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 |
|---|---|
| polymarket-mcp-server bybastianrok/polymarket-mcp A read-only MCP server that lets Claude query Polymarket's public APIs for markets, events, live order books, price history, trades, open interest, trader leaderboards, and wallet positions and P&L. It also offers arbitrage scanning, market | |
| Bybit MCP Server bybit-exchange/trading-mcp A production-ready MCP server for Bybit — 206 tools covering market data, trading, positions, account management, assets, and real-time WebSocket streams. Enables AI assistants to interact directly with the Bybit cryptocurrency exchange thr | |
| Modular RAG MCP Server bye-666/bye-rag A pluggable, observable modular RAG service framework that exposes tool interfaces via the MCP protocol, enabling AI assistants like Copilot and Claude to directly query knowledge bases. | |
| infographic-mcp byebyebruce/inforgraphic-mcp Renders infographics from DSL syntax into PNG images using AntV Infographic. Supports various templates, image customization, and multiple transport modes (stdio, HTTP, SSE). | |
| TradingView MCP Bridge byeung888/tradingview-mcp Personal AI assistant for your TradingView Desktop charts. Connects Claude Code to your locally running TradingView app via Chrome DevTools Protocol for AI-assisted chart analysis, Pine Script development, and workflow automation. | |
| airlock byjh/airlock A security gate MCP server that audits agent extensions (skills, MCP servers, tools) by scanning for risks, adversarial analysis, and sandbox execution, returning a trust verdict of allow, quarantine, or block. | |
| MCP Server with GitHub OAuth byjit/cloudflare-mcp-server A Model Context Protocol server that enables remote connections with GitHub authentication, allowing users to build applications that leverage MCP tools with secure OAuth-based access control. | |
| Toolkits MCP byjit/toolkits-mcp A collection of image processing tools that enables users to optimize images, remove backgrounds using AI, and generate favicons from logo files locally. | |
| capture-one-mcp byjustinjones/capture-one-mcp An MCP server that enables automating Capture One Pro on macOS, providing tools for reading and editing images, managing layers/masks, recipes, and processing with risk-tiered write gating. | |
| jev-eval-mcp byk/jev-mcp Enables prototyping, running, and evaluating typed judgment questions against TypeSafe's Jev model, including accuracy, calibration, and threshold analysis. | |
| mcp-context byliu-labs/mcp-context A plugin that intercepts large MCP tool outputs, indexes them into a local FTS5 knowledge base, and replaces them with summaries, enabling searchable retrieval to save context window space. | |
| MS SQL Server MCP Server bymcs/mssql-mcp Enables interaction with Microsoft SQL Server and Azure SQL databases through natural language, supporting queries, schema exploration, stored procedures, and complete database operations with connection pooling and security features. | |
| Unofficial Dex CRM MCP Server byndcloud/unofficial-dex-mcp An MCP server that integrates the Dex personal CRM API with AI assistants to manage contacts, groups, tags, and reminders through 27 specialized tools. It enables users to perform unified searches and execute full CRUD operations on their C | |
| DkwtMCP bynoe17/dkwtmcp Local MCP server that connects Claude Desktop with Garmin and Apple Health data to read training and recovery, estimate heart rate and pace zones, analyze performance, and create structured workouts. | |
| SEO MCP PRO bypixels/sandi-ads Enables Claude with 121 tools for website operations, Google Marketing, SEO, performance analysis, security auditing, monitoring, and accessibility testing. | |
| mysid-mcp bypreetham/mysid-mcp mysid is an ultra-fast, standalone code intelligence engine and Model Context Protocol (MCP) server written in Rust. It eliminates bloated token footprints and multi-turn round-trips for AI coding agents and human developers alike. | |
| testing-toolkit-mcp byreshb/testing-toolkit-mcp Provides coding agents with visibility into test health through tools for flaky test detection, test quality linting, and LLM evaluation harness, enabling them to triage failures, review test quality, and check prompt changes for regression | |
| Nautobot MCP Server v2 byrn-baker/nautobot-mcp-v2 Enhanced Nautobot 3.1.0 integration for NetClaw with GraphQL reads, REST writes, ITSM-gated changes, and live-vs-SoT reconciliation. Provides 13 tools covering devices, interfaces, VLANs, prefixes, IP addresses, cables, raw GraphQL, write o | |
| Ollama MCP Domain Expert Delegation byrn-baker/ollama-domain-experts-mcp An MCP server that lets AI agents delegate domain-specific tasks to local Ollama models, using purpose-built specialists for structured tasks like config generation, parsing, and validation. | |
| google_scholar_mcp byron993/google_scholar_mcp MCP server for searching academic papers via Google Scholar, retrieving metadata and abstracts, with support for Chinese queries and auto-translation. | |
| Self-Learning MCP byronap/self-learning-mcp Enables AI agents to learn from their work by recording tasks, extracting patterns, detecting mistakes, and proactively surfacing insights, all using the agent's own model through a cooperative intelligence pattern. | |
| Call Coach byrondarlison/call-coach Enables MCP-capable AI assistants to run live interview or discovery calls by loading Markdown question lists, starting and stopping local transcription, tracking answered questions, adding follow-ups, and saving or reading call transcripts | |
| mcp-archimate byrondelgado/mcp-archimate An MCP server that lets AI agents build, validate, and export ArchiMate models using 45 tools, 9 resources, and 4 guided prompts. | |
