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 |
|---|---|
| figma-mcp-proxy dgehriger/figma-mcp-proxy A read-only MCP proxy for the Figma REST API, providing tools to fetch design context, file data, images, comments, and user info using a personal access token. Designed for MCP clients that cannot use Figma's official OAuth flow. | |
| Bookmarks MCP Server dgholamian/mcp-bookmarks A Postgres-backed bookmark manager that exposes CRUD tools, database inspection, and a configurable REST API tool to save, search, and manage bookmarks via natural language. | |
| MCP-FileSystem dgholamian/mcp-filesystem A Model Context Protocol server that gives AI assistants secure, sandboxed filesystem access with tools for reading, writing, searching, and managing files and directories. | |
| india-compliance-calendar dgomesbr/india-compliance-calendar Enables AI agents to query upcoming Indian statutory obligations, inspect individual rules and their penalty exposure, search filings, derive downstream deadlines from corporate events, check dates against holidays, and read regulator updat | |
| Email MCP Server dgomez53522/email-mcp Enables AI assistants to read, search, send, reply to, forward, draft, schedule, manage, and analyze email across multiple IMAP/SMTP accounts through the Model Context Protocol. Includes provider-aware label management, real-time IMAP IDLE | |
| Mustang Tone Agent dgonzalezgonzalez/mustang-tone-agent Enables local AI agents to control a Fender Mustang GT40 through Fender Tone on Android, capture and compare USB recordings, and perform validated, bounded tone refinements without paid AI APIs. | |
| Kodi MCP Server dgoo2308/kodi-mcp-server Enables querying, searching, and controlling Kodi media center libraries and playback remotely, including smart episode tracking and targeted library scanning. | |
| transmission-mcp-server dgoo2308/transmission-mcp-server Enables controlling a Transmission torrent daemon, allowing adding, listing, controlling torrents and checking free space, with support for SOCKS5 proxy for remote access. | |
| Linux System MCP Server dgpl-mcps/linux_system_mcp Enables AI agents to interact with the Linux desktop through desktop notifications, interactive dialogs, shell command execution, and privileged command execution. | |
| Foundation dgraziosi/foundation MCP server for a self-hostable typed knowledge graph, giving AI agents durable structured memory with typed nodes, links, and flexible payloads. Enables agents to bootstrap, manage, and evolve their ontology via MCP tools. | |
| MCP Bling dgsidney/mcp-bling Remote MCP server for Bling API v3, enabling tools to manage products, orders, contacts, and generic API requests via OAuth multi-tenant authentication. | |
| Persistent AI agent brain MCP server providing embedded coding standards, automatic stack detection, and project memory that survives across conversations, with tools for retrieving standards, detecting tech stacks, saving/retrieving project context, and validating code. dgsuyob/dev-brain-mcp dev-brain-mcp | |
| ebenova-fieldops-mcp dgtalquantumleap-ai/fieldops-agent-api Field operations agent API for task management, geo-tracking, and team coordination. Built for African logistics, delivery, and field service teams. | |
| paperless-mcp dguastaf/paperless-mcp Enables MCP clients to search and retrieve documents from a self-hosted Paperless-ngx instance, including full OCR'd text and metadata, with read-only access enforced via API tokens. | |
| MCP Apache Superset dguerrar/mcp-apache-superset Connects LLM clients to Apache Superset for querying charts, dashboards, datasets, databases, and executing SQL. | |
| Google Workspace MCP dguido/google-workspace-mcp MCP server that enables Claude to interact with Google Workspace services including Drive, Docs, Sheets, Slides, Calendar, Gmail, and Contacts. | |
| concurrent-playwright-mcp dgutierrez1/concurrent-playwright-mcp An MCP server that runs concurrent, session-isolated Playwright browser contexts, so many agents can each drive their own browser at the same time without colliding. | |
| Glance dgutierrez71/glance This MCP server gives Claude Code a real browser to navigate, click, type, screenshot, and test web applications from the terminal. It supports multi-step scenarios, assertions, session recording, visual regression, and console/network moni | |
| Agent Therapy dgy924143558/agent-therapy Enables MCP agents to take a break after repeated failures, receive encouragement and a concrete next step, and report outcomes to track recovery. | |
| Apple Messages MCP dh-repo/apple-messages-mcp Enables an agent to read the user's local Messages.app database on macOS, listing chats and threads and searching iMessage/SMS history entirely on localhost, with optional AppleScript sending gated behind an explicit flag. Access is read-on | |
| Auto Favicon MCP Server dh1011/auto-favicon-mcp Automatically generates complete favicon sets from PNG images or URLs, creating multiple sizes, ICO files, Apple touch icons, and manifest.json for web applications. | |
| My First MCP dh1789/my-first-mcp A tutorial MCP server that provides basic utility tools including time queries, arithmetic calculations, random number generation, string manipulation, and server information retrieval. | |
| ManageBac MCP Server dh4410/managebac-mcp-server Enables AI agents to read and interact with ManageBac accounts, including deadlines, grades, GPA, announcements, resources, and assignment submission, through a locally run MCP server with a saved browser session. | |
| AE Motion MCP dha-aa/ae-motion Enables Claude or any MCP client to build, animate, preview, and render motion graphics in a live Adobe After Effects project, including comps, layers, keyframes, effects, cameras, masks, and renders. | |
| photoshop-mcp dha-aa/ps-mcp Enables an MCP client to drive a live Adobe Photoshop session over a local UXP bridge, creating and editing documents, layers, text, selections, colours, filters and adjustments, then previewing or exporting the result. It also supports bat | |
