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 |
|---|---|
| Dameng DM8 MCP Server 1593292349/mcp-server-dm8 达梦数据库 DM8 的 MCP 服务器，为 AI 助手提供只读 SQL 查询、表结构自动发现和样本数据查看功能。 | |
| Crypto_MCP 1595901624/crypto-mcp A Model Context Protocol server for AES encryption and decryption, supporting various modes, padding, and input/output formats for secure data handling. | |
| QRCode_MCP 1595901624/qrcode-mcp An MCP server that generates customizable QR codes with options for size, colors, error correction, and margin settings. | |
| my-mcp-server 15972289829/mcp A Model Context Protocol server that allows integration with Claude Desktop by creating and managing custom tools that can be executed through the MCP framework. | |
| js-reverse-mcp 1600822305/js-reverse-mcp A Chrome DevTools Protocol-based MCP server that enables AI coding assistants to control browsers for JavaScript debugging, reverse engineering, web scraping, and API debugging. | |
| SO Analyzer MCP 1600822305/so-analyzer-mcp Enables analysis of native Android libraries (SO files) and Flutter applications, including decompilation, function identification, SSL certificate bypass patching, and binary modification through 30+ specialized tools. | |
| ansys-agent-bridge 1622352030/ansys-agent-bridge Enables headless control of Ansys SpaceClaim, including opening, inspecting, modifying, scripting, and exporting geometry, while guarding operations that falsely report success to ensure geometry actually changed. | |
| lab-equipment-mcp 1622352030/lab-equipment-mcp An MCP server for controlling lab instruments (oscilloscopes, signal generators, etc.) via standardized interfaces like USBTMC, RS-232, and LAN. | |
| Markdown to HTML MCP Server 1623311678/markdown-to-html-mcp An MCP server that converts Markdown to HTML, supporting both stdio and HTTP interfaces for easy integration with Cursor and other MCP clients. | |
| yunwen-doc-ai-platform 1644156/yunwen-doc-ai-platform 提供文档智能问答的MCP服务器，支持查询知识库、获取会话历史和清理会话历史。 | |
| dsh-dispatch 16601134718/dsh-dispatch Exposes an HTTP MCP Streamable endpoint that dispatches tasks to DeepSeek Harness sessions, fanning them out across parallel ACP workers with follow-ups, waiting, result retrieval, and optional review. Spend, external-send, and network-expo | |
| MCP Server on Vercel 168moons/mcp A template for running Model Context Protocol servers on Vercel with Redis support, allowing developers to deploy their custom tools, prompts, and resources using the MCP TypeScript SDK. | |
| hippocampus 1690940255ran-dot/hippocampus Enables LLM agents to consolidate, revise, and selectively forget memory records through MCP tools for memory write, search, forget, provenance, consolidation, and stats. | |
| Yahoo Finance MCP Server 16coffee/finance-mcp A Model Context Protocol server providing comprehensive financial data from Yahoo Finance, allowing users to retrieve detailed stock information, financial statements, options data, and market news. | |
| polyu-estudent-mcp 1708004874a-star/polyu-estudent-mcp A local MCP server that lets Claude Code operate the PolyU eStudent portal to check grades, timetable, exams, search subjects, and manage course registration through natural language. | |
| llm-vision 1710782766/llm_vision A local MCP server that gives vision to vision-less LLMs by describing images and extracting text via Alibaba DashScope vision models. | |
| TrendRadar MCP Server 17191004/trendradar Enables real-time trending news aggregation from multiple sources, with AI-powered analysis, smart filtering, and multi-channel notifications (e.g., Telegram, WeChat, email) via MCP. | |
| trendradar-mcp 17191004/trendradar_260829 Enables AI assistants to query aggregated multi-platform hot topics and RSS feeds, filter by keywords, and trigger AI-powered translation, analysis, and channel notifications through natural language. | |
| content-publish-engine-mcp 1736280642-star/content-publish-engine MCP server for governed AI content publishing to platforms like WeChat, Juejin, CSDN, and Zhihu, exposing tools for platform auth checks, content preflight, publish job lifecycle, verification, and liveness monitoring. | |
| jev-cognitive-mcp 17671454333/jev-cognitive-mcp Enables coding agents to pre-screen commands for destructive patterns and credential leaks, arbitrate escalation with a five-factor controller, route tasks by complexity, verify completions, and rerank candidates through MCP tools. Outputs | |
| JD Saver 17678319606/jd-saver Enables users to search for hidden coupons, generate commission short links, find combined savings deals, set price drop alerts, and track historical prices for JD.com products. | |
| wanyi 17861102832/wanyimem Enables AI agents to maintain a local, event-sourced long-term memory with semantic retrieval, decision confidence checks, and proactive recalls, ensuring data never leaves the machine. | |
| mindraw_mcp 17lang/mindraw4agent A project-scoped MCP server that opens a Mindraw canvas from the active Codex workspace, with local sidebar preview and desktop app handoff. | |
| ChaiChai 17lijunyi/chaichai Enables AI clients to inspect local software structure, code, and runtime behavior through evidence-backed analysis, including sources, coverage, and limitations. | |
| Fabric MCP Server 1818tusculumst/fabric-mcp-server Provides access to 227+ expert-crafted Fabric AI patterns for tasks like summarizing, analyzing, and extracting wisdom, all through Claude Desktop with no API keys needed. | |
| SmartDrive 1818tusculumst/smartdrive-mcp Enables semantic search across your OneDrive documents using natural language queries, powered by RAG with Pinecone vector search and Azure Blob Storage. | |
| Hermes Bridge 182moon/odin-hermes-bridge Enables MCP agents to delegate tasks to a local Hermes Agent for terminal, file, browser, and coding operations, and schedule recurring jobs. | |
