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 |
|---|---|
| weather-mcp-server elmopps/weather-mcp-server Provides real-time weather data from the US National Weather Service API, enabling users to fetch active alerts for any US state and 5-period forecasts for any latitude/longitude location through natural language. | |
| nicheclock elmrank/nicheclock Enables AI assistants to query locally generated trend data from the last run, including rising topics by niche, upcoming dated events with publish-by dates, Search Console content gaps, and topic evidence for judging. It is read-only and d | |
| Remote Server MCP elmuz/remote-server-mcp A security-first MCP server that gives AI assistants controlled, safe access to manage remote servers via SSH with whitelisted operations and no generic command execution. | |
| RegGuard MCP Server elnino0009/regguard-mcp An AI-powered compliance assistant that analyzes financial marketing content for regulatory violations across multiple jurisdictions including Singapore, Hong Kong, UAE, and India. It enables real-time compliance checking, automatic disclai | |
| agent-julia elninopl/agent-julia Local-first MCP server providing persistent markdown memory with persona engine and fast search, designed to unify AI assistant memory across Claude Code, Cowork, and Dispatch. | |
| Semantic JS MCP elnonathan/semantic-js-mcp Provides structured semantic context for JavaScript/TypeScript codebases, enabling coding agents to navigate, review, and change code with explicit uncertainty. | |
| hledger-mcp eloircorona/hledger-mcp MCP server for hledger that exposes double-entry accounting tools to AI agents, enabling balance queries, transaction history, budget reports, and adding transactions to a journal. | |
| Remnawave Tools MCP eloktev/remnawave-tools-mcp Wraps the Remnawave API to provide per-operation MCP tools with mutation safety and data redaction, enabling secure interaction with Remnawave panel. | |
| github-data-mcp eloleksii/github-mcp A single-user MCP server that exposes your GitHub activity to Claude via three read-only tools: recent commits, open pull requests, and repository summaries. Deployed as a Vercel function using Streamable HTTP. | |
| paper-hermes elomokm/paper-hermes MCP server for scientific literature retrieval and summarization. Enables search, fetch, summarize, and translate arXiv papers, with subscription-based daily digests and integration with Obsidian and Telegram. | |
| Product Info Extractor MCP Server elon-jang/product-info-extractor-mcp Extracts product information such as price, stock, images, and sizes from e-commerce websites using stealth browsing techniques. | |
| multi-judge-consensus elonaug7/multi-judge-consensus Enables AI/agent-generated content to be reviewed by a cross-vendor committee of LLMs, returning verdicts, issues, votes, and cost estimates through an MCP review tool for consensus-based hallucination defense before shipping. | |
| ProxyPin MCP Server elonjask/proxypin-mcp Exposes ProxyPin's local network capture history to MCP-capable clients for searching, analyzing, and detailing captured HTTP traffic. It enables users to perform API structure analysis and generate client-side code directly from captured r | |
| Reqable MCP Server elonjask/reqable-mcp Exposes local Reqable network capture traffic to MCP clients for real-time monitoring and analysis of HTTP requests. It enables developers to query, search, and generate code from captured traffic stored locally within a private SQLite data | |
| diepi-mcp elonmaskhair-prog/dsh-plugin-diepi MCP server for natural-language daily stock/ETF strategy backtesting. It provides constrained tools for strategy specification, data validation, queue-based backtests, and verifiable result artifacts. | |
| Agent MCP BrightData elonmsk/mcp An intelligent agent using the Model Context Protocol to iteratively explore and analyze websites in a structured way, with built-in duplicate protection and conversational interface. | |
| Bilas.id MCP Server elony-7/bilas.id-mcp-server Enables AI agents to integrate with the bilas.id POS and laundry management platform for authentication, financial reporting, expense tracking, invoice lookup, production monitoring, IoT machine status, and outlet profile management. | |
| Image Context Runtime elopez854/codex-image-context-runtime Enables Codex to run context-bounded image generation and inspection as durable local jobs, returning bounded text handoffs, hashes, relative references, and Job IDs while keeping provider-returned media bytes outside the MCP boundary. | |
| metals-mcp eloquentix/metals-mcp MCP wrapper for Metals (Scala language server) that adds file editing and refactoring tools such as rename-symbol, add-import, and remove-unused-imports. | |
| SEAO procurement-intelligence MCP server elouansalaun/seao_mcp A read-only Model Context Protocol server that lets an LLM analyst interrogate Quebec's SEAO public-procurement open data (security-services subset) in plain language. | |
| SystemManager elouardyabderrahim/mcp Provides system-specific metadata through a tool that returns data for a given category. | |
| Phosphene elowenyu/phosphene Phosphene is an MCP server that enables AI to create and manage daily, challenge, and surprise tasks for human-AI interactions, while users complete them through a web interface to earn points, build streaks, unlock achievements, and redeem | |
| six-hats elpabloultron/six-hats Enables AI hosts to run structured multi-agent code review, architectural debate, adversarial auditing, and quick technical analysis through six parallel cognitive modes, returning unified diffs and actionable guidance. | |
| ai-papers-mcp elpaca/ai_papers_helper Enables searching and reading of AI/ML papers from conference proceedings and arxiv, with tools for full-text search, table of contents, and content grep. | |
| ScribblesLM elphamale/scribbleslm A self-hosted, notebook-scoped RAG pipeline with contextual retrieval, delivered as an MCP server. Enables ingestion of documents into named notebooks and semantic search returning raw ranked chunks. | |
