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 |
|---|---|
| InstrMCP caidish/instrmcp MCP server for quantum device physics laboratory instrumentation control, enabling LLMs to interact with physics instruments and measurement systems through QCodes and JupyterLab. | |
| Bayze caijianxiong2007-prog/bayze-mcp Enables AI clients over MCP stdio to run local-first, auditable multi-model workflows that draft, require structured review, and revise outputs on demand, with BYOK credential handling and no telemetry. Exposes tools for listing workflows, | |
| Email-MCP caijianying/email-mcp An MCP server that enables AI assistants to send emails through SMTP protocol by providing server credentials, recipient information, subject, and message content. | |
| Confluence Node MCP Server caijohnny/confluence-node Enables AI assistants to create, update, delete, and search Confluence pages directly through natural language commands in Cursor, with support for space management and page history. | |
| @caikiji/mcp-search caikiji/mcp-search Privacy-respecting, self-hosted metasearch MCP server that aggregates results from multiple search engines and fetches page content as Markdown. | |
| mcp-ssh caikiji/mcp-ssh MCP server for SSH remote execution, file transfer, and file editing with automatic backup/trash and ~/.ssh/config integration. | |
| mcp-gitee caindez/mcp-gitee Full-featured MCP server exposing 200+ Gitee API v5 endpoints for repository, issue, pull request, user, enterprise, gist, and search management. | |
| vps-pilot cainiao1907/vps-pilot Enables external local AI agents to connect to VPS hosts, type into and read back from live SSH terminals, run commands, and trigger high-level plan-execute agent tasks over stdio or Streamable HTTP. Every write goes through a danger-comman | |
| gemini-cli-mcp cainmaila/gemini-cli-mcp Enables AI assistants to delegate complex tasks to the local Gemini CLI, returning structured results with execution metadata. | |
| MCP Health Server caio313/mcp-health-monitor Integrity monitor for MCP server ecosystems, providing real-time health checks, drift detection, and cascade impact analysis for any AI agent. | |
| sheets-mcp caioalexandreps02/google-planilhas-mcp MCP server for Google Sheets that exposes tools to read cell ranges, update values, and apply advanced batch updates (borders, colors, data validation, conditional formatting) via HTTP. | |
| Local Worker MCP caioallgayer/local-worker-mcp Delegates heavy, repetitive, and verifiable tasks like PDF extraction, code analysis, and log processing to a local LLM to reduce token consumption for frontier AI models, while keeping decision-making with the main AI. | |
| TradeLab-MCP caioallgayer/tradelab-mcp Quantitative research MCP server that lets AI define strategies and uses MetaTrader 5's official Strategy Tester to execute backtests, managing experiments and results via tools like run_backtest, get_run, and compare_runs. | |
| ViziProof caiohenriqu123-art/viziproof Provides MCP tools to manage code review tasks, track evidence and GitHub checks, and record approval decisions in a local kanban board. | |
| Pluggy MCP Starter caiomioto2/pluggy-mcp-starter Enables users to ask natural-language questions about their spending, transactions, and connected bank accounts or cards by aggregating read-only Pluggy Open Finance data across multiple itemIds. It exposes schema and SELECT-only query tool | |
| agro-market-agent caioribeiro25/agro-market-agent MCP server providing agricultural market intelligence tools (price, margin, trend, report generation) that can be used by any MCP client to answer multi-step queries about commodity markets. | |
| Azure AI MCP Server caiotk/nexguideai-azure-ai-mcp-server Enables comprehensive integration with Azure AI services including OpenAI, Cognitive Services, Computer Vision, and Face API through a mission-critical MCP server. Provides enterprise-grade reliability with high availability, observability, | |
| DeBank MCP Server caiovicentino/debank-mcp-server Enables querying DeFi data through DeBank API, including wallet balances, token prices, NFT collections, protocol positions, transaction history, gas prices, and security analysis across 93+ blockchains through natural language. | |
| Hyperliquid MCP Server caiovicentino/hyperliquid-mcp-server Enables Claude Desktop to interact with Hyperliquid DEX for trading perpetual futures using natural language, supporting 27 tools across trading, account management, market data analysis, and real-time WebSocket subscriptions. | |
| jev-shield caiovicentino/jev-shield A semantic firewall for MCP servers that screens tool calls, results, and descriptions with calibrated probabilities, blocking exfiltration, destructive actions, and injection attacks while allowing policy-based thresholds to decide enforce | |
| Gotas Commerce MCP Server caiovicentino/mcpgotas A bridge between AI assistants and cryptocurrency payment services that enables creating and verifying USDT transactions through the Gotas Commerce API. | |
| Polymarket MCP Server caiovicentino/polymarket-mcp-server Enables Claude to autonomously trade, analyze, and manage positions on Polymarket prediction markets with 45 comprehensive tools including market discovery, real-time monitoring, portfolio management, and AI-powered trading recommendations | |
| Solana MCP Server caiovicentino/solana-mcp A Model Context Protocol server enabling AI agents to interact with the Solana blockchain for DeFi operations like checking balances, transferring tokens, executing swaps, and fetching price data. | |
| bilinote-mcp caiqianzhang/bilinote Enables AI coding agents to access Bilibili video data and turn videos into notes, including search, video info, subtitles, chapters, audio download, ASR transcription, comments, uploader collections, and favorites. | |
