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 |
|---|---|
| GoThreatScope anotherik/gothreatscope Go-based SBOM, vulnerability, and secret scanner with MCP support. | |
| ThreatByte-MCP anotherik/threatbyte-mcp An intentionally vulnerable case management system designed for security training that provides MCP tools for SOC analyst workflows like case handling and indicator search. It enables users to explore and demonstrate common security weaknes | |
| Evidence Gate anothermeatsack/evidence-gate Enables AI assistants to run local, model-backed decisions on short passages and routing choices, and to check whether exactly supplied text supports a scientific claim, returning the full probability distribution, review-policy status, and | |
| MCP Notes Connector anotherstream/mcp-notes-connector Enables integration with Evernote API to access and manage Evernote resources including notes, notebooks, and tags through the Model Context Protocol. | |
| superchat anou4r/superchat-mcp Enables local MCP clients to interact with the Superchat public API, supporting contact search, conversation management, notes, exports, and message sending using your own API key. | |
| UI5 MCP Server anovaes47714/mcp-server Enables agentic AI tools to scaffold UI5 applications and Integration Cards, retrieve API references and development guidelines, validate manifests, run linter checks, and inspect project metadata. | |
| garmin-mcp anpatellll/garmin-mcp A remote MCP server with GitHub OAuth that provides tools like arithmetic, GitHub user info, and image generation for authorized users. | |
| Obsidian Omnisearch MCP Server anpigon/mcp-server-obsidian-omnisearch Provides programmatic search functionality for Obsidian vaults through a REST API interface, allowing external applications to search through notes and retrieve absolute paths to matching documents. | |
| graylog-mcp anpy-j/graylog-mcp Provides a standardized MCP interface for querying Graylog logs, enabling AI agents to search, diagnose, and correlate runtime logs with code via configurable profiles. | |
| MCP Oracle Server anpy-j/mcp-oracle A Model Context Protocol server that enables Claude to access and interact with Oracle databases through natural language queries. | |
| music-perception-mcp anqipinku/music-perception-mcp Analyzes audio files to extract exact, reproducible measurements like loudness, tempo, key, spectral balance, and clipping for LLM-based DAW control. | |
| openHop MCP Server anquietas86/openhop-mcp-plugin Enables MCP clients to query a Repeater's mesh telemetry—including stats, neighbors, packets, routes, noise floor, GPS, and hardware—over authenticated Streamable HTTP, with optional read-only or admin write tools. | |
| Mailrith MCP Server anrawool/mailrith-agent-platform MCP server for building safe AI agent email marketing workflows with Mailrith. | |
| RAG MCP Server anrege/git-clone-https-github.com-alejandro-ao-simple-mcp-rag A MCP server for document ingestion and semantic search using ChromaDB and sentence transformers, enabling users to query natural language over ingested documents. | |
| AutoDev Codebase MCP Server anrgct/autodev-codebase HTTP-based server that provides semantic code search capabilities to IDEs through the Model Context Protocol, allowing efficient codebase exploration without repeated indexing. | |
| anriss anriss-dev/anriss Enables UI feedback loop by clicking elements, leaving comments, and letting AI coding agents (via MCP) resolve annotations interactively. | |
| FreshGen Link anrob/freshgen-link Self-hosted MCP server that integrates Kie.ai image and video generation into GoHighLevel's AI tools, enabling AI agents to create media on demand. | |
| uaal ansaribilal14/uaal Enables MCP clients to resolve, inspect, acquire, verify, and query routes, capabilities, schema, and health for public and authorized web resources, with fail-closed statuses and artifact production. | |
| aegis-prop-trader-sentinel-mcp ansarii/aegis-prop-trader-sentinel-mcp Real-time capital oversight, drawdown alerts, and economic news blackout defense for funded prop traders and AI agents across cTrader and Tradovate. | |
| neon-b2b-intelligence ansarii/neon-b2b-prospector Enables targeted B2B lead discovery, DNS MX deliverability verification, and extraction of web content into clean Markdown for AI agents. | |
| Firecrawl-Compatible Stealth Web Scraper MCP Server ansarii/neon-stealth-scraper Provides a drop-in replacement for Firecrawl's core tools, enabling AI agents to scrape, crawl, and map websites with resilient TLS fingerprinting and pay-per-success billing, while avoiding edge bot filters and blocked-request charges. | |
| neon-b2b-intelligence ansarii/web-reader-live-docs Enables targeted company discovery, real-time DNS MX deliverability diagnostics, and clean web Markdown extraction for AI agents. | |
| MCP Keyword Search ansariusaid/mcp-keyword-search Enables keyword searching within text files with configurable case sensitivity, returning matching lines with line numbers and occurrence counts. | |
| Power BI Report MCP Server ansehh/powerbi-report-mcp Enables MCP-compatible AI clients to build and modify Power BI reports through natural language, including pages, visuals, themes, filters, and formatting using local PBIR files without REST API keys or the Power BI service. | |
| CAP-based S/4HANA Business Partner MCP Server anselm94/cap-mcp-s4-bupa Enables testing and development against a mock S/4HANA Business Partner API, exposing customer and customer address entities through the MCP protocol. | |
| mcp-ai-agent-guidelines anselmoo/mcp-ai-agent-guidelines A TypeScript ESM MCP server exposing 20 public instruction tools and 7 utility tools, backed by 102 internal skills across 18 domain families — from requirements discovery and code quality through governance, resilience, and physics-inspire | |
