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 |
|---|---|
| Remote MCP Server Authless carbon1985/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling tools to be used via SSE endpoint from AI Playground or Claude Desktop. | |
| carbon-cashmere-mcp carboncashmere/carbon-cashmere-mcp Crypto intelligence MCP: 104 tools for market data, ML signals, on-chain analytics, derivatives, and Bittensor subnets. Pay-per-call via x402 USDC on Base/Solana/Algorand/Stellar or $9.99/mo API key. | |
| TailwindCSS MCP Server carbonodev/tailwindcss-mcp-server Provides comprehensive tools for TailwindCSS development including utility class retrieval, CSS-to-Tailwind conversion, and color palette generation. It enables AI assistants to search documentation, generate component templates, and provid | |
| carbonstop-mcp carbonstop-hub/carbonstop-mcp MCP server enabling AI assistants to automatically perform carbon footprint modeling, product queries, and emission analysis via the Carbonstop Cloud API. | |
| carbonstop-mcp carbonstop-hub/carbonstop-mcp2 Enables AI assistants to automatically call Carbonstop Cloud API for carbon footprint modeling, product query, and emission analysis through natural language. | |
| Google Tag Manager MCP Server carc96/google-tag-manager-mcp Enables AI agents to manage Google Tag Manager accounts, containers, workspaces, tags, triggers, variables, and versions via the Tag Manager API v2. | |
| cardano-debug-mcp cardananium/cardano-debug-mcp Enables an AI assistant to inspect, validate and step-debug Cardano transactions and Plutus scripts, including finding failing redeemers, explaining ledger/CBOR/CDDL errors, decompiling UPLC, and opening highlighted problems in cquisitor or | |
| polymarket-gateway-core cardanobuybot/polymarket-gateway-core MCP server enabling AI agents to place bets on Polymarket using CLOB v2 with x402 payment and auto-setup. | |
| ExamPrepAgent cardea-mcp/examprepagent An MCP server that provides tools to search for study questions and answers from a knowledge base, enabling exam preparation through random questions and guided learning. | |
| Rust Coder cardea-mcp/rustcoder Enables AI agents to generate, compile, and fix Rust projects from natural language descriptions using LLMs and the Rust compiler. | |
| Prompt Book Server cardinalblue/prompt-book-mcp-server Manages AI prompts stored in Notion databases, enabling search, retrieval, and management across multiple prompt collections. | |
| Cardlake MCP Server cardleforall/cardlakeforall Exposes every card type and feed action — reminders, learnings, work items, bookmarks, snooze, pin, favorite — to MCP-compatible AI assistants, so they can read and write a self-hosted personal feed through chat. Turns requests like "remind | |
| @cardmagic/notes cardmagic/notes CLI and MCP server to search and browse Apple Notes with fuzzy matching, full-text search, and PDF text extraction. | |
| reminders cardmagic/reminders Enables fuzzy search, creation, and management of Apple Reminders via CLI or MCP tools. | |
| slack-messages cardmagic/slack-messages Enables fuzzy searching and browsing of Slack messages, users, and channels via CLI or MCP server integration. | |
| pricewise-mcp cardohso/pricewise-mcp Enables MCP clients to compute Portuguese vehicle taxes (ISV and IUC) and to estimate used-car price ranges from structured inputs. Every tax answer returns legal sources, explicit assumptions and a not-tax-advice disclaimer, while price es | |
| Hegelion cardoso42532/hegelion Enables LLMs to perform dialectical reasoning through thesis, antithesis, and synthesis, and to run player-coach autocoding loops for independently verified code implementation via MCP-enabled editors. | |
| PlayCanvas Editor MCP Server cardoso56/editor-mcp-server Enables AI agents to automate the PlayCanvas Editor through a built-in MCP client, with no browser extension needed. Provides tools for entities, scripts, assets, scenes, templates, animation, builds, store imports, viewport and editor cont | |
| mcp-shodan cardoso6097/mcp-shodan Enables AI agents to query the Shodan API and Shodan CVEDB for host reconnaissance, device search, DNS lookups, and CVE/CPE vulnerability intelligence through MCP tools. | |
| Project OS for Codex MCP Server cardoso90405/project-os-for-codex Enables AI agents to retrieve Git-backed project context—kickoff cards, acceptance criteria, handoffs, progress, and next actions—and to append validated, audited progress events under scoped credentials. | |
| Kommo MCP Server cardosolucass96/kommo-mcp-server Enables integration with Kommo CRM to manage leads, add notes and tasks, update custom fields, and list pipelines. Supports multi-tenant authentication and includes an approval system for bulk operations. | |
| Office AI Blueprint MCP Server cardozoesaggioro/office-ai-blueprint A connector that surfaces ~50 tools from 10+ integrated business systems (CRM, finance, support) via MCP, enabling an AI assistant to securely query and operate on correlated office data. | |
| CardsNearby MCP Server cardsnearby/cardsnearby-mcp Enables AI agents to search live directory data for local US card shops and upcoming card shows by coordinates or city/state, returning distance-sorted results with addresses, games, services, ratings, and dates. It also reports which US st | |
| appflowy-mcp careemer/appflowy-mcp A self-hosted, token-scoped Model Context Protocol server for AppFlowy. It gives AI agents tools to read and edit your AppFlowy workspaces while bounding each client to exactly the pages you allow via per-token tree-shaped scopes. | |
| @career-now/mcp career-now/mcp Enables AI agents to search and explore a large database of tech job listings with filtering options. | |
