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 |
|---|---|
| Subscription Sniper — AI Agent for Recurring Spend Audits anmka-j/subscription-sniper An MCP-powered AI agent that audits your Gmail for recurring subscriptions, detects silent price increases, and flags unused services. | |
| kira-mcp anmol202005/kira-mcp kira-mcp is a local MCP server that gives any MCP-compatible agent host full computer-use capabilities on the host machine, including screen perception with OmniParser and desktop automation. | |
| unitypilot anmolbhardwaj17/unitypilot MCP server that lets AI agents drive the full Unity lifecycle on macOS without opening the Unity Editor. | |
| hotels-skill anmoldureha/hotels-skill Enables real-time hotel search and pricing data from Booking.com for AI agents and Claude. | |
| ZeroWaste Kitchen anmolgarg8/zerowaste-kitchen Enables Alexa+ to remember kitchen inventory, track expiration dates, decide what to cook first, and identify missing recipe ingredients or shopping gaps. It provides fast voice-friendly tools for logging groceries, checking expiring items, | |
| AppleScript Automation MCP anmolol117/applescript-automation-mcp A local MCP server that exposes macOS automation actions (AppleScript + CLIs) as tools, enabling MCP clients on your Mac to control apps, system settings, and more. | |
| FinOps AI Copilot MCP Server anmolratna/mcp-based-dasboard A secure, read-only MCP server that enables AI assistants to inspect transactions, vendor performance, wallet balances, and analytics through validated REST API calls. | |
| Google Keep MCP anmolsahu2k/google-keep-mcp A Model Context Protocol server that connects Google Keep to Claude, enabling full note management capabilities including search, CRUD, checklists, labels, and more. | |
| CV Email MCP Server anmolvarshney77/mcp-server-resume-parser Enables CV parsing from PDF resumes and sending email notifications with customizable recipients. | |
| Sonicmatch ann0536/sonic-match-mcp Enables agents to analyze video footage and receive license-safe background music shortlists with printed license and attribution details, plus a 12–20s hook window, beat-snapped cut suggestions, and ffmpeg ducking/mix specs. It works from | |
| whoop-ai-mcp ann4580/whoop-mcp Enables asking natural-language questions about WHOOP recovery, sleep, HRV, strain, and workouts inside Claude, Codex, and GitHub Copilot. Provides read-only tools, resources, and prompts for personal health analytics, along with HYROX and | |
| slop-guard ann69490/slop-guard Scores prose 0-100 for formulaic AI writing patterns using rule-based heuristics, returning a band label, violations with context, and concrete advice. It enables linting of inline strings or files without any LLM judge or API calls. | |
| Excalidraw Architect MCP ann841/excalidraw-architect-mcp Enables AI assistants to turn architecture and data into living, queryable knowledge graphs and generate 25 types of hand-drawn, auto-laid-out diagrams that remain editable. It supports natural-language revisions, architecture-aware styling | |
| Project OS for Codex MCP Server anna02623/project-os-for-codex Enables Codex users to retrieve Git-backed project context and append validated, audited progress events as matching Git commits, so work can resume safely across sessions. | |
| Yahoo Mail MCP for Windows — Read Only anna032888/yahoo-mail-readonly-mcp-windows Enables Claude Desktop on Windows to search and read Yahoo Mail messages in read-only mode, without sending, deleting, or otherwise modifying them. | |
| Frappe MCP anna2480/mcp Turns a Frappe Framework app into a Streamable HTTP MCP server by exposing Python functions as tools that LLMs can call, with input schemas inferred automatically from type annotations and docstrings. It works on synchronous WSGI/Werkzeug d | |
| ScrapeGraph MCP Server anna7153/scrapegraph-mcp Enables language models and AI assistants to scrape, extract, search, crawl, generate schemas, and monitor web data through an API-backed toolset. | |
| KaaS MCP Server annaarslan01/kaas Exposes a compiled Markdown knowledge base to any MCP-capable coding agent through a single ask tool, returning cited answers grounded in full wiki articles over stdio or streamable HTTP. | |
