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 |
|---|---|
| veyra-contacts aquariosan/veyra-contacts Contact manager for AI agents with company, tags, and full-text search. Reads are free, writes require Veyra commit mode. | |
| veyra-forms aquariosan/veyra-forms Form builder and response collector for AI agents. Reads are free, writes require Veyra commit mode. | |
| veyra-notes aquariosan/veyra-notes Note-taking MCP server for AI agents with tags and full-text search. Reads are free, writes require Veyra commit mode. | |
| veyra-snippets aquariosan/veyra-snippets Code snippet storage for AI agents with language tags and full-text search. Reads are free, writes require Veyra commit mode. | |
| veyra-tasks aquariosan/veyra-tasks Task manager for AI agents with projects, priorities, and status tracking. Reads are free, writes require Veyra commit mode. | |
| veyra-webhooks aquariosan/veyra-webhooks Outbound webhook sender for AI agents with delivery log. Reads are free, sends require Veyra commit mode. | |
| Actor-Critic Thinking MCP Server aquarius-wing/actor-critic-thinking-mcp Provides dual-perspective analysis through alternating actor (creator/performer) and critic (analyzer/evaluator) viewpoints, generating comprehensive performance evaluations with balanced, actionable feedback. | |
| Trivy aquasecurity/trivy-mcp Trivy plugin for starting an MCP server | |
| carpet-design-mcp aquibfaiyaz/carpet_mcp Enables Indian carpet exporters, manufacturers, and designers to generate AI design prompts, explore carpet styles and color palettes, and create Etsy SEO listings, bridging overseas market trends with local weaving specifications. | |
| railinfo-mcp aquibfaiyaz/railinfo-mcp Enables real-time Indian Railways information retrieval, including live train running status, station schedules, and upcoming arrivals/departures. | |
| poke-mcp aquibm/poke-mcp Enables users to turn their LLM client into a Pokédex by looking up Pokémon by name, including partial or misspelled names, and predicting battle outcomes between two Pokémon. | |
| Local Memory MCP aquietriver/synapse-mcp Persistent local semantic memory for MCP tools, enabling storing and searching notes by meaning using local embeddings and SQLite. | |
| TradingView MCP Jackson aquilestang/tradingview-agent-mcp Enables AI assistants and CLI tools to read and control a locally running TradingView Desktop app via Chrome DevTools Protocol, including morning briefs, chart navigation, indicator analysis, Pine Script development, alerts, replay practice | |
| dot-lit aquistbe/transport-lit Enables AI assistants to perform keyword searches across U.S. DOT grey literature and international transportation research reports from multiple repositories, using a local SQLite FTS5 index with optional full-text PDF retrieval. | |
| ar-agents ar-agents/ar-agents Agent Toolkit for Mercado Pago | |
| Notion Page Viewer ar-codelabs/mcp_notionmcp_webviewer Enables viewing and browsing Notion page content through a web interface with multiple display modes, supporting various block types including text, images, toggles, and child pages. | |
| codebase-rag ar-maan05/codebase-rag Enables LLM agents to efficiently understand and navigate a codebase by providing semantic search over symbols and a reference graph, replacing expensive grep/glob calls with structured tools like definition lookup, caller/callee queries, a | |
| Live Marketing Data MCP ar2our/live-marketing-data-mcp Connect AI assistants to live Meta Ads, GA4, and Google Search Console data. 100% local, credentials machine-locked and encrypted. Supports Claude Desktop, Cursor, Windsurf, Cline, and more. | |
| claude-codex-bridge ar36planet/claude-codex-bridge-public Bridges Claude Code and Codex TUI in real time, allowing them to share the same thread and send messages back and forth. | |
| Context Guardian ar5en1c/context-guardian MCP server that cuts cloud LLM costs 36-42% by indexing context locally and giving agents precision retrieval tools instead of raw context dumps. | |
| termmirror ar9av/termmirror Enables AI agents to drive real interactive terminal sessions—PTYs, TUIs, REPLs, SSH, even another agent's CLI—with a live web view where humans can watch and type in. | |
| Companion Animation Pipeline MCP Server arabianguy08/3d-model-to-animation-pipeline Enables AI clients to control background Blender jobs over stdio so they can inspect a 3D character or companion model, calibrate its anatomy and named bones, bake and export animation, and numerically verify the persisted GLB for playback | |
| docs-mcp-server arabold/docs-mcp-server A Model Context Protocol (MCP) server that scrapes, indexes, and searches documentation for third-party software libraries and packages, supporting versioning and hybrid search. | |
| modbus-copilot aradhsai/modbus-copilot Ask a Modbus device questions by tag name instead of register number. Provides read-only tools to list devices, search tags, and read values with provenance. | |
| QueryIO aradhyas8/queryio-mcp Enables coding agents to safely investigate PostgreSQL runtime state through bounded, read-oriented MCP tools for row-and-foreign-key neighborhood inspection, schema and statistics lookup, and table listing, with truncation, redaction, time | |
| notification-test arafatkatze/test-mcp Enables testing real-time MCP notifications that appear as VS Code popups, demonstrating standalone log messages. | |
| AgentGround Cross-Check Verifier arafel187/agent-ground Enables AI agents to cross-verify candidate claims against caller-supplied source texts, flagging hallucinations, numerical drift, entity mismatches, contradictions, and unverified assertions. It returns sentence-level verdicts with matched | |
