hosted instances so they can discover projects, repositories, and branches, then create or update pull requests from a local Git context and return the PR number and browser URL. An explicit | |
| neko-mcp cavaldos/neko-mcp Enables AI agents to control a neko virtual browser via WebSocket and REST APIs, while allowing live viewing through a WebRTC stream. |
37,101–37,150 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.