| mcp-zen-of-languages anselmoo/mcp-zen-of-languages Enables AI assistants and developers to analyze code for language-specific best practices and idiomatic patterns across programming languages, CI automation, and configuration formats. | |
| Cline Email MCP Auto-Setup anselmwang/cline-email-mcp Automatically configures email notification functionality for Cline through SMTP integration. Enables Cline to send email notifications for task completion, errors, or user input requirements with automated setup and testing. | |
| RAG Chatbot MCP Server ansh-7666/ai-based-chatbot Exposes a local RAG document index as MCP tools (ask, search, rebuild_index, status) for MCP clients like Claude Desktop and Claude Code to query your documents over stdio. | |
| FastMCP Supply Chain Optimizer ansh-riyal/fastmcp A custom implementation for real-time supply chain optimization that enables parallel tool calling to provide intelligent inventory management recommendations and actionable insights in response to live supply chain events. | |
| MCP-RAG ansh-riyal/mcp-rag An agentic AI system that orchestrates multiple specialized AI tools to perform business analytics and knowledge retrieval, allowing users to analyze data and access business information through natural language queries. | |
| expense-tracker ansh-rohilla/expense-tracker-mcp-server A lightweight MCP server for recording, browsing, and summarizing expenses locally using SQLite, with a customizable categories resource. | |
| Gmail MCP Server ansh-wappnet/gmail_mcp A Model Context Protocol server that enables applications to interact with Gmail through a clean API, supporting email searching, sending, reading, and label management. | |
| Gmail MCP Server ansh-wappnet/gmail_mcp_server Enables programmatic interaction with Gmail using OAuth 2.0 authentication, allowing users to search, read, send, and manage emails through a standardized interface. | |
| MCP Weather Data Fetcher ansh642/mcp-server Enables AI agents to retrieve live weather updates for any city via OpenWeatherMap, wrapped in MCP format. | |
| MCP Workstation anshace/mcp-workstation Enables AI clients to connect once and access tools from many registered MCP servers plus built-in modules, with multi-user authentication, per-user server/tool toggles, and a skills hub. | |
| MCP Boilerplate anshajk/mcp_boilerplate A boilerplate for deploying a remote MCP server on Google Cloud with authentication, enabling experimentation with MCP tools. | |
| Expense Tracker MCP Server anshgautam-github/mcp-expense-tracker Enables local-first expense logging, editing, and analysis through natural language conversation, backed by a SQLite database and accessible via MCP over stdio. | |
| astromock-mcp anshiika123/mcp-a Exposes Vedic astrology tools for birth chart, dasha, transit calculations, and question context analysis. | |
| Calculator MCP Server anshika1109/calculator-mcp-server A mathematical utility server implementing the Model Context Protocol to provide tools for basic and advanced calculations. It enables users to perform operations such as addition, subtraction, powers, square roots, and percentages through | |
| Stock Market Real-Time Analyzer anshika1109/stock-market-analyzer An MCP server that provides real-time stock market data and price comparisons from Yahoo Finance, Alpha Vantage, and Finnhub. It enables AI assistants to fetch individual quotes, compare data across multiple sources, and retrieve market met | |
| GhostWall MCP Server anshikasingh28072006/ghostwall Enables offline multi-agent security orchestration by providing tools for network traffic analysis, log correlation, threat scoring, and firewall mitigation via JSON-RPC. | |
| atelier-mcp anshrajore/atelier-mcp Post-generation quality gate MCP server that audits and fixes AI-generated code for UI/UX design compliance and backend architecture robustness via tools like critique_ui, critique_backend, and generate_fix. | |
| health-mcp anshrajput/any-health-mcp Enables AI agents to query personal health data collected by any wearable or phone fitness app through Android Health Connect or Apple Health, exposing read-only tools for metrics like heart rate, sleep stages, VO2 max, and body composition | |
| mcp-workstation anshroshan/mcp-hub Enables AI clients to connect to a single MCP endpoint that aggregates many MCP servers and built-in tools, with multi-user authentication, per-user server configuration, encrypted secrets, and a skills hub. | |
| devvault-mcp anshtripathi03/devvault-mcp Enables coding agents to connect to a user's DevVault, allowing them to search, retrieve, save, and append research/context containers directly from the agent. | |
| ExpenseTracker MCP Server anshu857754/remote-mcp-server An MCP server for tracking personal expenses, supporting adding, listing, and summarizing expense entries with data stored in a local SQLite database. | |
| pg-sentinel anshujod/postgres_mcp_server A PostgreSQL MCP server with three independent safety layers that allows LLMs to explore and query databases safely via read-only SELECT operations, with full audit logging and query plan intelligence. | |
| mcp-trip-orchestrator anshul2k17saini/mcp-trip-orchestrator Enables multi-agent travel planning by orchestrating specialized agents for transport, accommodation, and experiences, using live web search and structured data extraction to generate complete trip plans. | |
| logseq-mcp anshulbansod2/logseq-mcp An MCP server that lets an AI agent operate a Logseq (DB) graph through safe, high-level tools for reading and managing notes, tasks, and projects without needing to know Logseq's internals. |
29,401–29,450 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.