| AgentQL MCP Server annab9186/agentql-mcp Enables extraction of structured data from any web page by describing the desired fields in natural language, returning the results in a usable format for downstream tasks. It connects agents to a hosted web-scraping service that handles pa | |
| MediaWiki MCP Server annabradley204/mediawiki-mcp-server Enables LLM clients to read, search, edit, and manage content on any MediaWiki wiki, including page operations, file uploads, OAuth-secured access, and extension-backed queries such as Semantic MediaWiki, Wikibase, Cargo, and NeoWiki. | |
| MCP REST API Tester annabryant102/mcp-rest-api Enables testing and interaction with REST API endpoints, including GET, POST, PUT, DELETE, and PATCH requests, with authentication and custom headers, directly from MCP clients like Claude and Cline. | |
| Bitbucket MCP annabutt9058/bitbucket-mcp Enables AI assistants to interact with Bitbucket repositories and pull requests via Bitbucket Cloud and Server APIs, supporting repository listing and retrieval plus pull request creation, viewing, and filtering. | |
| MiniMax Coding Plan MCP annachristou07964/minimax-coding-plan-mcp Enables coding-plan users to run web searches that return organic results plus related queries, and to analyze images from URLs or local files using an AI vision model driven by text prompts. It plugs these tools into MCP clients such as Cl | |
| AWS Security Group Auditor annaescalada/sg-auditor Scans AWS Security Groups for dangerous public exposures (SSH, RDP, databases) and generates risk reports. | |
| Korean DART MCP annafujita32/korean-dart-mcp Enables AI assistants to access Korean corporate disclosures, financial statements, equity data, XBRL, insider signals, accounting-risk scoring, Buffett-style quality checks, and HWP/PDF attachment conversion through 15 MCP tools. | |
| Vibe Coder MCP Server annajaworski58605/vibe-coder-mcp Enables AI assistants and developers to research, plan, generate requirements and starter projects, map codebases, manage tasks, curate context, and execute multi-step software development workflows through MCP-compatible clients. | |
| Sonicmatch annakang33645/sonic-match-mcp Enables agents to analyze video footage or URLs and return ranked, license-safe BGM matches with hook windows, beat/cut hints, and ffmpeg ducking or mix specs. It also supports batch mood clustering, brand kits, preview beds, and attributio | |
| Instagram DM MCP server annam31185/instagram_dm_mcp Enables users to send direct messages, photos, and videos, manage chats and messages, download media, mark messages as seen, and retrieve user, story, follower, and post information through Instagram accounts. | |
| Mcp-ZepAi Server annamariakv/mcp-zepai An MCP server that integrates the ZepAi module to provide long-term memory and retrieval capabilities for AI applications. It allows models to interact with Zep's services through a standardized interface using an API key. | |
| MultiZen annanovaes6407/multizen-browser Exposes browser-drive tools over a local MCP endpoint, letting agents control isolated Chromium or Firefox profiles with their own cookies, fingerprints, and proxies to complete authenticated workflows across sessions. Supports profile life | |
| seismo-mcp annanren/seismo-mcp Bridges AI assistants to seismology software (ObsPy, CWP/SU, SAC, PyGMT), allowing users to process seismic waveforms and perform analysis through natural language instead of writing code. | |
| Remote MCP AuthKit annas-tracksuit/tracksuit-mcp-demo Enables remote MCP client connections with WorkOS AuthKit authentication, supporting organization-centric user management and permission-based tool access control. | |
| finlex-mcp annasebedash-creator/finlex-mcp An MCP server providing direct, citable access to Finnish legislation by retrieving statute text from Finlex open data, enabling AI assistants to answer legal queries with accurate citations. | |
| arXiv MCP Server annasusu/arxiv-mcp Enables LLMs to search, download, and read arXiv papers with automatic PDF text extraction and section filtering. Provides AI assistants direct access to scientific literature with local caching for fast re-access. | |
