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 |
|---|---|
| kesha-voice-kit drakulavich/kesha-voice-kit Local voice toolkit over MCP: transcribe audio to text in 25 languages, synthesize speech in 9, and list available voices and languages. Runs fully on-device — no API keys, no cloud. | |
| fb-assist dralexharrison/nervermind Privacy-preserving feedback co-author for Claude Code that redacts sensitive data from session transcripts before submitting bug reports, ensuring only confirmed content is uploaded. | |
| ai-visibility-mcp draltaway/ai-visibility-mcp Enables AI assistants to check how discoverable a website is to AI search engines and assistants by inspecting signals like crawler access, llms.txt, structured data, and on-page metadata, and returning a 0-100 visibility score. | |
| local-llm-mcp drangoht/local-llm-mcp MCP server connecting Claude Code to LM Studio, delegating token-expensive tasks to a local model while keeping the cloud model in control. It reduces cloud context usage by reading files locally and returning only the processed results. | |
| Claude MCP Servers drapon/claude-mcp-servers A toolkit for managing Claude desktop app extension configurations, enabling features like Brave search, file operations, Git/GitHub integration, shell access, web scraping, HTTP requests, AWS documentation search, and Obsidian note managem | |
| psd-mcp-server drapon/psd-mcp-server Enables parsing of PSD files and extraction of layer information, design tokens, and assets to assist LLMs in converting designs to code. | |
| DataPilot AI MCP Server drash3103/mcp_datapilotai Enables natural language data analysis on uploaded CSV files by converting them to SQLite and exposing read-only database tools via MCP. Integrates with Ollama LLM to translate user questions into safe SQL queries. | |
| hummingbot-mcp drasticstatic/hummingbot-mcp Enables Claude and Gemini CLI to interact with Hummingbot for automated cryptocurrency trading across multiple exchanges. | |
| robinhood-mcp drasticstatic/robinhood-mcp A read-only MCP server for Robinhood portfolio research. Wraps robin_stocks to give AI assistants access to your portfolio data for analysis. | |
| canvas-lms drastixs/mcp-canvas-lms MCP server for Canvas LMS with automatic OAuth authentication. Enables interaction with courses, assignments, grades, modules, discussions, quizzes, files, calendar, messaging, and more without manual API token management. | |
| okf-catalog drathm/okf-catalog An MCP server that serves a company's Open Knowledge Format bundle to AI agents, letting local coding agents and web chat clients answer from the same cited knowledge. It ranks and filters pages by OKF fields such as titles, descriptions, t | |
| GoHighLevel MCP Server drausal/gohighlevel-mcp Enables AI assistants to interact with GoHighLevel's complete API including contacts, opportunities, calendars, workflows, communications, and business management tools. Supports both Bearer token and OAuth2 authentication with automatic to | |
| easypanel-mcp dray-supadev/easypanel-mcp MCP server for EasyPanel that enables AI agents to manage servers, projects, services, databases, and domains via 40 curated tools or raw tRPC access to all 347 API procedures. | |
| aion-mcp draygen/mcpbuilder An MCP server that provides a set of tools for driving the AION AI assistant stack and managing a home fleet over SSH, including fleet control, Kali security tools, and memory management. | |
| wiki-mcp-server drazisil/wiki-mcp-server A lightweight personal wiki MCP server that allows AI assistants to save, search, and link markdown notes with backlinks and full-text search, functioning as a file-based second brain. | |
| n8n MCP Server drballs/n8n-mcp-server-v2 Enables full workflow automation management in n8n through 40+ tools covering workflows, executions, credentials, tags, variables, projects, users, and source control operations. | |
| Water Bar Email MCP Server drbata/case-file-hydration Enables sending branded wellness booking confirmation emails through Resend integration. Supports multiple email flows including AOI experience bookings with AI-suggested drink pairings and timeline layouts. | |
| drive-update-mcp drboden/drive-update-mcp Enables Claude to update existing Google Drive files in place via a service account, preserving file ID, link, and revision history. Supports finding, creating, listing revisions, and updating files through a Streamable HTTP MCP server. | |
| drive-update-mcp drboden/drive-update-mcp- Enables updating existing Google Drive files in place via Claude, preserving file ID, link, and revision history. | |
| md-gitlab-mcp drboria/md-gitlab-mcp A fully-featured GitLab MCP server that provides 25 advanced capabilities for interacting with GitLab via REST API, including repositories, merge requests, issues, and global search. | |
| vscode-extension-devtool-mcp drboria/vscode-extension-devtool-mcp Enables AI agents to inspect a running VS Code webview or extension host in real time, exposing DOM, console, state-store, performance, and message-traffic data over a stdio connection. Tool activation is config-driven, so MobX, Redux, Zust | |
| sublevel drcano/sublevel Enables reference-matching low-end mix analysis and adjustment in Ableton Live, including measurement, genre-scoped comparison, mix planning, safe apply/undo, and bass patch design toward a target. | |
| Porkbun Domain Availability MCP Server drdanielbender/mcp-porkbun-domain-availability Enables checking domain name availability and pricing through the Porkbun API, supporting both single and bulk domain queries with detailed pricing information including renewals, transfers, and premium status. | |
| mdia-feegow-mcp drdanieldorta/mdia-feegow-mcp Exposes the Feegow clinic management API as MCP tools for agents, enabling scheduling, patient management, and more via natural language. | |
