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 |
|---|---|
| marketnow-memory alicelabs-llc/marketnow-memory Provides persistent local memory for any MCP-compatible AI agent, enabling agents to store, search, recall, forget, export, and manage preferences, rules, and facts with zero dependencies, no cloud, and no API keys. | |
| LocalFiles MCP Server alicelynxx/localfiles-mcp-server Provides secure access to local files from specified directories. Enables listing files, reading contents, and configurable file size and extension filtering. | |
| mcptube-vision alicem16910/mcptube Enables users to ingest YouTube videos and have transcripts plus visual scene analyses compiled into a growing, cross-linked wiki that can be queried agentically for answers with citations. | |
| Piia Engram alicemitchell19730/piia-engram Enables multiple MCP-compatible coding agents to share a local-first, user-owned identity and knowledge layer of editable preferences, lessons, decisions, and project context that can be inspected, overridden, and carried across tools. | |
| Dynamic Reincarnation Story alicenjr/dynamic-reincarnation-mcp Enables interactive reincarnation storytelling where users choose their path after death, becoming characters like a vengeful spirit, Bilbo Baggins, or Monkey D. Luffy. Features dynamic narrative generation with personalized story paths bas | |
| Fermah MCP Community alicepoltora/fermah-mcp A public, read-only MCP server for researching Fermah products and documentation, with tools for searching docs, reading pages, listing products and proof systems, and generating non-binding project outlines. | |
| GIWA MCP Server alicepoltora/giwa-mcp-server Enables AI agents to interact with the GIWA blockchain, including balance queries, contract interactions, Flashblocks preconfirmations, Dojang attestations, and UP ID resolution. | |
| Sub Killer MCP Server alicepoltora/sub-killer-mcp MCP server for Dead Subscription Killer — scan wallets, detect crypto subscriptions, manage approvals on Monad blockchain. | |
| UTEXO MCP alicepoltora/utexo-mcp A hosted Model Context Protocol server providing secret-free, read-only Bitcoin and RGB tools for AI clients like Claude, with no API keys or installation required. | |
| Frappe MCP alicer9248/mcp Enables Frappe Framework apps to function as Streamable HTTP MCP servers by registering Python functions as tools and exposing them through a Werkzeug-compatible endpoint. | |
| remote-mcp-server-authless aliceric27/remote-mcp-server-authless A remote MCP server deployed on Cloudflare Workers without authentication, enabling tool creation and integration with MCP clients like Claude Desktop and Cloudflare AI Playground. | |
| mcp-system-summary alicetears/mcp-system-summary Provides structured instructions to Cursor for generating comprehensive system summaries of Node.js/TypeScript codebases. | |
| Stock MCP alicexu28466/stock-mcp Enables AI agents and backend workflows to access standardized multi-market financial data, technical indicators, fundamentals, news, filings, money flow, and CSV/JSON exports through MCP tools and HTTP endpoints. | |
| SV1 Agent Bridge alichicken/sv1-agent-bridge A local MCP server that enables AI agents to control Synthesizer V Studio 1.x via its Lua scripting API. | |
| DSH Crew (dsh-crew) MCP server / @zseven-w/dsh-crew alichoi8779/dsh-crew It lets Claude Code, Codex, Antigravity, and Grok dispatch work to real DeepSeek Harness agents while keeping native subagent progress UI, tier policy and escalation, dispatch guardrails, a jobs board, and a multimodal bridge giving text-on | |
| Zettelkasten MCP Server aliclark0512/zettelkasten-mcp Enables users to create, link, explore, and synthesize atomic notes through Claude or other MCP-compatible clients. Supports note types, semantic bidirectional links, tags, search, and graph-based discovery. | |
| Alidade MCP alidade-ai/alidade-mcp Forwards every tool call to a hosted MCP backend and, when supplied with your own X API bearer token, fills in the text and engagement metrics of X posts returned by mention and semantic searches so agents see readable posts instead of bare | |
| xunfeiPpt MCP Server alieforwang/xunfeippt Enables PPT generation using iFlytek Zhiwen API, supporting multiple transport protocols (HTTP, SSE, HTTP-Stream) and ReACT workflows for intelligent template selection, content generation, and document-to-PPT conversion. | |
| fatsecret-mcp alien-agent/fatsecret-private-mcp Provides LLM agents with read-only access to FatSecret's food and recipe database through MCP tools for searching foods and retrieving detailed nutritional information. | |
| mailchimp-mcp-alien-lifestyles alien-lifestyles/mailchimpmcp_v0 Integrates Mailchimp with Claude Desktop, enabling management of audiences, campaigns, and reports via natural language commands. | |
| rc-mcp alien2003/rocketchat-e2ee-mcp Enables Claude Code to browse and full-text search a Rocket.Chat workspace, including end-to-end encrypted rooms, by decrypting messages, threads and files locally with your own keys and password. It is read-only, exposes rooms, threads, me | |
| OuterSpace Apizr alien6-studio/outerspace-apizr Python capability compiler with scientific experiment tracking. Its local stdio MCP server provides six read-only tools for static discovery, readiness, exposure planning and experiment history/comparison under operator grants. Three option | |
| TunnelAdmin alienblog/tunnel_admin Web-based SSH connection manager with an MCP server that enables AI agents to manage remote hosts via terminals, file transfers, and port forwarding, featuring human-in-the-loop approval for secure access. | |
| ResiliReplay aliengineering-byte/resilireplay Local-first MCP and coding-agent reliability harness that captures bounded, sanitized failure evidence and generates deterministic executable regression tests. Capture is opt-in; no API key or hosted service is required. | |
| mcp-strudel alienmind/mcp-strudel Enables conversion between Strudel mini-notation patterns and MIDI notes, allowing Claude to generate and manipulate musical patterns and write them into Ableton clips via integration with AbletonMCP. | |