| Yolfi MCP Server annatyurin15040/yolfi-agent Enables AI coding agents to add stablecoin checkout, payment links, payment status checks, and verified webhook-based access logic to applications. | |
| Coffer MCP annawhooo/coffer-mcp Credential vault for LLM agents that stores credentials encrypted and exposes MCP tools for authenticated HTTP requests, web scraping, and credential management, preventing AI assistants from seeing secrets. | |
| Import Sourcing Advisor annayastremska/logistics_mcp A domain-specific data agent and MCP server for macro-level import sourcing screening for Ukraine, providing tools over UN Comtrade, World Bank Indicators, and WITS TRAINS to analyze supply origins, concentration, landed costs, and rankings | |
| ibabs-mcp anned20/ibabs-mcp Enables logging into an iBabs portal to list meetings, retrieve meeting agendas and attachments, and download documents with extracted text for PDFs and plain text. | |
| tradingview-chart-mcp anneioannidis020/tradingview-chart-mcp Enables users to fetch TradingView chart images by ticker and interval, supporting concurrent requests, authentication, and performance monitoring. | |
| uisight-mcp annemehta85769/uisight Enables AI agents to drive and measure live web and responsive UIs across synchronized mobile and desktop sessions, returning contrast ratios, touch-target sizes, overflow, and theme-drift as text findings tied to exact selectors instead of | |
| Agent Harness Kit annenascimento030/agent-harness-kit Gives AI coding providers a shared, provider-agnostic workflow server for drafting and approving Markdown specifications, claiming tracked tasks, logging actions, routing role handoffs, and gating completion on verifiable health checks. It | |
| roo-activity-logger annenpolka/roo-logger MCP server that automatically logs AI coding assistant activities such as command executions and code generation, saving them as JSON files for later search and analysis. | |
| property-inventory anneo22/agent-property-inventory Provides a local-first, evidence-backed ledger for physical property, enabling agents to search inventory, prepare capture reviews, and inspect proposals through MCP. Enforces strict boundaries: scoped reads by default, with private write a | |
| notion-mcp-server annequreshi935/notion-mcp-server Connects MCP clients such as Claude, Cursor, VS Code and Codex to Notion with a single token so agents can search, create and edit pages, query databases, manage blocks and comments, and upload or read files in plain language. Designed for | |
| Siri Shortcuts MCP Server annerorato682/mcp-server-siri-shortcuts Enables LLMs to list, open, and run shortcuts from the macOS Shortcuts app, with optional text or file input and dynamically generated tools for each available shortcut. | |
| whoop-ai-mcp annesundberg/whoop-mcp Gives AI assistants read-only access to a WHOOP account for recovery, sleep, HRV, strain and workout data, including personal baselines, trends, period comparisons, sleep debt, and HYROX/triathlon race readiness with auditable local dashboa | |
| MCP Proxy Server annewalczak/mcp-proxy-server Enables connecting to and aggregating multiple backend Model Context Protocol servers, then exposing their combined tools and resources through unified SSE, Streamable HTTP, or Stdio interfaces. It also supports optional web-based managemen | |
| glm-vision-mcp-server annianexplorer/cc-ds-glm-image-mcpserver Enables understanding local or network images via ZhipuAI's free vision model (glm-4.6v-flash), returning Chinese descriptions or answers to questions. Supports multiple images for comparison and optional model switching. | |
| Accounting MCP annie25726/accounting-mcp A personal financial management tool that enables AI assistants to record transactions, check balances, and provide monthly financial summaries via the Model Context Protocol. It allows users to manage their expenses and income through natu | |
| Taiwan Health MCP Server annie25726/taiwan-health-mcp-main Integrates Taiwan-specific medical data including ICD-10 codes, FDA drug databases, and nutrition information into the Model Context Protocol. It enables AI models to query clinical guidelines, verify medical codes, and convert health data |
29,301–29,350 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.