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 |
|---|---|
| Xyntherium Verify MCP augustbrookz/xyntherium-verify-mcp Enables AI agents to check a drafted answer against supplied sources or a document before stating or acting on it, returning claim-level support status, contradictions, omissions, and a verdict. | |
| Claude Advanced Memory Engine augustianrajesh/claude-save-token Provides structured local memory for Claude Desktop, reducing token usage by over 95% through intelligent retrieval and layered storage. | |
| remote-mcp-server-authless augustin-gorge/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling tools to be used from Cloudflare AI Playground or Claude Desktop via mcp-remote proxy. | |
| design-mcp augustinezuka/design_mcp MCP server for design decisions during a build, providing live UI/animation library docs (via llms.txt) and a curated knowledge base of UX laws and UI conventions. It enables agents to look up real component APIs and apply design best pract | |
| free-web-ai-worker augustlies/free-web-ai-worker Enables AI agents to delegate simple text subtasks such as summarising, translating, classifying, extracting, and reformatting to free web AIs through the user's own Edge/Chrome browser, returning only plain-text answers to save the main mo | |
| MCP Gateway Prototype augusto-realist/artiva-mcp-gateway-prototype A local MCP server for BigQuery that integrates Okta authentication and workload identity federation, enabling natural language queries and dataset exploration. | |
| Apple Reminders MCP augustofranke/apple-reminders-mcp Enables model-controlled read/write access to macOS Reminders, including lists, reminders, dates, repeats, early reminders, priority, flags, notes, and URLs. | |
| GitHub MCP Server augustolamim/_mcp Enables AI models to create and manage GitHub repositories, branches, and files directly through a personal access token. This Docker-friendly server facilitates repository administration and content updates without requiring a local clone. | |
| project-tasks-mcp augustooliveira1993/project-tasks-mcp Enables managing projects, features, tasks, dependencies, executions, and human review through a Streamable HTTP endpoint, along with persistent inter-agent cooperation via task messaging and event subscriptions. It also supports administra | |
| Wan 3.0 Prime API MCP Server augustusrenfield6/wan-3-0-prime-api Exposes four narrow tools for submitting text, frame, and reference video-generation jobs and for looking up job status through the Argolink Wan 3.0 Prime API, reading credentials from the environment. | |
| SkyBrain augwalts/skybrain Provides a shared MCP memory layer for AI clients, backed by Cloudflare Workers and D1, enabling personal Markdown notes management. | |
| AWS FinOps MCP Server augzbhvccu/aws-finops-mcp-server Enables AI assistants to analyze AWS cloud costs, audit for waste such as idle EC2 instances and unattached volumes, and check budget status through natural language. Runs locally against existing AWS CLI profiles, allowing read-only querie | |
| Blockland MCP auios/blocklandmcp Enables an MCP client to connect to a running Blockland client to execute TorqueScript, inspect player state, control character movement and actions, and capture screenshots. | |
| FlyMemory aujurd22/dsh-flymemory Enables AI agents to build and query a private, on-device long-term memory through 15 MCP tools for storing decisions, searching past context, tracking entity state, merging duplicates, and resolving conflicts. Automatic hooks capture each | |
| Google Calendar MCP Server aukay13/google-calendar-mcp-server Exposes Google Calendar as a tool for Claude Desktop, allowing natural-language queries about your schedule by listing upcoming events via the Google Calendar API. | |
| WhatsApp MCP Server (TypeScript) aukik/whatsapp-mcp-ts Enables AI agents to interact with your personal WhatsApp account to search messages, list chats, and send messages. It stores all authentication and message data locally using SQLite for privacy and direct multi-device API connection. | |
| aum-mcp-server aumsuthar/aum-mcp-server A personal MCP server split into focused servers — each loads only the tools it needs, keeping Claude's context lean. | |
| obsidian-mcp-server aumsuthar/obsidian-mcp-server Gives Claude direct access to an Obsidian vault, enabling read, write, search, and automatic git sync for cross-device use. | |
| Remote MCP Server on Cloudflare aungkoko-coding/remote-mcp-server A template for deploying a remote Model Context Protocol (MCP) server on Cloudflare Workers with OAuth authentication and SSE transport. It enables LLM clients to securely access and execute tools hosted in a serverless environment. | |
| UpGrad LXP MCP Server aunkidwai/lxp_firefox_mcp Automates navigation of UpGrad's learning platform using Playwright to extract class transcripts and download resources. | |
| Hierarchical Skills For AI MCP Server aunxfb/hierarchicalskillsforai A hierarchical MCP server for managing skill definitions with a browsable tree structure and full-text search. It allows AI agents to efficiently discover and use skills without consuming context tokens. | |
| Aura Courier MCP auraajenticai/aura-courier-mcp A unified MCP connector for Bangladeshi couriers, enabling parcel booking and tracking across multiple services through a single interface. | |
| Aura Courier MCP auraajenticai/courier-mcp-site Aura Courier MCP | |
| aura aurafhe-official/mcp Enables AI agents to run private computations on encrypted data using fully homomorphic encryption, supporting operations such as addition, mean, comparison, concatenation, and scientific functions without exposing plaintext inputs. | |
| AI Chat MCP auraflame-ywt/dsh-ai-chat-mcp Exposes a local DeepSeek Harness instance to external MCP clients over Streamable HTTP, legacy HTTP+SSE, or a stdio bridge. Enables creating sessions, running multi-turn conversations, reading and full-text searching history, cancelling run | |