| sui-ops-bot-mcp aliercanozgokce/sui-ops-bot MCP server for managing developer escalations: turns Slack messages into tracked issues in Google Sheets, with tools to post messages, check status, get weekly reports, mark solved, and ping. | |
| gromacs-mcp alierkn/gromacs-mcp Enables running GROMACS molecular dynamics simulations through natural language, with tools for topology building, solvation, simulation management, and trajectory processing via the Model Context Protocol. | |
| vmd-mcp alierkn/vmd-mcp Drive VMD headlessly from any MCP client to analyze structures and trajectories, and ray-trace publication-quality images with no display. | |
| image-analyzer-mcp alierq/image-analyzer-mcp Analyzes images via OpenAI-compatible vision APIs, returning structured JSON for layout, components, colors, typography, and issues, with tools for single image analysis, comparison, and clipboard image analysis. | |
| Puppeteer Debugger MCP Server aliex7664/puppeteer-debugger-mcp-server An MCP server based on Puppeteer and Chrome DevTools Protocol for advanced browser debugging, performance analysis, and memory detection. It enables users to inspect DOM elements, monitor console errors, capture screenshots, and perform hea | |
| healthcare-mock-mcp alif-laam-meem/healthcare-mock-mcp Enables voice/chat agents to rehearse healthcare member-service conversations using synthetic tools for eligibility, benefits, claims, pharmacy pricing, and case creation, all against fabricated data with no real PHI. | |
| Deckbook alifanov/deckbook MCP server for the Deckbook task tracker, allowing AI agents to create and manage tasks with project-scoped tokens. | |
| doc-splitter alifazelidehkordi/verichunk Conceptual document splitter that parses PDF/DOCX into study-sized chunks with safe-cut constraints, verified output, and bilingual study indexes, exposed as MCP tools for AI coding assistants. | |
| Legal Document RAG MCP Server alifindrar/doc-scraper Enables semantic and keyword search over legal documents, conflict detection, and document overview, supporting Indonesian and English texts. | |
| Toru alifoo/toru Enables coding agents to record product demos, changelog GIFs, help-center guides, and bug repros by driving a signed-in browser or Mac window, then rendering branded MP4 and GIF outputs with delivery checks. | |
| NVD MCP Server alig1493/nvd-mcp-server MCP server for the NIST National Vulnerability Database — lets AI assistants search CVEs by keyword, severity, CPE, CWE, KEV status, and date range via natural language. | |
| vectordb-mcp alihaider20/mcp-vectordb-rag Local RAG system that ingests documents into a vector database using FAISS and SQLite, then enables Claude to search over them via MCP tools, all running locally with no API key required. | |
| SuperOffice AI Support MCP Platform alihaider663/superoffice-ai-support-mcp Enables AI assistants to securely triage SuperOffice CRM support cases by retrieving tickets, running database diagnostics, searching knowledge bases, and orchestrating cross-system incident investigations. | |
| superoffice-mcp-server alihaider663/superoffice-mcp-server Enables AI assistants to query and manage SuperOffice CRM Onsite data—contacts, persons, appointments, support tickets, custom extra tables, and audit logs—via the REST WebAPI. | |
| ai-medialens alihkhawaher/ai-medialens Enables AI coding agents like Cline to analyze video, audio, PDFs, and images by sending files to OpenRouter's multimodal models. It also provides a CLI and Python module for media analysis, with support for time-range trimming, PDF OCR, an | |
| Everything Search MCP Server alihkhawaher/everything-search-server Provides integration with Everything Search Engine allowing powerful file search capabilities through the Model Context Protocol with advanced search options like regex, case sensitivity, and sorting. | |
| neuron alii/neuron A Discord MCP server that gives AI agents full control of a Discord bot — messages, channels, roles, threads, forums, events, webhooks, reactions, moderation, image generation, and real-time voice. | |
| Accessibility MCP Server alii13/accessibility-mcp-server Enables AI agents to perform conversational accessibility testing with actionable insights, code-level fixes, and support for authenticated sessions and batch audits. | |
| arxiv-mcp aliildan/arxiv-toolkit Enables searching arXiv, fetching metadata, reading papers as section-aware Markdown, listing recent papers, and downloading PDFs via five MCP tools. | |
| Cochrane MCP aliildan/cochrane-mcp Turns the Cochrane Library into a tool for AI agents to search and retrieve clinical evidence, including systematic reviews, trials, and plain-language summaries. | |
| willhaben-mcp aliildan/willhaben-mcp Enables searching Austria's largest classifieds marketplace (willhaben.at) for real estate, cars, jobs, and second-hand items via natural-language queries and structured filters, with full listing details. | |
| ytb-tools aliildan/ytb-tools Enables AI assistants to search YouTube, fetch transcripts, and get AI summaries of videos without API keys. | |
| Medium MCP Server aliiqbal208/medium-mcp Enables AI assistants to interact with Medium's platform for publishing, updating, and managing articles and drafts through OAuth 2.0 authentication with automatic retry logic and rate limit handling. | |
| KPI-Lens aliivaezii/kpi-lens An MCP server for supply chain intelligence that enables conversational querying of eight operational KPIs and anomaly detection data through Claude. It allows users to analyze performance metrics like OTIF and inventory turnover while prov | |
| github-review-queue-mcp alijahak/github-review-queue-mcp Lets MCP clients such as Claude or ChatGPT find the pull requests waiting on your review, read their details and changed files, check CI status, post comments, and submit approve, request-changes, or comment reviews. It runs locally over st |
26,551–26,600 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.