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 |
|---|---|
| DocGraph carrilloapps/docgraph Universal documentation knowledge-graph MCP server with hybrid full-text + vector search. Indexes local files and remote sources from Notion, Jira, Obsidian, Linear, GitHub, and Confluence into a single SQLite knowledge graph, exposing it t | |
| browser-relay carrothu-secret-workstation/mcp-browser-relay It enables a single stdio MCP endpoint to multiplex calls by session_id to dedicated, isolated @playwright/mcp child processes, giving each session or subagent its own separate Chrome browser with isolated profiles and cookies. | |
| Windchill MCP Server cars-10/windchill-mcp-server Comprehensive MCP server for PTC Windchill PLM, providing 64+ tools across 7 agents for part, document, change, workflow, project, data admin, and server management, with dynamic server switching. | |
| DigiLIB cars3/digilib-mcp Enables any MCP-capable AI agent to search academic papers and books across six free, keyless sources concurrently, then export a cited literature review as LaTeX source with APA, Chicago, or MLA citations. Requires no API keys or paid serv | |
| Intake-Triage carsonlabs/intake-triage Classify raw text into structured triage objects with intent, urgency, category, and sentiment. Zero-config MCP tool for support intake, lead routing, and ticket automation | |
| LeadEnrich MCP Server carsonlabs/leadenrich-mcp Waterfall lead enrichment for AI agents. Cascades through Apollo, Clearbit, and Hunter to build the most complete lead profile in a single call. | |
| SteadyFetch carsonlabs/steadyfetch Provides AI agents with reliable web fetching capabilities, handling retries, caching, and anti-bot bypass automatically. | |
| MCPCloud carsor007/mcpcloud A self-hosted MCP gateway that lets you write Python functions and register them as skills to be used as tools by any MCP-compatible client like Claude Desktop or Claude API. | |
| OpenAlex MCP carsten-streb/openalex-mcp An MCP server for searching and exploring OpenAlex's index of 250M+ scholarly works, authors, institutions, journals, funders, and grants through Claude. | |
| MetaTrader MCP Server carsti/metatrader-mcp-server Enables AI assistants to interact with the MetaTrader 5 trading platform through natural language, including retrieving market data and account information and placing, modifying, or closing orders. | |
| pyramid-mcp cartaorobbin/pyramid-mcp Exposes Pyramid web application endpoints as Model Context Protocol (MCP) tools, enabling AI assistants to interact with Pyramid apps via natural language. | |
| rfd-mcp carteakey/rfd-mcp MCP server for searching and monitoring RedFlagDeals deals. Provides tools to search deals, get deal details, and set up monitors for new deals. | |
| MCP AI Docs cartek99/mcp-ai-docs An MCP server that provides indexed, searchable access to Anthropic Claude and Google Gemini documentation, with full-text search, page fetching, and section listing capabilities. | |
| Cartena MCP Server cartena-tecnologia/cartena-mcp Enables AI clients like Claude to interact with Cartena tools via MCP, supporting remote OAuth or local stdio authentication. | |
| geo-audit-mcp carter-wzq/geo-audit-mcp MCP server for GEO site audits, checking 31 signals across 6 pillars and returning a score, breakdowns, and actionable fix prompts. | |
| mcp-server-starrocks carter934/mcp-server-starrocks It enables AI assistants to interact with StarRocks databases by running SQL queries, exploring schemas and data, accessing system information, and generating Plotly charts from query results. | |
| MCP Tree Explorer carterlasalle/directory_structure_mcp A lightweight MCP tool for directory tree visualization in Cursor, with smart filtering and customizable ignore/keep patterns. | |
| DevEnvInfoServer carterlasalle/system_information_mcp An MCP server that provides detailed information about your development environment to the Cursor code editor, enabling more context-aware assistance. | |
| Time MCP Server carterpape/pape-mcp-server-time Provides current time information and timezone conversion capabilities using IANA timezone names and automatic system detection. It enables LLMs to fetch current times across different regions and convert specific times between timezones. | |
| cartcut-mcp cartesiancs/cartcut Edit video in the CartCut desktop editor: cuts from a transcript, captions, motion, effects. | |
| engram-mcp cartisien/engram-mcp Persistent semantic memory for AI agents. SQLite-backed, local-first, zero config. Semantic search via Ollama embeddings with keyword fallback. Tools: remember, recall, history, forget, stats. | |
| mcp-server-codegraph cartographai/mcp-server-codegraph Generates and queries a graph representation of a codebase to identify entities and their relationships, such as function calls and inheritance. It supports multiple languages including Python, JavaScript, and Rust to help users navigate an | |
| Cartwheel MCP cartwhl/cartwheel-mcp Enables AI assistants to generate 3D character animations from text, search and retrieve motions, and inspect characters and scenes via Cartwheel's public API, with downloadable BVH files for Blender workflows. | |
| vscode-notebook-mcp caryan/vscode-notebook-mcp Exposes VSCode Jupyter notebooks to MCP-compatible AI agents, enabling them to read, edit, and run cells against the same kernel. | |
| Outlook MCP (inworkgroup) carycracker/outlook-mcp-inworkgroup Enables AI assistants to read, search, and manage Outlook/Office 365 work mailboxes and calendars, and create reply drafts without sending by default. | |
