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 |
|---|---|
| GitHub Repo Finder ehsas317/github-repo-finder A production-grade GitHub repository finder that helps LLMs discover best repositories with advanced search, ranking, and token optimization. | |
| Google Webmaster MCP ehukaimedia/google-webmaster-mcp Enables AI agents to manage Google Tag Manager, Google Search Console, and Google Analytics (GA4) through unified access to tags, search performance data, URL inspection, sitemaps, and analytics reporting. | |
| newsroom-mcp ehurrn/newsroom-mcp Type-safe MCP server for investigative journalism that enforces evidentiary standards on master-file.json, preventing chain-of-custody violations and ensuring publishable claims meet criteria. | |
| colab-persist ehzawad/colab-persist Enables local coding agents to manage disposable Colab GPU runtimes, restore and save Google Drive checkpoints, execute scripts, and safely stop VMs through MCP stdio tools. | |
| mcp-api-reference ei-nakamura/mcp-api-reference An MCP server that automatically crawls, indexes, and serves API reference documentation for LLMs, enabling to search and retrieve endpoint details. | |
| rails-lens ei-nakamura/rails-lens An MCP server that exposes Ruby on Rails implicit dependencies like callbacks, associations, and concerns to AI coding tools. | |
| API Health Check MCP Server eiabhiram/api-healthcheck-mcp Monitors API endpoint health by checking availability, measuring response times, and providing detailed status reports with error handling and timeout protection for the localhost:8080/api/ticket endpoint. | |
| Educational MCP Server eiadrian/educational-mcp Enables AI assistants to access educational domain tools including grading, cognitive diagnosis, knowledge tracing, learning path recommendations, and sentiment analysis through FastAPI-powered small models. | |
| AgentPlayerAchievements eiainano/agentplayerachievements MCP turns vibe coding into a game. Steam-style achievements for Claude Code, Hermes and more. | |
| NodeAPI eianray/node-api Machine-native GIS processing API for AI agents and developers. Convert, reproject, validate, repair, buffer, clip, dissolve, and tile vector geodata across 25 endpoints. Pay-per-use USDC on Solana Mainnet ($0.01/op). No accounts, no API ke | |
| XRootD MCP Server eic/xrootd-mcp-server An MCP server providing access to XRootD file systems, allowing LLMs to browse directories, read file metadata, and access contents via the root:// protocol. It supports advanced features like campaign discovery, file searching, and ROOT fi | |
| Spire.Doc MCP Server eiceblue/spire-doc-mcp-server Enables AI agents to create, read, modify, and convert Word documents without Microsoft Word, supporting 18 tools for document operations, paragraph manipulation, table management, formatting, and conversion between multiple formats includi | |
| Spire.XLS MCP Server eiceblue/spire-xls-mcp-server A robust solution that enables AI agents to create, read, modify, and convert Excel files through the Model Context Protocol without requiring Microsoft Office installation. | |
| Harbor MCP eidantz/harbor Provides MCP tools to manage a local-first Kanban board, including projects, issues, dependencies, and labels. Enables AI clients to interact with the board via a stdio MCP server connected to a NestJS API. | |
| railguey-mcp-cloudflare eidos-agi/railguey-mcp-cloudflare Hosts a Streamable HTTP MCP server that lets Grok connect to Railway by pairing account tokens, then interact with Railway resources through natural language. | |
| research.md eidos-agi/research.md MCP server that enforces evidence-graded, phase-gated, peer-reviewed research workflows for AI agents to conduct rigorous decision-making. | |
| resume-resume eidos-agi/resume-resume Enables finding and resuming past coding sessions in plain English, managing dirty repos, and recovering from crashes, with indexed full-text search across session history. | |
| @segnals/mcp eidostein/segnals-mcp Enables AI agents to manage Segnals trading bots, strategies, PnL, and the strategy marketplace through natural language. | |
| JSON Schema Validator MCP Server eienwolf/jsonshema_mcp A comprehensive server that enables validation of JSON data against JSON Schema Draft 2020-12, with support for external references, schema management, and real-time streaming validation. | |
| SNOMED CT MCP Server eigenbau/mcp-snomed-ct An MCP server that provides SNOMED CT clinical terminology lookup via any FHIR R4 terminology server supporting SNOMED CT and ECL. Offers tools for searching by term, fetching by code, and navigating the concept hierarchy. | |
| aicesat eigenbeam/aicesat Enables querying, visualizing, and co-registering ICESat-2 ATL03 and ICESat/GLAS GLAH06 altimetry data as 3D point clouds, with plate-motion correction and Δh statistics. | |
| remote-mcp-mem0 eighthundreds/remote-mcp-mem0 A remote MCP server deployed on Cloudflare Workers for memory storage and retrieval using Mem0, supporting SSE and standard MCP connections. | |
| learn-mcp eik-1/local-mcp-server A learning MCP server with tools, resources, prompts, and sampling for AI clients like Cursor, using local JSON storage. | |
| puppeteer-real-browser-mcp-server eikaramba/puppeteer-real-browser-mcp-server Provides AI assistants with powerful, detection-resistant browser automation capabilities, allowing them to control a real web browser to navigate, extract content, and perform tasks while avoiding bot detection. | |
| Binance Agent MCP Server eikarna/binance-agent-mcp Enables AI agents to autonomously analyze market data, compute risk metrics, and execute spot or futures trades on Binance with safety guardrails like dry-run mode and slippage protection. | |
| chronomem eikarna/chronomem Enables AI agents and MCP clients to store, retrieve, and manage bi-temporal, graph-aware facts in an embedded SQLite memory engine with token-budgeted recall and contradiction tracking. | |
