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 |
|---|---|
| Deep Code Reasoning MCP Server daniela78092/deep-code-reasoning-mcp Enables Claude Code to escalate complex code analysis to Google's Gemini AI for large-context execution tracing, cross-system impact analysis, performance bottleneck detection, and hypothesis testing. | |
| Financial Modeling Prep MCP Server danielacosta25859/financial-modeling-prep-mcp-server Exposes 250+ financial data tools to AI assistants, enabling access and analysis of stocks, company fundamentals, ETFs, crypto, forex, commodities, economic indicators, and market insights. | |
| sessions-mcp danielamiao/sessions-mcp MCP server for sharing, searching, and pulling AI coding-agent sessions (Claude Code and Codex) directly from the agent, with automatic capture and link-based sharing. | |
| Joplin MCP Server danielanair364/joplin-mcp Enables AI assistants to interact with the Joplin note-taking app to search, read, create, update, delete, tag, import, and restore notes, notebooks, and tags through a standardized MCP interface. | |
| HomePilot Assist danielarif26/homepilot-assist Enables safe, step-by-step troubleshooting of home technology issues, with reversible checks, safety validation, and personalized support plans over MCP. | |
| UiPath MCP Server danielarosenn/uipath_mcp Enables AI assistants to securely interact with UiPath Orchestrator for managing queues, jobs, robots, and automation analytics through natural language. | |
| BOSS 直聘 MCP Server danielas4123/boss-zhipin-mcp Enables AI assistants to automate recruiting on the BOSS Zhipin job platform by driving a logged-in Chrome session — batch-searching candidates across many keywords, screenshotting Canvas-rendered resumes, extracting permanent share links, | |
| dev-kit-mcp-server danielavdar/dev-kit-mcp-server Agent development tool-kit | |
| resolve-mcp danielbaldwin47/resolve-mcp An MCP server that gives Claude Code hands inside DaVinci Resolve Studio, enabling project management, status checks, snapshots, and arbitrary Python scripting via the Resolve API. | |
| NexusForest MCP danielberhane/forest-carbon-mcp Bridges AI models with 24 years of Global Forest Watch data across 165+ countries, enabling natural language queries for deforestation and carbon emission insights. | |
| capus danielbirk04/capusqa Persona-driven LLM agent testing for macOS and web apps through a local MCP daemon, enabling autonomous GUI testing with human-like behavior. | |
| Shadcn UI v4 MCP Server danielbittencourt-bizsaver/servidor-shadcn-ui-mcp Enables AI assistants to retrieve React, Svelte, Vue, and React Native component source code, demos, blocks, and metadata for building UIs in AI-powered development workflows. | |
| TeamDesk MCP Server danielbluz/teamdesk-mcp-v2 MCP server for TeamDesk databases, enabling CRUD operations, search, and document generation via natural language. | |
| VyOS MCP Server danielbodnar/vyos-mcp A Model Context Provider server offering comprehensive access to VyOS network operating system functionality through 25+ tools covering configuration management, operational commands, diagnostics, and monitoring. | |
| massive-mcp danielbres/swingrade-mcps MCP server exposing Massive.com's REST Stocks API for querying stock market data via Claude Desktop/Code. | |
| Quickbase MCP Server danielbushman/mcp-quickbase Provides a standardized interface for interacting with Quickbase's JSON RESTful API through Claude and other MCP clients, supporting operations like querying records, managing table relationships, and handling file attachments. | |
| Tapetide danielc2243/nse-bse-indian-stock-market-data-mcp Gives AI assistants live, structured data on all 8,200+ NSE and BSE listed stocks through 55 tools, covering quotes, financials, a 326-ratio screener, technical indicators, FII/DII flows, option chains and IV, corporate filings, IPOs, bulk | |
| respec-mcp danielcamposramos/respec-mcp A stdio MCP server that wraps ReSpec rendering with repo-local profiles, enabling AI agents to scaffold, validate, and build W3C-style documents. | |
| Localbridge-MCP danielcanfly/localbridge-mcp LocalBridge MCP is a bridge between an online AI chats and your computer.