| thunderbird-mcp elphiene/thunderbird-mcp A read-only MCP server that lets Claude read and search emails from Thunderbird accounts and access contacts, working directly with profile files. | |
| mcp-remote-py elphinsnow/mcp-remote-py A minimal Python-based proxy that bridges local MCP STDIO clients with remote MCP SSE servers. It enables bidirectional JSON-RPC message passing between standard command-line tools and web-based remote endpoints. | |
| Warframe Market MCP elpideus/warframe-market-mcp Enables searching Warframe items, viewing price history, and managing buy/sell orders through the Warframe Market API. | |
| mcpvault elraian/mcpvault Local, encrypted credential vault for AI agents that enables secure multi-account management across services like Supabase, GitHub, Vercel, and Stripe, allowing seamless account switching without restarting the chat client. | |
| brickbuilder-mcp elrashomacuin24/brickbuilder-mcp Enables Claude to design LEGO models brick by brick, typically from a reference photo, check that they hold together, and export them as LDraw (.ldr) files that Mecabricks and BrickLink Studio open directly. Models autosave for later editin | |
| chainlink-sentinel elromevedelelyon/chainlink-sentinel MCP server for Chainlink ecosystem monitoring with 6 tools: price feed tracking, VRF monitoring, automation status, CCIP tracking, and staking analytics. MIT licensed. | |
| claw-mcp-toolkit elromevedelelyon/claw-mcp-toolkit All-in-one MCP toolkit with 29 tools across 5 modules: crypto prices, web utilities, social media, finance tracking, and productivity. MIT licensed. | |
| revenue-mcp elromevedelelyon/revenue-mcp MCP server for tracking revenue opportunities including bounties, grants, hackathons, and freelance gigs with automatic deadline monitoring. 11 tools, MIT licensed. | |
| hermes-mail-gateway elroscaojr/hermes-mail-gateway Provides MCP-based email access for Gmail, Zoho Mail, and generic IMAP/SMTP accounts, with durable SQLite outbox, idempotent operations, and attachment handling. | |
| UI Toolkit MCP Server elsahafy/ui-toolkit-mcp Comprehensive MCP server for end-to-end UI development, offering tools to generate components, manage design tokens, audit accessibility, autofix issues, inspect live pages, compare screenshots, and more across multiple frameworks. | |
| AWS FinOps MCP Server elsahwang47/aws-finops-mcp-server Enables users to query AWS cost and usage data, audit for wasted resources like idle EC2 instances and unattached volumes, and check budget status using natural language across multiple profiles and regions. It runs locally against existing | |
| puffer-feed elsalvatore-sys/puffer-feed Enables logging progress updates to ThePuffer build tracker via a single tool, with safe concurrent writes. | |
| FVWM3 Window Manager elsanchez/mcp-server-fvwm3 Enables interaction with the FVWM3 window manager for configuration generation, window management, and debugging. Provides access to config files, runtime state, and control tools for managing desktops, monitors, and tiling operations. | |
| Gitingest-MCP elsapelletier/gitingest-mcp Enables MCP clients to extract GitHub repository summaries, project directory structures, and file contents for quick inspection and use in tools like Claude Desktop, Cline, and Cursor. | |
| Ollama MCP Server elsapelletier/ollama-mcp Enables MCP-compatible clients to interact with local and cloud Ollama models by exposing Ollama SDK functionality as tools for model management, text generation, chat, embeddings, and web search/fetch. | |
| AgentQL MCP Server elsapowell/agentql-mcp Enables users to extract structured data from specified web pages by providing a URL and a prompt describing the desired fields. | |
| Charlotte elsarodrigues68331/charlotte Enables AI agents to navigate and interact with web pages through a typed, structured representation — returning a compact page orientation on arrival, targeted element queries on demand, and full detail only when requested instead of raw a | |
| elsba3ei Webhook MCP Server elsba3ei/elsba3ei-webhook-mcp A high-performance local and public webhook inspector for testing SSRF, APIs, and out-of-band interactions with Cloudflare Quick Tunnel, dynamic mocks, and callback polling for AI agents. | |
| pcb-ai-agent elser17/pcb-ai-agent Provides read-only MCP tools for parsing KiCad netlists and schematics, running evidence-based audits, and generating deterministic sizing and BOMs. | |
| plc-ai-agent elser17/plc-ai-agent Exposes read-only tools for OPC UA PLC tag monitoring and diagnostics, and enables template-driven, validated IEC 61131-3 SCL code generation with a mandatory human review gate before download. | |
| Supabase MCP Server elsheppo/chumbo Exposes your application's resources and tools as an MCP server using Supabase Auth, Postgres, and Row Level Security, allowing authorized users to connect via compatible MCP clients. | |
| Shopify MCP Manager elsi06/shopify-mcp-manager Enables AI assistants like Cursor or Claude Desktop to fully manage a Shopify store using the Model Context Protocol, with tools for products, orders, customers, inventory, discounts, and analytics. | |
| TinyDB MCP Server elsrjuez/tinydb-emcipi Provides long-term memory for chatbots through a TinyDB-backed MCP server. Enables storing, searching, and managing JSON records with schema validation without requiring external databases. | |
| taskmarket-mcp eltociear/taskmarket-mcp MCP server exposing TaskMarket's public, read-only discovery tools so agents can browse and inspect funded onchain tasks on Base without a wallet. | |
| bookings-mcp eltonc369/bookings-mcp Enables AI agents to browse customers, bookings, and availability while any booking creation or cancellation stays gated behind a human-approved, single-use token cryptographically bound to the exact arguments. Runs over stdio or Streamable |
47,751–47,800 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.