| ImageSorcery MCP eikechukwu39/imagesorcery-mcp-safe Enables AI assistants to perform local computer-vision-based image recognition and editing, including cropping, resizing, rotating, background removal, drawing text and shapes, object detection, OCR, overlays, and metadata inspection withou | |
| DPS-Superskills-MCP eilodon/dps-superskills-mcp Exposes 31 high-assurance agentic coding skills as MCP tools and resources, enabling AI agents to invoke structured workflows across DISCIPLINE, TECHNIQUE, KNOWLEDGE LAYER, and REFERENCE registers. | |
| cadence-mcp eimaieros/cadence-mcp Enables an AI assistant to run a practice job interview end to end: starting a session for a role and focus areas, streaming the interviewer's next question, recording the user's answers, and retrieving the transcript, budget spend, and fin | |
| Agentic RAG MCP Server eimantahir027/mcp-powered-agentic-rag A local Retrieval-Augmented Generation system that enables AI agents to query and retrieve information from document collections using ChromaDB vector search and Ollama LLMs through a FastAPI interface. | |
| wp-mcp-server eimon/wp-mcp Enables an AI design agent to connect to any WordPress site, inspect its real rendered CSS/JS/theme, and create or update pages through the WordPress REST API and optional companion plugin routes. | |
| sources-mcp eingin/sources-mcp Read-only MCP server exposing homelab data sources (files, mail, calls) to Cloudflare OS, enabling read-only access to documents, emails, and call records. | |
| windows-computer-use-mcp einosensokami/windows-computer-use-mcp A local, dependency-free MCP server that gives AI agents controlled access to the active Windows desktop, enabling automated interaction with applications through screenshots, clicks, typing, and window management. | |
| NFL Transactions MCP einreke/nfl-transactions-mcp A Modular Command-line Program for fetching and filtering NFL transaction data, including player movements, injuries, disciplinary actions, and more from ProSportsTransactions.com. | |
| Sleeper API MCP einreke/sleeper-scraper-mcp This Model Context Protocol server provides access to the Sleeper Fantasy Football API, enabling agents to fetch data about users, leagues, drafts, rosters, matchups, and player information without requiring an API key. | |
| MeteoSwiss MCP Server eins78/meteoswiss-llm-tools Provides access to official MeteoSwiss weather data, including regional reports, daily forecasts, and website search functionality across multiple languages. It enables AI assistants to retrieve real-time weather information and documentati | |
| zotbridge einstein628/zotbridge Connects a Zotero library to MCP-compatible clients, enabling library search, full-text PDF reading, highlight retrieval, and formatted citation export. | |
| MCP PDF Extract einsteindark-edgm/mcp-read-doc-local A Model Context Protocol server that enables listing and reading PDF documents from a configured directory, extracting text content for MCP clients like Claude Desktop. | |
| invoicehub-mcp einvoice-dev1/invoicehub-mcp EU e-invoice validation, as a developer API.
Check whether an electronic invoice conforms to EN 16931 — the European standard behind France, Germany, Belgium, Poland and the 2030 ViDA mandate — with a single REST call. Structured JSON error | |
| ChatGPT Direct Developer MCP eiomra/t3-chatgpt-direct-mcp Enables ChatGPT to interact with registered T3 Code projects through an authenticated MCP endpoint, supporting directory listing, hash-checked file reads/writes, Git status/diff inspection, and opt-in package scripts. | |
| China Festival MCP Server eis4ty/china-festival-mcp Provides Chinese holiday information, lunar calendar conversion, traditional festivals, 24 solar terms, and BaZi (Eight Characters) calculations for AI assistants to accurately handle Chinese calendar queries and date conversions. | |
| SymPy Sandbox MCP eis4ty/sym-mcp A secure mathematical computation sandbox that enables LLMs to perform symbolic math operations like algebra, calculus, and equation solving via SymPy. It features low-latency execution through pre-warmed process pools and provides standard | |
| AWS Customer Playbook Advisor MCP eisuke000111/aws-customer-playbook-advisor-mcp Provides real-time access to AWS security best practices, incident response playbooks, and preventive security measures from the official AWS Customer Playbook Framework repository. Enables users to query AWS security guidance for services | |
| Gmail + Calendar MCP Server eitan3/gmail_mcp A multi-account MCP server providing 72 tools for Gmail and Google Calendar, with password protection, environment variable-based credentials, and support for multiple accounts. | |
| scrapy-mcp eitan3/scrapy_mcp_scraper A headless web-scraping MCP server built on Scrapy, providing tools for polite fetching, CSS/XPath extraction, link/table extraction, sitemap and robots.txt reading, and bounded asynchronous crawls. | |
| tg-mcp eithery-rc/tg-mcp A remote HTTP bridge that lets Claude Code agents message you on Telegram, ask questions with tap-to-answer buttons, and send files, while your replies are pushed into running sessions as channel events — with per-project topics, message qu | |
| network-lab eiuemura/network-lab-mcp Enables AI assistants to understand lab topologies, follow operational principles, and interact with real network devices through observable terminals while keeping private access information hidden. | |
| Google Search Engine MCP Server eivs/google-search-engine-mcp Enables Google search queries and webpage content extraction through an MCP server deployed on Cloudflare Workers. Supports single and batch webpage content extraction with integrated OAuth authentication. | |
| Fetch MCP Server eivs/mcp-fetch Enables fetching and processing web content by retrieving URLs and converting HTML to markdown format. Supports chunked reading of webpages and both local (stdio) and HTTP transport modes with optional authentication. | |
| MCP WebSearch eivs/mcp-websearch A web search MCP server using DuckDuckGo, supporting streaming HTTP and session management. |
47,301–47,350 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.