| delphi-mcp carywang1234/delphi-mcp A read-only MCP server that lets an AI agent browse and read the Chief Delphi robotics forum — scoping categories, finding and reading threads, and vetting user profiles — using only anonymous public endpoints, with no account, API key, or | |
| mcp-monodraw caryyon/mcp-monodraw Enables creation, editing, and export of ASCII art diagrams using Monodraw on macOS, with tools for generating boxes, flowcharts, tables, trees, and sequence diagrams. | |
| cc-as-subagent cas-t1glione/cc-as-subagent Exposes the local Claude Code CLI as a subagent for Codex, enabling background review and implementation jobs with two fixed permission tiers. | |
| qoder-as-subagent cas-t1glione/qodercli-as-subagent Enables Codex to delegate review and implementation tasks to the local Qoder CN CLI as background jobs, with two permission tiers and polling-based status updates. | |
| Casa CoinGlass MCP casa972/casa-coinglass-mcp Enables Claude to access real-time CoinGlass market data for Binance and MEXC, including open interest, funding rates, CVD/taker volume, long-short ratios, and liquidations. | |
| zima-mcp casareanderson/zima-mcp Lets an AI assistant check on a ZimaBlade or any Docker host over plain SSH (load, top processes, container stats, logs, disk) and restart only allowlisted containers. Nothing to install on the box. | |
| CNBC News Scrape MCP cascas2010/cnbc-news-scrape-mcp An MCP server for scraping and retrieving CNBC news content. | |
| WhatsApp MCP Server cascodigital/whatsapp-mcp-server Enables LLM clients to read and search your own WhatsApp messages stored in a local SQLite database, captured live via a linked device. | |
| Casdoor MCP Server casdoor/casdoor Official MCP server built into Casdoor, the open-source identity and access management (IAM) and single sign-on (SSO) platform. It exposes Casdoor's users and applications as MCP tools over a JSON-RPC endpoint at /api/mcp, with per-tool aut | |
| caselegis-mcp caselegis/caselegis-mcp Enables searching, retrieving, and checking citation status of California legal opinions via the Caselegis API. | |
| Switchr MCP Server caseman72/switchr-mcp Enables monitoring and control of SwitchBot devices (temperature sensors, plugs, bots) via Claude Desktop or Home Assistant. | |
| Wyzer MCP Server caseman72/wyzer-mcp MCP server for controlling Wyze smart home devices (plugs, switches, thermostats, air purifiers) via Claude Desktop or Home Assistant. | |
| FHIR Progressive Discovery MCP Server casemark/fhir-mcp Enables progressive discovery and management of FHIR healthcare resources through intent-based grouping, with support for creating/validating resources, converting between formats, and transforming medical PDFs to FHIR DocumentReference res | |
| Motion MCP Server casenterprises/motion-mcp-server Enables AI assistants to manage Motion tasks, projects, workspaces, schedules, comments, custom fields, and recurring tasks through natural-language conversation via the Model Context Protocol. | |
| verifactu-qr caseroclaw/verifactu-qr Enables AI agents to generate and validate Spanish VeriFactu invoice QR URLs and tax identifiers, with official AEAT error codes and JSON consultation URL support. | |
| semantic-image-search-mcp casey-hemingway/semantic-image-search-mcp Enables natural language search of local photo archives using AI-powered semantic understanding, with integration into Claude Desktop via the Model Context Protocol. | |
| rct2-agent caseyjohnsonwv/rct2-agent Enables an agent to sidecar-manage an OpenRCT2 park while you play: reading park state, adjusting prices, staff, marketing, loans, taking screenshots, and controlling game time, with management-only actions that never build. | |
| mcp-mockuuups caseyro/mcp-mockuuups Enables searching thousands of device and print mockups and rendering screenshots or uploaded images into them via the Mockuuups Studio API. | |
| Readwise MCP HTTP Server caseyro/mcp-readwise Enables searching and accessing Readwise highlights and documents through HTTP endpoints using the Model Context Protocol. Provides vector and full-text search capabilities with streaming responses for retrieving reading highlights and note | |
| mcp-timely caseyro/mcp-timely A read-only MCP server for querying Timely time tracking data, providing tools for project overviews, time spent summaries, and work log entries. | |
| Bullhorn MCP Agent caseytts/bullhorn-mcp-agent Enables MCP-compatible AI clients to securely search and retrieve Bullhorn jobs, candidates, and placements, manage candidate files and resumes, and run generic entity searches/queries without exposing credentials. | |
| Raindrop MCP Server cash/raindrop_mcp_server An MCP server that exposes Raindrop.io's bookmark management API as tools for AI assistants, enabling collection, bookmark, and tag operations. | |
| Recall cashcon57/recall A self-hosted MCP memory server with hybrid semantic and keyword search, providing persistent memory for AI coding assistants like Claude Code, Cursor, and Windsurf. | |
| BCH MCP Server cashlabs-dev/bch-mcp A comprehensive Bitcoin Cash (BCH) MCP server that enables wallet management, transaction utilities, and full CashToken operations including genesis, minting, and burning. It also provides advanced features such as escrow contracts, smart c | |
| shuiyuan-mcp-lite cashrel894/shuiyuan-mcp-lite Enables read-only access to the SJTU Shuiyuan community, allowing users to search topics, read posts and user profiles, and list categories and tags through MCP. |
37,001–37,050 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.