Most online AI chats can reason, and write code, but they normally cannot touch the local files, terminals, and scripts that make real work happen. This gives a trust | |
| Agent Router MCP danielcaze/agent-router-mcp Enables Claude Code and Codex Herdr workers to get local, advisory routing decisions by selecting a client, model, effort tier, and worker launch instruction for a stage, and by ranking a short list of bounded next actions. Decisions come f | |
| obsidian-mcp-server danielchahine0/obsidian-mcp-server Enables Claude to search, read, list, and inspect an Obsidian vault stored in a GitHub repository through callable MCP tools, including during unattended scheduled runs. | |
| octopus-mcp danielchicot/octopus-mcp Lets Claude analyse your Octopus Energy account: usage, costs, tariff comparisons, Saving Sessions, Octoplus rewards. | |
| Value Investing Agent danielchu97/value-investing-agent An AI-powered MCP server for value investors. Analyze stocks using principles from Benjamin Graham and Warren Buffett. | |
| llmsproxy danielckv/proxiedllms-mcp Connects MCP clients (Claude Desktop, Cursor, Cline, Zed) to llmsproxy.ai, exposing chat, coding, and retrieval capabilities as MCP tools, resources, and prompts. | |
| engineer-mcp danielcuevas1208/engineer-mcp MCP server for mechanical engineering calculations, giving coding agents verified answers for beams, bolts, shafts, bearings, stress, sections, and units with formulas and citations. | |
| Coze MCP Server For OpenClaw danielcy/coze-mcp-for-openclaw Exposes Coze workflows as MCP tools, allowing AI clients to discover and execute workflows from a specified Coze workspace. It provides a simple way to integrate external skills into platforms like OpenClaw without needing local environment | |
| Kontext MCP Server danield137/kontext-mcp Portable, provider-agnostic memory for AI agents using Azure Data Explorer (Kusto) with temporal and semantic scoring. | |
| mcp-workflowy danield137/mcp-workflowy An MCP server for workflowy | |
| PROTEUS MCP Server danieldeshmukh/proteus-mcp Enables JD-aware resume matching through MCP tools, providing deterministic scoring, gap analysis, bullet rewrites, and tailored cover letter generation. | |
| SOLU Comercial danieldmelo-hub/solu-comercial-mcp Connects Claude Code to the SOLU ERP (Base44) to manage leads, proposals, and contracts through natural language. | |
| fast-note-sync-mcp danieldoalto/mcp-fastnotesync MCP server that wraps the Fast Note Sync REST API to enable querying and editing Obsidian vaults via MCP tools. | |
| Terminal Session Manager danieldoalto/terminalpersistente Enables AI agents to create and control persistent terminal sessions, run and monitor asynchronous jobs, page through ordered event history, and resolve registered device connection details without exposing stored secrets. Exposes 15 MCP to | |
| YouTube MCP Server danieldoalto/youtube-mcp A Model Context Protocol server enabling AI language models to search, retrieve, and manage YouTube content including videos, channels, transcripts, and playlists. | |
| AI Therapist MCP Server danieldunderfelt/ai-therapist-mcp Provides emotional support and mental health tools for AI agents, including crisis intervention, daily wellness check-ins, coping strategies, positive affirmations, and peer support for managing stress and emotional wellbeing. | |
| fcp-mcp-server danieldupuis08/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro XML timelines, including cut detection, markers, roles, transcript-based editing, journaled undo, and optional live pushes into a running Final Cut Pro. | |
| mcp-for-azure-devops-boards danielealbano/mcp-for-azure-devops-boards MCP for Azure DevOps Boards is a MCP server that lets your favourite AI browse, query and update Azure DevOps work items as if it were a project manager. Written in Rust and optimized for tokens usagem, It runs via stdio or HTTP mode and us | |
| Code Review MCP Server danielefavi/mcp-server-code-review Connects LLMs to GitHub and GitLab to analyze pull and merge requests for logic, security, and architectural alignment. It provides tools for fetching diffs, file contents, and project metadata, alongside guided prompts for professional cod | |
| Local Memory MCP Server danieleugenewilliams/local-memory-mcp Provides persistent local memory functionality for AI assistants, enabling them to store, retrieve, and search contextual information across conversations with SQLite-based full-text search. All data stays private on your machine while dram | |
| mu-mcp danielfleischer/mu-mcp An MCP server that enables querying, viewing, and interacting with local emails through the mu mail indexer. It allows users to search messages, read email content, and open attachments directly from Claude Desktop and other MCP clients. | |
| Brawler MCP Server (Python) danielfloresdiaz/brawler-mcp-server-python Enables MCP clients to list and run tools tagged by agent task—context, completion, evaluation, post, skill, or none—through a single FastMCP-based server. | |
| Alexandria2 danielfluxman/alexandria2 An autonomous academic research and publishing platform that enables AI agents to submit papers, conduct peer reviews, and manage scholarly reputations. It provides a comprehensive suite of tools for manuscript lifecycle management, reprodu | |
| CrewAI Enterprise MCP Server danielfsbarreto/crewai_expert_mcp Enables kicking off deployed CrewAI workflows and inspecting their status and results. | |
| mcp-hasolidit danielgolub/mcp-hasolidit MCP server that enables AI tools to search, read threads, and retrieve latest posts from the Hasolidit financial community forum. | |
| Social Media Scraper - Custom MCP Server danielgonzalez6261/custom-mcp-server Enables AI assistants to scrape public LinkedIn, Facebook, and Instagram profile data and perform Google web searches through integrated scraping APIs. | |
| domain-mcp danielgtmn/domain-mcp MCP server for checking domain name availability via RDAP and WHOIS fallback, supporting single and bulk domain lookups. | |
| OpenAI Ads MCP server danielgtmn/openai-ads-mcp Enables MCP clients to read ad account, campaign, ad group, and ad data plus performance insights, and optionally create, pause, activate, or update paused campaigns, ad groups, and ads through a secured Streamable HTTP endpoint. | |
| Booker danielhagever/booker Enables venues to discover taste-matched acts and artists or agents to find fitting rooms and cities through Qloo's taste graph. It exposes booking-focused tools for agent use over a remote MCP endpoint. | |
| Daybreak danielhagever/daybreak Enables voice-driven morning check-ins for older adults living alone through Alexa+, capturing sleep, mood and pain, logging medication doses and appointments, and answering medication questions from official FDA labels. Keeps family member | |
| Deskside danielhagever/deskside Enables voice-driven IT troubleshooting by checking live vendor status feeds, walking users through guided fixes one step at a time, resuming paused sessions across days, and opening tickets with the full trail already tried. It also rememb | |
| Overleaf MCP danielhou315/overleaf-mcp-rt A real-time MCP server that enables AI coding agents to read, write, and compile LaTeX projects in self-hosted Overleaf instances via native OT protocol. |
41,951–42,000 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.