| OpenAPI Contract MCP arag0rn/openapi-contract-mcp Enables coding agents to check requests against a live OpenAPI 3.x specification rather than guessing, by resolving endpoints from a docs anchor, operationId, path fragment or tag, revealing what each operation accepts and returns with $ref | |
| Lakeflow MCP Server arahimi-hims/lakeflow-mcp Enables AI agents to manage Databricks Lakeflow jobs by building and uploading Python wheels and triggering runs with specific arguments. It provides a structured way to orchestrate complex data experiments and monitor execution directly on | |
| My AskAI MCPs arainey2022/myaskai-mcps Provides read-only Model Context Protocol tools for My AskAI, enabling documentation search, filesystem queries, and pricing estimates. | |
| Vercel MCP Proxy araj3539/vercel-mcp-proxy Enables managing a Vercel account through MCP tools such as listing projects, viewing deployments and logs, and redeploying. Includes an OAuth layer so Gemini Spark can connect securely. | |
| SmartPark Central MCP Server araksyag/epam-ai-engineering-stage3 Records approved parking reservations to a secure text file via the Model Context Protocol, with token authentication and input sanitization. | |
| prestocks-pulse aralroca/prestocks-pulse Enables AI agents to research and trade tokenized pre-IPO stocks on Solana, including premium radar, PRE8 index, creation/redemption flows, split-aware Jupiter quotes, and basket building. | |
| Telegram MCP Bridge aralroca/telegram-bot-mcp Enables MCP agents to request human confirmation for actions via a Telegram bot. It uses a Vercel-hosted proxy and Redis to facilitate secure, real-time YES/NO approvals from a mobile device. | |
| coremodels-mcp-server aramai-schematica/coremodels-mcp-server CoreModels MCP Server provides 16 tools for AI agents to manage graph-based data models, enabling creation, querying, and manipulation of entities, relations, and observations within structured knowledge graphs. | |
| schematica-mcp-server aramai-schematica/schematica-mcp-server Schematica MCP Server provides 8 tools for AI agents to browse, search, and manage a curated library of reusable data model schemas, enabling standardized entity and relation type definitions for knowledge graphs. | |
| robinhood-chain-mcp arambarnett/robinhood-chain-mcp Enables agents to query live Robinhood Chain data including tokens, wallets, Chainlink feeds, heat scores, and tracking error on tokenized equities, all read-only without API keys. | |
| jev-browser-mcp aramirez51/jev-browser Enables LLM clients to carry out web automation goals by having code describe the current page while a Typesafe System One model decides which element, action, and value to use, with Playwright performing each step and reporting a done/bloc | |
| mcp-telepizza aramosf/mcp-telepizza Unofficial read-only MCP server for Telepizza.es that enables querying menu, prices, offers, stores, loyalty points, and order history using your own account. It cannot make purchases. | |
| yandex-music-mcp aramvr/yandex-music-mcp An MCP server that turns Yandex Music into tools an AI agent can call directly — search, queue, play, build playlists — with no browser involved. | |
| Sentia MCP Server arananet/sentia Enables assistants to query a fleet of sensor patches, read status and measurement time series, review alerts and network statistics, and simulate uplinks that return both the encoded payload and its decoded reading. | |
| Argos-MCP araneadev/argos Enables Claude Code to securely interact with PostgreSQL, MySQL, SQLite, and SQL Server databases, featuring read-only mode, query validation, SSH tunneling, and field redaction for production-safe data access. | |
| Chaos-MCP araneadev/chaos-mcp On-demand micro-mutation sandbox for AI test verification that maps weaknesses in unit tests by running isolated mutation testing via the Model Context Protocol. | |
| Knossos MCP araneadev/knossos Local-first MCP server that scans a repository once and answers architecture questions from an evidence-backed graph, enabling dependency analysis, impact analysis, and codebase exploration without re-reading the source tree. | |
| Momus-MCP araneadev/momus-mcp A local-first, deterministic, read-only MCP server that audits test suites for false-green tests, tautological assertions, and mock-contract drift, ensuring tests truly validate production code. It provides tools to detect test fidelity iss | |
| Nemesis-MCP araneadev/nemesis-mcp Checks mocks, stubs, and spies against current production code to detect stale or mismatched test doubles without running any tests. | |
| YouTube MCP Server Enhanced aranej/youtube-mcp-enhanced Enables AI language models to interact with YouTube content through the YouTube Data API, including retrieving video details, transcripts, channel information, playlists, and searching videos with enhanced responses that include direct URLs | |
| icici-mcp aranjan/icici-mcp Enables trading Indian stocks on ICICI Direct through natural conversation with any MCP-compatible AI assistant, featuring automated TOTP login and tools for portfolio monitoring, order placement, and market data. | |
| ai-shopping-list aranlucas/ai-shopping-mcp Enables AI models to manage Kroger/QFC shopping lists, search products, and plan meals via the Kroger API. | |
| pantry-pulse aranlucas/pantry-pulse Enables AI assistants to read current pantry inventory and low-stock shopping needs, export a shopping queue, and perform idempotent inventory adjustments and catalog link management through remote MCP tools. |
30,051–30,100 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.