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 |
|---|---|
| Token Runway cpleasance/token-runway Enables AI agents to monitor live token consumption and rate-limit windows across providers and assess whether expensive actions are justified before exhausting quotas, with optional budget guardrails. | |
| Puppeteer MCP Server cploujoux/mcp-puppeteer A Model Context Protocol server that provides browser automation capabilities using Puppeteer, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment. | |
| DuckDuckGo MCP Agent cploutarchou/duckduckgo-mcp-agent A minimal, production-ready MCP server enabling LLMs to perform web searches via DuckDuckGo without API keys, supporting SSE streaming and LM Studio compatibility. | |
| Flighty MCP Server cplx/flighty-mcp-server Connects AI assistants to the Flighty flight tracking app for querying flight status, delay forecasts, stats, and adding/removing flights via natural language. | |
| MCPSaver cpntodd/mcpsaver Local MCP server for persistent, searchable agent memory using SQLite FTS5, replacing flat MEMORY.md files with efficient full-text search and workspace context caching. | |
| soft1-mcp cpouldev/soft1-mcp Enables read-only analysis of Soft1 ERP databases through guarded T-SQL queries, schema discovery, knowledge search, and CSV/XLSX exports. | |
| wg21-wiki-mcp cppalliance/wg21-wiki-mcp A local MCP server that gives an LLM agent read access to the WG21 (ISO C++) committee wiki as a verifiable source of truth, requiring authentication and providing exact wikitext with provenance. | |
| MCP Planning Server cppmyjob/cpp-mcp-planner Provides structured task planning and tracking capabilities with 40 tools for managing requirements, solutions, architectural decisions, and hierarchical implementation phases with progress tracking. | |
| Metabase MCP Server cpr43/metabase-mcp Enables AI assistants to interact with Metabase analytics platform, allowing users to query databases, manage dashboards and cards, execute SQL queries, and access analytics data through natural language. | |
| vision-mcp cpramod/vision-mcp An MCP server that provides image analysis capabilities using vision-capable AI models, including object detection, OCR, scene description, and image comparison. | |
| fsq-codebase cprepos/codeinfuse Enables fast semantic code search using FSQ embeddings, with zero-config indexing and support for multiple programming languages via the Model Context Protocol. | |
| GoHighLevel MCP Server cpretzinger/gohighlevel-mcp Connects Claude Desktop to GoHighLevel CRM with 269+ tools for complete contact management, messaging, sales pipelines, appointments, e-commerce, invoicing, social media, and marketing automation through natural language. | |
| memory-forge cpretzinger/memory-forge A production-ready MCP server for persistent AI memory across LLMs like Claude and ChatGPT. Provides automatic conversation backup, multi-user support, and multi-storage (PostgreSQL, Redis, Qdrant). | |
| Dialpad MCP Server cprfirstaid/dialpad-mcp MCP server exposing Dialpad call details, transcripts, and call initiation as tools for use in Claude Desktop and Claude Code. | |
| Linear MCP Server cpropster/linear-mcp-server A Model Context Protocol server that allows Claude to interact with Linear's API for managing teams, issues, projects, and cycles. | |
| Konsilium cpt-rabbit/cpt-konsilium Enables privacy-first medical document analysis with multi-perspective AI review. Ingest documents, run consilium reviews, generate doctor letters, and search patient memory—all through natural language. | |
| CountBean cputester5465/countbean-plugin MCP server for Beancount plain-text accounting: turns plain English into double-entry transactions, runs bean-check, and commits each change to git so it can be diffed and reverted. Works on a local ledger file with no account, or on a host | |
| VolPilot cpuu/volpilot An MCP server that enables conversational Windows memory forensics through Volatility 3, letting an assistant inspect processes, network connections, registry artifacts, kernel objects, and other evidence artifacts from a memory image using | |
| mcp-medusa cpxazn/mcp-medusa Exposes Medusa anime automation tools for adding anime and querying seasonal anime via MCP. | |
| bring-mcp cpy-pst-gmbh/bring-api-mcp-connector MCP server that writes items to a Bring! shopping list, enabling Claude to add recipe ingredients directly to your list via natural language. | |
| USTC School MCP cpzioo4/ustc-school-mcp Enables read-only querying of eight campus services through independent local MCP adapters: mailbox search, reading and attachment download, Blackboard courses, academic-system terms, timetable and grades, library loans and navigation, teac | |
| GitHub Trend Radar MCP Server cqnxnzg/github-trend-radar Enables AI assistants to query GitHub trending projects, analyze language and technology trends, and generate visual trend reports. | |
| RealTest MCP Server cquillen/realtest-mcp Provides structured access to RealTest backtesting documentation and example scripts to help LLM agents generate accurate RealScript code. It offers tools for semantic search, authoritative function references, and verified script retrieval | |
| Cerebro de compañía cquiroz6211/winterbrain Converts meetings, chats, and notes into reusable knowledge for a venture capital firm, enabling knowledge capture and retrieval via Claude or Codex. | |
| Outlook MCP Server cqyefeng119/windows-outlook-mcp An integration server that lets you control Microsoft Outlook on Windows via COM, enabling email reading, summarization, and draft generation without complex security setup. | |