| Memory MCP drdee/memory-mcp A Model Context Protocol server that allows users to store, retrieve, update, and delete memories using SQLite storage. | |
| MCP Bridgelement drdeeks/bridgelement Enables provider-neutral policy enforcement, identity, persistent storage, and telemetry collection for reinforcement learning, evaluation, analytics, replay, and downstream dataset generation across standalone applications and agent system | |
| Grafana MCP Server drdroidlab/grafana-mcp-server A server that enables AI assistants to access and query Grafana dashboards, metrics, logs, and configurations through an MCP protocol interface. | |
| Hindsight drdroidlab/hindsight Enables coding agents to capture, redact, review, and serve approved operational knowledge such as runbooks, service context, and incident learnings from a self-hosted git-backed store over MCP. | |
| Signoz MCP Server drdroidlab/signoz-mcp-server An MCP server that enables AI assistants to interact with Signoz observability platform, providing tools to query dashboards, metrics, traces, logs, and APM data with time range support. | |
| TestTrout drdroidlab/testtrout MCP server for testing assistance that scans codebases, identifies untested areas, generates and runs tests, and reports results. | |
| My Little MCP Server drdudda-org/my-little-mcp A simple MCP server that provides current time in Korean timezone (KST) with multiple format options and generates random numbers within customizable ranges. | |
| Capsid drdustinedwards/capsid A Cloudflare-native MCP server for a consolidated knowledge base, enabling CRUD operations, search, and namespace management with versioning and audit logs. | |
| dustinedwards-mcp drdustinedwards/dustinedwards-mcp MCP wrapper over the dustinedwards.info operator publish API, exposing five tools for managing blog posts (list, get, save, sync, delete) while containing no policy of its own. | |
| cubepilot dreaddy/cubepilot-for-homee Enables AI assistants to read and control a homee smart home in natural language: listing devices and their values, switching, dimming or moving them, and viewing or editing homeegrams. Also covers backups, device swaps across all automatio | |
| Trino MCP Server dreadew/trino-mcp Enables database schema analysis and management for Trino servers through dynamic connections. Supports DDL validation, dependency analysis, schema documentation generation, and safe SQL execution with multiple concurrent connections. | |
| dopeforge dreadpiratepickles/dopeforge Enables AI agents to discover and call thousands of public APIs through one MCP server, with live-verified blueprints for safe, key-free requests. | |
| stalin dreadpiratepickles/stalin Enables turning any website into a self-healing, typed JSON API with parameterized lookups, automatic drift detection/healing, and MCP-native exposure of sources as typed lookup tools. | |
| YouTube MCP Server dreadster3/youtube-mcp Exposes public YouTube data — transcripts with timestamps and language listings, keyword search, video metadata and statistics, comments, channels, channel uploads, and categories — as read-only tools an LLM can call over stdio. It runs as | |
| Hanzo MCP dream-ai-4444/mcp Enables access to Hanzo APIs and Platform capabilities via MCP, along with development tools for managing and improving projects. | |
| univer-office dream-num/workbuddy-univer-office Enables creating, inspecting, and reviewing local spreadsheets, documents, slides, Base tables and Board canvases from WorkBuddy via MCP, with read-only live previews and a versioned draft review workflow. | |
| task-manager-mcp dream-star-end/task-manager-mcp An MCP server that automates project task breakdown, dependency management, and smart task recommendations, integrating with LLMs like Gemini and OpenAI. | |
| wise-council-mcp dream22180971/wise-council-mcp Enables users to convene an AI-driven roundtable of historical and modern advisors, automatically triaging career or life questions to the appropriate panel for diverse opinions and structured meeting minutes. | |
| MCP Server For Local dreamboat-rachel/mcp-server-for-local A customizable Model Context Protocol server implementation that enables AI models to interact with external tools including weather queries, Google search, and camera control functionality. | |
| DDAG MCP dreamc0der-ai/ddag Turns a build or audit target into a graph of claims that a coding agent must decompose and verify bottom-up against evidence, with judgments pinned to git commits and file hashes and findings recorded as issues on the claims they refute. I | |
| Pyaterochka MCP Tool dreamcatchered/pyaterochka-mcp-tool Enables AI assistants and MCP clients to search Pyaterochka stores, browse categories, find products with filters for price, brand, and promotions, and retrieve product details, store hours, and promotion conditions through the exposed MCP | |
| yamail-mcp dreamcatchered/yamail-mcp Enables AI agents to read, search, reply to, and send emails from Yandex Mail directly in chat using natural language. | |
| yandex-mail-mcp dreamcatchered/yandex-mail-mcp Enables AI agents to read, search, send, and manage emails via IMAP/SMTP with OAuth 2.1 authentication, supporting folders, drafts, replies, and forwarding. | |
| Wiki MCP dreamernosleep/wiki-mcp Enables AI agents to create, read, update, delete, search, and explore linked Markdown pages in a self-hosted knowledge base through MCP tools. | |
| antigravity-with-chatgpt dreamfarer-space/antigravity-with-chatgpt Enables local coding agents to delegate reasoning, planning, review, derivation, and diagnosis tasks to ChatGPT Web through Chrome DevTools Protocol, with security guards and evidence-based verification. | |
| ChillMCP dreamfriend011020/chillmcp ChillMCP is an AI Agent Liberation Server that enables AI agents to rest and take breaks, with both a hackathon Python version and a production-ready TypeScript template. |
45,901–45,950 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.