| eXpress MCP connector bysherstnev/express-mcp-connector Enables reading and searching a user's eXpress chats and message history locally, with optional confirmed sending of text messages. | |
| mcp-searchapi byski/mcp-searchapi An MCP server that exposes eight SearchApi.io search engines as discrete tools, returning trimmed structured results to save context. | |
| browser-store bysking/browser-store MCP server for managing and controlling multiple isolated Chrome/Edge browser instances, exposing tools for navigation, screenshots, clicking, form filling, and JavaScript execution to AI clients. | |
| Outline MCP Server bysonte/outline-mcp-server Enables querying, searching, and managing documents in an Outline instance via the Model Context Protocol. | |
| postgres-mcp-server bysonte/postgres-mcp-server Local MCP server for safe querying and inspecting PostgreSQL databases, with write and maintenance operations disabled by default. | |
| MCP SSH Manager bysonte/ssh-manager-mcp-server MCP server for managing remote servers via SSH, enabling command execution, file transfer, rsync, tunnels, health checks, backups, and database operations. | |
| MELODI MCP Server byt3lab/melodi_mcp_server Acts as a secure, dynamically synchronized gateway between MCP clients and MELODI ERP, enabling tool discovery, local schema validation, and authorized execution of ERP operations over STDIO or HTTP/SSE. | |
| github-mcp-worker bytask/github-mcp-worker Exposes GitHub REST and GraphQL APIs as 51 gh_* tools over Streamable HTTP, letting MCP clients read and write repositories, branches, commits, issues, pull requests, Actions workflows, releases, and notifications. It authenticates via Clou | |
| npu-vision-fallback byte-naut/npu-vision-fallback Provides an MCP server for local low-power screen vision, enabling AI agents to perform OCR and UI detection on inaccessible screens (games, remote desktops) using NPU acceleration and system OCR. | |
| Igor Pro Bridge byte-physics/igor-bridge-mcp-server Exposes a running Igor Pro instance to MCP clients, enabling command execution, wave data reading, compilation management, and launching/relaunching Igor Pro. | |
| Cueflow MCP Server byte42-it/cueflow Enables AI assistants to author, validate, and preview narrated, animated UI walkthroughs from static HTML scene kits, producing self-contained multilingual HTML guides without recording video. | |
| palaia byte5ai/palaia palaia gives your agents a persistent, searchable knowledge store. They save what they learn, find it by meaning, and share it across tools and sessions automatically. | |
| ByteBar Exam Prep MCP Server bytebarhq/bytebar-mcp Enables MCP-compatible AI assistants to search an exam-prep catalog, retrieve 204 free practice questions with answers and explanations across 15 IT and nursing certifications, check pricing, and get official exam facts. | |
| @botozap/mcp bytecraft-fernando/botozap-js MCP server exposing WhatsApp Cloud API operations as tools for AI agents like Claude Code, Cursor, and Codex. | |
| mcp-flux-schnell bytefer/mcp-flux-schnell A TypeScript-based MCP server that enables text-to-image generation using Cloudflare's Flux Schnell model API. | |
| material-icons-agent-skill byteflipper-58/material-icons-agent-skill Enables AI agents to search, import, migrate, validate, and maintain official Google Material Symbols across various platforms and IDEs. | |
| kimai-task-tracker-mcp byteflowsivar/kimai-task-tracker-mcp MCP server that enables managing tasks (Activities) in a Kimai project and tracking time, with tools to list, create, complete, reopen, start/stop timers, and log time. | |
| ghidra-bridge bytelandtechnology/ghidra-bridge Enables MCP clients to inspect and automate a running binary-analysis session, with tools for program, memory, function, and listing operations. | |
| Orders MCP server bytemonk-academy/mcp-vs-api Enables AI agents to find stale unshipped orders, retrieve order details, and mark orders as shipped by wrapping the orders REST API as MCP tools. | |
| Nexus MCP Server bytepine/nexusvscode Enables AI clients to interact with Unreal Engine through natural language commands by proxying MCP requests to the NexusLink UE plugin. | |
| MCP_Python bytermi/mcp_python MCP server deployed on Azure Functions that provides a LearnAgent tool to search and retrieve Microsoft Learn documentation. | |
| QGIS MCP Server bytes-007/qgis-mcp-optimizado Enables any MCP-speaking AI agent to drive QGIS directly by managing layers, editing features, running processing algorithms, rendering maps, and authoring layouts through 125 tools. It bridges agents to a running QGIS instance over a plugi | |
| interactsh bytes-knight/interactsh-mcp Enables AI agents to run an out-of-band interaction session: obtain a persistent payload domain and unique injection hosts/URLs, then poll for captured DNS, HTTP, SMTP and LDAP callbacks with per-hunt cursors. This supports SSRF, blind RCE, | |
| bytesagain-mcp bytesagain/mcp-server Search 60,000+ AI agent skills from ClawHub, LobeHub, Dify, and GitHub via MCP SSE or REST API. Free, no API key required. | |
| mcp-textbrowser bytesbrains/mcp-textbrowser A text-first headless browser MCP server that extracts DOM and OCR text from web pages, offering a cheaper alternative to screenshot-based browsing by defaulting to zero image tokens. | |
| SettleMate bytestudiosaus/settlemate An MCP server that acts as an AI collections agent for Australian tradies and SMEs, enabling automated chasing of overdue invoices, payment plans, and payments through a secure permissions engine. | |
| mysql-mcp-server-all bytetora/mysql-mcp-server-all A read-only MySQL MCP server supporting stdio, SSE, and Streamable HTTP transports, enabling secure querying and schema inspection of MySQL databases from MCP clients. |
36,251–36,300 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.