| google-sheets-mcp cairas/google-sheet-mcp Local Model Context Protocol server for reading and writing Google Sheets through Google Sheets API v4. | |
| cairn cairn-kb/cairn Enables AI agents to read, search, and propose shared team knowledge as reviewable claims, while holding agent-proposed additions until a human approves them. Agents can also cite documents as evidence for existing claims, with no tools for | |
| paper-handler-mcp cairnstew/paper-handler Enables agents to work on academic paper corpora through compact JSON tools, exposing an outline/section/edit/lint loop so a model can scaffold, read and revise one section at a time without loading whole documents. Also covers metadata edi | |
| knowledge-mcp caitao-ct/knowledge-base 语义搜索知识库，支持文档获取和索引刷新，使AI Agent能够检索团队知识。 | |
| Caitlyn OpenAPI MCP Server caitlyn-ai/caitlyn-openapi-mcp Exposes OpenAPI specifications as queryable documentation resources for LLMs, enabling semantic search, endpoint details, and deep links to Scalar docs. | |
| SRP Hub MCP caiuriuller/srp-hub-mcp Connects AI assistants to the Hub API, enabling them to manage resources such as customer leads through structured tools. It provides validated operations for creating customer records, supporting specific Brazilian fiscal ID (CPF/CNPJ) val | |
| mcp-patent caiuschrom-a11y/mcp-patent MCP server for USPTO patent prior-art search, enabling keyword search, ranking, and date filtering via Claude, Cursor, or Windsurf. | |
| mcp-trademark caiuschrom-a11y/mcp-trademark USPTO Trademark Watcher MCP server enabling trademark search, watch, and alert management from within Claude or other MCP clients. | |
| hevy-mcp caiuse/hevy-mcp Access your Hevy workout data through natural language. Query workout history, exercise details, routines, and track progress. | |
| entire2api caiweike/entire2api Enables AI agents to send short standalone questions to an Entire review job through a local stdio MCP tool and receive structured answers with model and run identifiers. | |
| packet-tracer-mcp caixax/packet-tracer-mcp Enables AI agents to control Cisco Packet Tracer in real time, allowing natural language-driven creation and configuration of network topologies. | |
| Caiyun Weather MCP Server caiyunapp/mcp-caiyun-weather Enables querying real-time, hourly, weekly, and historical weather data, as well as weather alerts, using the Caiyun Weather API. | |
| bptoolkit-mcp caizhirong486-lab/ue_bptoolkit Enables AI coding agents to read, review, and generate Unreal Engine 5.4+ blueprints, including dumping graph JSON, reviewing Wwise logic chains, and building blueprints from JSON specs. | |
| Home Assistant MCP Reporter cajo-dk/mcp A minimal MCP server that exposes a single tool to forward JSON reports from Home Assistant to Power Automate webhooks. It enables automated workflow integration by securely transmitting data between Home Assistant and Microsoft Power Autom | |
| Hotmart MCP Server cajuflow/hotmart-mcp Enables AI agents to manage Hotmart products, sales, and other operations through a standardized Model Context Protocol interface, integrating with Claude and other LLMs. | |
| Cakemail API MCP Server cakemail/apidoc.mcp.cakemail.com Enables AI assistants to browse, inspect, and call the Cakemail API via dynamically loaded OpenAPI spec. | |
| Cakemail API MCP Server cakemail/cakemail-api-documentation-mcp An MCP server that provides AI agents with direct access to authoritative Cakemail API specifications, enabling accurate code generation and eliminating hallucination. | |
| Cakemail MCP Server cakemail/cakemail-mcp-server Enables comprehensive email marketing automation through the Cakemail API, including campaign management, transactional emails, contact list operations, template design with BEEeditor, detailed analytics, and multi-account enterprise manage | |
| Internet Search MCP Server cakhiltej9001-source/internet_search_mcp_agents Custom MCP server exposing an internet_search tool that fetches DuckDuckGo results, enabling AI agents to perform web searches and retrieve structured information. | |
| content-validity-index-mcp cakrawala-tumbuh/content-validity-index-mcp Enables AI clients to browse instruments, items, dimensions, expert assignments, and calculate Content Validity Index (CVI) via a standard MCP interface. | |
| Azure DevOps MCP Server cakriwut/ado-mcp-server Enables integration with Azure DevOps services, allowing interaction with work items, pull requests, pipelines, wikis, boards, and projects through natural language in Cline and other MCP clients. | |
| canvas-mcp cal-poly-dxhub/canvas-mcp Enables managing Canvas LMS courses, assignments, grades, modules, and more from MCP-compatible clients like Claude Desktop, Kiro, or Amazon Q Developer. | |
| OMCP cal3bdev/omcp Converts an OpenAPI spec into an MCP server, enabling AI agents to call your API without writing tool definitions or integration code. | |
| CalabiYau Map Engine MCP calabiyaugames/calabiyau_map_engine_mcp Connects MCP clients to a local browser-based map editor, enabling session discovery, map state inspection, item and actor queries, actor placement and movement, selection changes, deletion, and undo/redo operations. Supports STDIO, Streama | |
| Calame calame-tech/calame Visual no-code generator that turns any database into multiple scoped MCP servers — one per access group, with PII masking and fail-closed query scoping built in. | |
| MCP Todo calamityadam/mcp-todo Enables users to manage a persistent todo list through natural language, supporting adding, listing, toggling completion status, and removing todos. Features both stdio and HTTP transports with optional authentication and JSON file storage. |
36,451–36,500 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.