| Wordle MCP (Python) cr2007/mcp-wordle-python Fetches Wordle solutions from the Wordle API for dates ranging from May 19, 2021 to 23 days in the future. | |
| Agentic-AI-Planning-And-Reasoning-MCP cr21/agentic-ai-planning-and-reasoning-mcp MCP server for step-by-step mathematical reasoning and planning, enabling AI agents to execute calculations and perform GUI actions like opening PowerPoint. | |
| continue-chat-export cr4i50n/mcp-continue-chat-export Sanitizes Continue.dev session exports and reformats them as readable Obsidian chat Markdown, with MCP tools that return only metadata (paths, counts) for privacy. | |
| Higress AI-Search MCP Server cr7258/higress-ai-search-mcp-server A Model Context Protocol server that enables AI models to perform real-time internet and knowledge searches through Higress, enhancing model responses with up-to-date information from Google, Bing, Arxiv, and internal knowledge bases. | |
| Higress OPS MCP Server cr7258/higress-ops-mcp-server Enables comprehensive configuration and management of Higress through the Model Context Protocol, with an MCP client built on LangGraph and LangChain MCP Adapters for agent-driven interaction. | |
| Zero Wire MCP craael/zero-wire-mcp Gives MCP clients read-only access to Cloudflare Zero Wire vulnerability briefings, letting them list, search, and retrieve briefings by CVE ID, title, or URL along with each one's assessment prompt. Returns only data published in the feed, | |
| ko-bridge crabbtech/ko-bridge Enables an AI model to drive a Teenage Engineering EP-133 K.O. II from a Mac over USB MIDI, SysEx, and USB audio, managing sample uploads, project writes, playback, recording, and device backups. | |
| op-bridge crabbtech/op-bridge Lets an AI model drive a Teenage Engineering OP-1 field over USB MIDI — designing sounds, playing scored parts, running tape and mixer, and authoring presets — while capturing every take from the device's own USB audio. The model then works | |
| MCP数据库查询服务 crablduck/mcp_database 一个基于Model Context Protocol的SQLite数据库查询服务，为AI应用提供标准化的数据库访问、安全的SQL查询执行以及表结构预览功能。 | |
| crabsmadethis/d2r-horadric-tools Diablo II Resurrected modding toolkit — character builder, mod build/deploy pipeline, save inspector, CASC reader, and MCP server for Claude/Codex/AI integration. Linux/Steam Deck. | |
| bespoke-mcp crack-pantelimon/bespoke-mcp Enables an LLM to drive a live Bespoke Synth, including module graph editing, control modulation, sequencing, playback control, and audio analysis feedback with visualizations. | |
| @clarvivo/mcp cracked-collective/clarvivo-mcp Lets coding agents set up Clarvivo analytics directly by detecting the app framework, creating or reusing the appropriate project, returning the exact snippet, and verifying real traffic. | |
| Boarderless MCP Server crackenreleased/boarderless.app_mcp Enables AI agents to inspect and edit the live browser-resident canvas of the Boarderless app via a structured spatial ledger. | |
| Speech-to-Text MCP Server crackgo/speech-to-text-mcp-server An MCP server that provides speech-to-text transcription and speaker diarization using OpenAI Whisper and pyannote.audio. | |
| mcp-creatio crackish/mcp-creatio MCP server for Creatio CRM that enables AI assistants to read, create, update, delete records, execute business processes, and manage settings via OData and REST APIs. | |
| wigolo craftart/wigolo Enables AI agents to perform local-first web search, fetch, crawl, extract, cache, research, and autonomous information gathering through MCP, with no API keys or cloud dependencies. | |
| fitia-mcp crafter-station/fitia-cli Enables AI assistants to access and manage a user's Fitia account, including profile, Premium, food search, diary, meal suggestions, and preview-first writes that require confirmation before mutating data. | |
| CrafThinkERA MCP crafthinkera/mcp Enables AI agents to initiate, inspect, and advance physical-production workflows via the CrafThinkERA service, bridging natural-language instructions to actionable production steps while preserving human approval boundaries. | |
| vector-mcp craftingcodegig/vector-mcp Integrates RAG into AI agents via MCP Server, supporting multiple vector database technologies for collection management and search operations. | |
| remote-mcp-server-authless craftix-labs/remote-mcp-server-authless Enables deploying a remote MCP server on Cloudflare Workers without authentication, allowing MCP tools to be used from clients like Cloudflare AI Playground or Claude Desktop. | |
| Kitchen MCP craftpip/kitchen-mcp Your digital kitchen, powered by AI. Track what you have, discover what you can cook, and get guided through every recipe — step by step, timer by timer. | |
| Termux MCP craftultra000-png/termux-mcp Enables AI agents to remotely run a full Bash shell in Termux on Android, allowing file management, package installation, tests, Git, and other shell operations through a temporary ngrok tunnel. | |
| agroagent craguila14/agroagent An AI agent that orchestrates four specialized MCP servers to provide actionable agricultural recommendations for Chilean farmers, integrating weather, market prices, crop history, and regulatory documents. | |
| dockhand-mcp craibo/dockhand-mcp MCP sidecar server that exposes Dockhand's container, image, volume, network, and stack management as MCP tools over Streamable HTTP, enabling MCP clients to manage Docker resources through Dockhand's REST API. | |
| syncro-mcp craig0100/syncro-mcp MCP server for Syncro MSP that enables managing customers, tickets, assets, contacts, and invoices through a decision tree architecture for efficient tool navigation. |
40,601–40,650 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.