| shell-session-mcp carefuldeveloper/shell-session-mcp Provides persistent interactive shell sessions via pseudo-terminals for MCP agents, enabling bidirectional communication, incremental reads, and stateful command execution across steps. | |
| chatgpt-image-mcp carellice/chatgpt-image-mcp Enables Claude and other MCP clients to generate new images and edit existing ones through the locally installed ChatGPT/Codex app without an API key, returning saved file paths and inline previews so results can be inspected and iterated o | |
| ai-care-agent-mcp caresolace/ai-care-agent-mcp MCP server for headless care coordination, providing tools for case-aware provider search powered by ai-carematch. | |
| tsforge-mcp caresotin/tsforge-mcp A zero-dependency MCP server exposing 15 timestamp tools that LLMs compute unreliably, including cron edge cases, the Excel 1900 leap-year bug, ISO-8601 duration arithmetic, multi-dialect SQL timestamp generation, business-day counting, and | |
| InterSystems IRIS MCP Server caretdev/mcp-server-iris Execute SQL Query on InterSystems IRIS
Do some monitoring and manipulations with Interoperability | |
| Discord MCP Server careylzh/discord-mcp-server Enables LLMs to send and read messages in Discord channels through the Discord API, with server and channel discovery. | |
| speak careyscott/speak Lets Claude convert its replies into natural spoken scripts and play them with pause, resume, and rewind controls, plus voice and engine selection. | |
| luffy-video cargod/luffy-video-download-helper Enables local agents to discover and download videos from current browser pages, manage download tasks, and retrieve progress and results via MCP. | |
| bolsa-de-carga-mcp cargoffer/bolsa_de_carga-mcp Freight marketplace MCP server for European road logistics. Search and manage freight loads, post truck capacity, create auctions, manage deliveries and drivers through the Cargoffer Bolsa de Carga API. Connect your AI agent to the freight | |
| ecmr-mcp cargoffer/ecmr-mcp MCP server for electronic consignment notes (eCMR). Create, sign, manage, and track electronic transport documents with QR codes, PDF generation, and digital signatures through the Cargoffer ECMR API. Designed for AI agents like Claude Desk | |
| Tolls MCP Server cargoffer/tolls-mcp-server Calculate toll costs, list operators, and get tariff data across Spain, Portugal, and France through an LLM assistant. | |
| transcend-mcp-server cargoffer/transcend-mcp-server AI-powered route optimization MCP server for heavy vehicles and logistics. Calculate truck-optimized routes, predict traffic congestion with LSTM neural networks, compute toll costs, fuel costs and CO2 emissions, find truck stops and check | |
| @cargoffer/zbe-mcp cargoffer/zbe-mcp-server MCP server for checking vehicle routes against Low Emission Zones (ZBE/LEZ) in Spain and Portugal. | |
| Trello MCP Server cargom98/gm-trello-mcp Provides programmatic access to Trello's API to manage boards, lists, cards, and organizations via MCP. | |
| Pythia caribeedu/pythia Serves AI clients on demand with atomic, provenance-tracked claims about your people, teams, systems and decisions, exposing search, open, timeline, correct and define tools so assistants can pull what is currently true rather than stale do | |
| brain caricalia/mcp-brain Provides Claude with shared, durable memory across clients, backed by Supabase Postgres and pgvector. It lets agents save decisions, preferences, and project context, then recall them later with project-scoped visibility and semantic or tex | |
| Cariot MCP Server cariotinc/cariot-mcp-server Enables querying Cariot APIs for fleet management data, including alcohol checks, daily reports, drivers, vehicles, and realtime snapshots, with utility for generating chart configurations. | |
| Code Review Workflow MCP Server carl-jcc/code-review-workflow Enables automated code review by reading code files, checking for style issues like console.log and TODOs, and generating formatted reports. | |
| Laya MCP carl0s/laya-mcp-server Enables MCP clients to ask typed questions about text or JSON and receive structured answers with probabilities, and also exposes a REST endpoint for non-MCP tools. | |
| quota-mcp carl0sfelipe/quota-mcp Tracks AI subscription quota (5h/day/week windows) and recommends which provider an agent should use, using local-first data and observed rate-limit events to veto providers. | |
| Pentest MCP carl7352/pentest-mcp Enables professional penetration testers to run reconnaissance, exploitation, brute-force, traffic capture, and reporting workflows through stdio, HTTP, and SSE transports with auth and engagement record management. | |
| MediaWiki MCP Server carl93366/mediawiki-mcp-server Enables LLM clients to read, search, create, edit, move, protect, and delete pages, upload files, and query wiki data across any number of configured wikis. It supports per-wiki defaults, OAuth authentication, and extension packs for Semant | |
| identity-mcp carlademarchiv/identity-mcp Institutional MCP server that centralizes access to identity, institutional profiles, and basic person data. Currently a bootstrap with no business logic or tools implemented. | |
| Glance carlaktas/glance It gives Claude Code a real browser so it can navigate, interact with, screenshot, and test web applications from the terminal. It also supports assertions, session recording, visual regression checks, and network/console monitoring. | |
| wikicore carlaost/wikicore Enables AI assistants to build and maintain a shared, git-backed Markdown wiki: they search, file, update and link notes with YAML frontmatter, keep verbatim sources, and optionally read code repos, so knowledge one assistant records is ava |
36,801–36,850 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.