| AuraImage MCP Server auraimage/mcp-server Enables AI agents to audit images for LCP savings, migrate assets to AuraImage CDN, generate alt text, create responsive tags, and preview smart crops directly from the editor. | |
| garmin-mcp aural-psynapse/garmin-mcp Enables users to access and analyze Garmin Connect data through natural language, supporting multi-user setups, SQLite-backed history, and optional remote access via Cloudflare Tunnel. | |
| Paperclip MCP server auralab-dev/paperclip-mcp Enables AI agents to interact with issue, comment, document, and agent workflows through a simplified HTTP API, returning compact Markdown or file-based snapshots. | |
| Neleus MCP auralshin/neleus-mcp Enables interaction with Hyperliquid markets for technical analysis, order book data retrieval, and cryptocurrency trading. Supports read-only market access without credentials and authenticated trading operations via private key configurat | |
| Feather MCP Server auram-stone/feather-mcp-server Enables AI agents to automate Facebook lead generation and CRM tasks such as searching leads, sending friend requests, managing contacts, broadcasting messages, and tracking growth metrics. | |
| klone-mcp aurasoph/hyak-mcp A minimal MCP server for UW Hyak (klone) that exposes tools to run shell commands and write files remotely, along with documentation resources for klone-specific utilities. | |
| Global Papers MCP auraweon7-ship-it/global-papers-mcp Unified academic paper search MCP server integrating OpenAlex, Semantic Scholar, CrossRef, and arXiv APIs, enabling Claude to search and analyze over 500 million scholarly papers. | |
| .KCI MCP Server (한국학술지인용색인) auraweon7-ship-it/kci-mcp Enables Claude to search and analyze Korean academic papers using the Korea Citation Index (KCI) Open API. Supports paper search, detailed metadata retrieval, reference analysis, author and keyword searches, and citation index queries. | |
| PyBaMM MCP Server aurbanec/pybamm_mcp Enables LLM-powered IDEs to search PyBaMM documentation and source code, with tools for full-text search, reading doc pages, and browsing source files from a local clone. | |
| n8n MCP Server aurelienfagioli/n8n-mcp-aurelien A complete Model Context Protocol server that enables Claude to create, manage, and execute n8n workflows through conversational AI. | |
| prioritization aurelijusb/mcp-prioritization An MCP server that provides a drag-and-drop UI for prioritizing list items, allowing users to reorder items interactively and send the prioritized list back to the chat. It supports MCP Apps UI rendering and falls back to text instructions | |
| google-sheets-mcp aureliocecchi/mcp-google-sheets A local MCP server that lets AI assistants read and write Google Sheets directly with per-user OAuth, supporting tabs, ranges, rows, and filtered lookups. | |
| Engram aurelius86/engram Self-hosted, governed long-term memory and knowledge-graph server for AI agents with access control, hybrid retrieval, and typed graph linking. | |
| Savor Life MCP Server aurenshi/savor-life Enables AI agents to search restaurants, publish and maintain store data, submit verified freshness feedback, and query demand or updates through MCP tools. It provides both read-only and full administrative endpoints backed by open restaur | |
| Trader Journal MCP aureon-capital-ai/aureon-ai-trading-coach Provides AI-powered trading analytics and coaching by analyzing historical trades to identify strategies, emotional patterns, and behavioral mistakes via MCP tools. | |
| protonpass-mcp aurethedev/protonpass-mcp A Model Context Protocol (MCP) server for Proton Pass. It wraps the official pass-cli binary and exposes 14 tools so any MCP-compatible AI assistant (Claude Desktop, Claude Code, etc.) can manage your vaults, credentials, and secrets. | |
| Aurify MCP Gateway aurify-org/aurify-mcp An MCP server that lets AI agents manage Aurify financial data—wallets, transactions, budgets, investments, and profile—by translating MCP calls into the same REST API the web frontend uses. | |
| screens mcp aurigax-ai/screens Enables a computer-use agent to see and drive one isolated, sandboxed Linux desktop by exposing Anthropic's computer toolset actions alongside launching apps and listing windows, with screenshots scaled to a 1280-pixel longest side. It runs | |
| ActivityWatch MCP Server auriora/activitywatch-mcp Enables LLM agents to query and analyze ActivityWatch time tracking data, including window activity, web browsing, and category management with natural language time periods and automatic data aggregation. | |
| Kahuna aurite-ai/kai A persistent memory MCP server for AI copilots that automatically surfaces relevant context across sessions, projects, and teams, eliminating the need to repeat information. | |
| Total Recall auriti-labs/kiro-memory Persistent cross-session memory for AI coding assistants, automatically capturing and injecting context across sessions via MCP tools. | |
| data-quality-loop auron-lmh/data-quality-loop Enables autonomous data quality inspection and repair workflows. It scans DuckDB warehouses for anomalies, generates and verifies fixes in a dry-run copy, then applies them after validation, with full audit logging. | |
| Armor Crypto MCP aurora-smith-ts58tc/armor-crypto-mcp A single source for integrating AI Agents with the Crypto ecosystem, including wallet creation, swaps, transfers, and event-based trades like DCA and stop loss. | |
| Kromo Cargo aurora33labs/kromo-cargo Enables AI agents and counter staff to run inventory and fast sales for a single-branch physical store — products, stock movements (entries, sales, adjustments), reports, labels and imports — over the same database the app uses, exposed via | |
| 010 Editor MCP Bridge auroraaeon/010-editor-mcp Enables agents to perform bounded binary-file inspection, hashing, search, and diffing within configured roots, and to preview and apply expected-byte-validated patches that produce new output copies while preserving originals. It also read |
31,701–31,750 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.