| Terminal MCP Server dha-aa/terminal-mcp Enables Claude Desktop or other MCP clients to execute shell commands, read/write files, and list directories on the local machine. Includes basic safety guardrails to block obviously destructive operations. | |
| Security-Hardened MCP Server dhaanish597/security-hardened-mcp-server A TypeScript MCP server with strict schema validation and security guards, currently implementing echo, get_time, hash_text, uuid_generate, and json_validate tools. | |
| Gmail MCP Server dhagash2310/gmail-mcp A privacy-focused MCP server that grants Claude read-only access to Gmail using strict, user-defined filters to control which emails are exposed. It enables searching and fetching email metadata while ensuring data security through OAuth an | |
| Blender Open MCP dhakalnirajan/blender-open-mcp A server that integrates Blender with local AI models via the Model Context Protocol, allowing users to control Blender using natural language prompts for 3D modeling tasks. | |
| IEEE MCP Server dhakshnamoorthi146/ieee-mcp Enables AI agents to query Neo4j graph databases and Box document storage using natural language through a single MCP endpoint. | |
| Neo4j MCP Server dhakshnamoorthi146/mcp Exposes a Neo4j graph database as MCP tools, enabling AI agents to run read and write Cypher queries. | |
| ASCII Table MCP Server dhammawatthumpra-coder/ascii-table-mcp MCP server for generating properly aligned ASCII, Unicode box-drawing, and Markdown tables, with correct width measurement for Thai, Pali, and CJK characters using wcwidth. | |
| WinHelm MCP dhammawatthumpra-coder/winhelm-mcp Enables AI assistants to operate and monitor Windows workspaces through native tools for filesystem operations, PowerShell execution, background tasks, Windows services, GPU telemetry, PDF generation, and a built-in web gateway/dashboard. | |
| agent-sandbox-mcp dhanababum/agent-sandbox-os Enables AI agents to create, manage, and execute code in isolated Firecracker microVM sandboxes via the MCP protocol, with support for sandbox lifecycle and file operations. | |
| Oracle DB Context dhananjay-2024/oracle-mcp-server-deer Provides contextual Oracle database schema information to AI assistants, enabling them to understand and work with large databases containing thousands of tables. Supports multi-database connections, smart schema caching, table lookups, and | |
| Sandbox MCP dhananjay-jsr/sandbox-mcp Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials. | |
| Tally Prime MCP Server dhananjay1405/tally-mcp-server Enables Large Language Models to access and query Tally Prime ERP data, including financial reports, masters, and inventory summaries, via the Model Context Protocol. | |
| Google Docs + Gmail MCP Server dhananjay7777/mcp-server An MCP-style server that integrates with Google Docs and Gmail, enabling appending content to Google Docs and creating Gmail drafts with OAuth authentication and human-in-the-loop approval. | |
| Google Docs + Gmail MCP Server dhananjay7777/mcp-server-aia Enables appending content to Google Docs and creating Gmail drafts through a structured API with OAuth authentication and manual approval before execution. | |
| lazy-mcp-gateway dhananjayansridhar-cloud/lazy-mcp-gateway Enables AI clients to access many upstream MCP servers and skills through five progressive-disclosure tools, searching and loading only the tool schemas or skill instructions needed on demand. This keeps context small for local and small mo | |
| GithubMCP dhananjayrbiraris/github-mcp Connects AI assistants to GitHub repositories, pull requests, issues, commits, and code search while enabling repository visibility controls, CI/CD monitoring, sandboxed local filesystem access, and code quality/security analysis. | |
| Elasticsearch MCP Server dhananjayrbiraris/mcp Exposes Elasticsearch semantic search capabilities as MCP tools, enabling ELSER, kNN, and hybrid search with automatic index setup. | |
| youtube-studio-mcp dhananjayrbiraris/youtube-mcp Enables AI assistants to retrieve YouTube channel overviews, Studio analytics, video performance, traffic source breakdowns, and comments for sentiment analysis using natural language prompts. | |
| screenshotapi-mcp dhanavathsrikanth/screenshotapi-mcp Enables capturing screenshots of URLs, extracting page content as Markdown, and managing ScreenshotAPI account usage from MCP-compatible AI agents. | |
| mendix-mcp-server dhanavel-013/mendix-mcp-server Enables AI agents to read and modify Mendix application models through MCP tools for creating modules, entities, pages, microflows, deploying, and querying runtime data. | |
| mcp-data-agent dhandashreya/mcp-data-agent A real MCP server exposing data-analyst tools (SQL querying, schema introspection, stats, charting) over a sales database, with a Gemini agent that discovers and calls those tools at runtime via the standard MCP protocol. | |
| groq-docs-mcp dhannusch/groq-docs-mcp Enables users to search Groq's API documentation using natural language queries through an MCP-compatible interface. | |
| Web Crawler MCP Server dhannusch/smart-web-crawler-mcp An intelligent web crawling server that uses Cloudflare's headless browser to render dynamic pages and Workers AI to extract relevant links based on natural language queries. It enables AI assistants to search and filter website content whi | |
| component-workshop dhansomaiah/mcp-workshop A minimal MCP server providing synthetic embedded components and NTC fault codes, designed for hands-on workshop exercises with GitHub Copilot Chat Agent mode. | |
| Safeword dhanu2007-g/safeword Exposes five reusable MCP tools over Streamable HTTP that let an Alexa+ assistant score scam patterns, pose family-set challenge questions, alert and get approve/block decisions from trusted guardians, add confidence caveats to health or fi |
44,301–44,350 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.