| ArcgisMCP 1834495203/arcgismcp Enables AI clients to read and describe ArcGIS geodatabase, shapefile, and raster data, run vector geoprocessing, editing, statistics, cartography, and format-conversion tools through a local ArcPy worker, and trace the lineage of derived d | |
| mathematica-skill 1837620622/mathematica-skill Enables AI agents to perform real Wolfram Language computation, create and edit native .nb notebooks and figures, export data, and independently verify results through a stdio MCP interface. | |
| Garmin Assistant API 1838337544m-droid/garmin-assistant Enables local synchronization of Garmin activity and health data using a personal API key, then lets MCP-connected AI clients analyze training readiness and recovery with cited models and research. Supports viewing records, sleep/HRV, stres | |
| AppFlowy MCP Server 18896101294/my-appflowy-mcp Enables automatic upload of AI-generated rich text content to AppFlowy with Markdown syntax support, allowing seamless document creation and management through natural language instructions. | |
| amap-location-mcp 188zjl/amap-location-mcp An MCP server that provides location-based services using Amap APIs, enabling AI assistants to answer navigation queries by resolving addresses, converting coordinates, and comparing walking, driving, and transit routes. | |
| termux-phone-mcp 188zjl/termux-phone-mcp Provides Android device and Termux capabilities to RikkaHub via a local MCP server, enabling device info, battery, power sampling, package installs, proot-distro management, brightness/volume control, and optional command execution. | |
| exception-mcp-server 18abhi89/exception-mcp-server Enables AI-powered analysis of exceptions using vector similarity search and Azure OpenAI for operations teams. | |
| kelivo-image-mcp 1906777392-star/kelivo-image-mcp Remote MCP server that enables Kelivo chat models to generate images via tool calls, supporting OpenAI-compatible relay and NovelAI backends, and returning images as Markdown links or native image blocks. | |
| ops-mcp-kit 1907670605/ops-mcp-kit Enables AI assistants to query company logs, databases, caches, and config centers (e.g., Aliyun SLS, MySQL, Redis, Nacos) through local MCP servers, with read-only enforcement and SSH tunneling for production access. | |
| MCP DB Python 191341025/mcp-db-python A Python-powered Model Context Protocol server that provides safe database inspection and read-only querying capabilities for MySQL databases. Enables LLM agents to explore database schemas, execute read-only SQL queries, and retrieve metad | |
| OpenClaw-xiaozhi MCP Server 19147951441/openclaw--xiaozhi-mcp-server A bridge server that connects MCP-compatible clients to the OpenClaw (Jarvis) AI assistant for asynchronous task processing and real-time WebSocket communication. It enables users to send intents, execute tasks, and query results using a su | |
| MySQL MCP Server 1940633231/sql-mcp-agent Enables natural language querying of MySQL databases by exposing tools to list tables, retrieve schemas, and run read-only SELECT queries with safety protections. | |
| EvolvMem 1942293420/evolvmem_mcp A fully-local, three-layer memory plugin for Claude Code with Chinese support, offering hybrid FTS5/trigram and HNSW vector search, self-iterating memory management, consolidation, and a web console. | |
| gibwork-sentinel-mcp 195440/gibwork-mcp-sentinel Exposes pre-flight analytics and guardrail tools over stdio that let AI agents and maintainers rank open Gibwork bounties by risk-adjusted expected value and on-chain Solana vault solvency, audit escrow state and queue saturation, and valid | |
| @godman-protocols/lax-mcp 195440/lax-mcp-server Enables users to search registered agents, fetch capability offers, list and inspect jobs, and submit bounty work to the LAX registry through MCP tools over stdio or Streamable HTTP. | |
| Xero MCP Server 1981rba/xero-mcp-server Enables standardized access to Xero's accounting and business features via the MCP protocol, supporting contact, invoice, quote, credit note, account, and report management through OAuth2 authentication. | |
| attribute-classifier-mcp 19892500339/attribute-classifier-mcp Enables a complete visual analysis pipeline that detects objects in images, crops them, and classifies each object's attributes such as material and color using dedicated CNN models, returning structured JSON results. | |
| engram 199-biotechnologies/engram Gives AI persistent personal memory with hybrid search, temporal decay, and knowledge graph. Works with Claude and any MCP client. | |
| Zen MCP Server 199-biotechnologies/mcp-zen-npx Gives Claude access to multiple AI models (Gemini, OpenAI, OpenRouter, Ollama) for enhanced development capabilities including extended reasoning, collaborative development, code review, and advanced debugging. | |
| MCP Autostarter 199-mcp/mcp-autostarter An intelligent MCP server that enables seamless restarting of Claude's MCP handler process without disrupting the UI, allowing for plugin reloading without closing the entire Claude Desktop application. | |
| ElevenLabs MCP Enhanced 199-mcp/mcp-elevenlabs An enhanced server for ElevenLabs that enables high-quality text-to-speech, voice cloning, and multi-speaker dialogue management. It features advanced conversational tools for transcript retrieval, history tracking, and emotional audio synt | |
| MCP Google Workspace 199-mcp/mcp-google Enables comprehensive management of Google Calendar, Contacts, and Gmail through AI systems. Supports full CRUD operations including creating/updating/deleting events, managing contacts, sending emails, organizing with labels, and batch ope | |
| MCP Kling 199-mcp/mcp-kling An integration that enables Claude to generate AI videos from text prompts or images using Kling AI's video generation models. |
21,801–21,850 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.