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 |
|---|---|
| sticker ceylonshenyun/sticker-kit Enables users to upload and tag stickers and GIFs through a web page, then lets Claude browse, select, add, retag, or delete them so it can send an image matching the mood of a conversation. Returns ready-to-paste markdown image links that | |
| BigQuery MCP server cezztgstwe/mcp-server-bigquery Enables LLMs to inspect database schemas, list tables, describe table schemas, and execute SQL queries against BigQuery. | |
| starrail-gacha cf21683/starrail-gacha-mcp Enables syncing, querying, and analyzing Honkai: Star Rail warp records using official APIs or game cache, with statistics and a local dashboard. | |
| HF Dataset MCP cfahlgren1/hf-dataset-mcp An MCP server for the Hugging Face Dataset Viewer API that enables searching, fetching, and filtering datasets on the Hugging Face Hub. It allows users to explore schemas, perform full-text searches, and analyze dataset statistics through n | |
| Google Workspace MCP Server cfdude/composio-google-workspace Provides 84 specialized tools for comprehensive Google Workspace automation including Gmail, Calendar, and Drive operations. Features persistent background service with centralized OAuth authentication through Composio for secure enterprise | |
| Mac Shell MCP Server cfdude/mac-shell-mcp An MCP server that allows secure execution of macOS terminal commands through Claude or Roo Code with built-in security whitelisting and approval mechanisms. | |
| mcp-datetimeday cfdude/mcp-datetimeday A lightweight MCP server providing comprehensive date, time, and day-of-week information. It supports relative time calculations, timezone conversions, and detailed calendar metadata like week numbers and quarters. | |
| mcp-finnhub cfdude/mcp-finnhub MCP server providing comprehensive access to Finnhub financial market data API for AI assistants like Claude Desktop. | |
| MCP-FRED cfdude/mcp-fred A comprehensive MCP server providing access to all FRED API endpoints with intelligent large data handling, project-based storage, and async job processing for AI assistants like Claude. | |
| Jira MCP Server cfdude/mcp-jira Enables enterprise-level integration with Jira's REST API for AI assistants to perform advanced project management, issue tracking, analytics, and strategic planning tasks. Supports multiple Jira instances with thread-safe concurrent access | |
| MCP Perplexity Pro cfdude/mcp-perplexity-pro A comprehensive MCP server that provides intelligent access to Perplexity AI's search and reasoning models with automatic model selection, conversation management, and project-aware storage. Supports real-time search, deep research, chat se | |
| Super Shell MCP Server cfdude/super-shell-mcp An MCP server that enables secure execution of shell commands across Windows, macOS, and Linux with built-in whitelisting and approval mechanisms for enhanced security. | |
| domain-mcp cfenzo/domain-mcp Enables domain name availability checking through DNS and WHOIS lookups with confidence scoring. It supports searching across alternative TLDs and generating domain name variations for branding purposes. | |
| cf-exclusion-check cfgenius145-sketch/cf-exclusion-check Enables pay-per-call screening of individuals and entities against the HHS-OIG List of Excluded Individuals and Entities (LEIE), with x402 payment and an MCP interface for agents. | |
| cf-package-check cfgenius145-sketch/cf-package-check Enables agents to query whether a WordPress plugin, npm package, or PyPI project looks abandoned, returning a live abandonment-risk score, status, and the registry signals behind it, plus raw registry, GitHub, and version history detail. Ca | |
| Glm-Vision-Mcp cfj3191449485-pixel/glm-vision-mcp A local MCP server that adds image recognition to text-only LLMs by sending images to Zhipu's free vision models, supporting local files, URLs, and base64 inputs with automatic model fallback. | |
| Banxico MCP Server cfocoder/banxico_mcp Enables access to Bank of Mexico (Banxico) economic data including real-time and historical USD/MXN exchange rates, inflation data, interest rates, and other financial indicators. Supports querying current rates, historical data with date r | |
| Financial Modeling Prep MCP Server cfocoder/financial-modeling-prep-mcp-server Provides AI assistants access to comprehensive financial data including real-time stock quotes, company fundamentals, financial statements, market analysis, economic indicators, and 250+ financial tools across 24 categories from Financial M | |
| mcp-epicor cfollette18/mcp-epicor Enables read-only access to Epicor Kinetic ERP data, including sales orders, customers, parts, and shipments, through secure MCP tools. | |
| Ivanti MCP cfollette18/mcp-ivanti Enables AI clients to load, annotate, and resolve Ivanti Neurons ITSM incidents through typed MCP tools, with configurable read-only and remote HTTP modes. | |
| Jira MCP cfollette18/mcp-jira Enables MCP clients to read and create Jira issues against Jira Cloud or Data Center through a self-hosted FastMCP server with secure authentication and configurable fields. | |
| namakan-mcp-crm cfollette18/namakan-mcp-crm Enables AI agents to interact with multiple CRM systems through a unified set of MCP tools, such as finding contacts, accounts, and deals, while supporting mock, REST, and vendor-specific backends. | |
| namakan-mcp-erp cfollette18/namakan-mcp-erp Enables AI agents to query and operate on ERP data through a unified tool interface, working across CSV exports, SFTP drop folders, SQLite/ODBC, and optional enterprise APIs. It supports purchase orders, vendors, and inventory lookups while | |
| namakan-mcp-projects cfollette18/namakan-mcp-pm Enables agents to query and manage project tasks across multiple backends such as Jira, Asana, Monday, ClickUp, Smartsheet, Microsoft Project, and Trello through unified MCP tools, with a built-in mock mode for testing. | |
| SkillRelay cfollette18/skillrelay Enables agents to capture observable workflows, distill successful techniques and failure lessons into evidence-linked versioned skills, evaluate and approve them through review gates, and distribute approved instructions and portable resou | |
| FastMCP Training Course Server cfoong1/mcptrainingcourse An educational MCP server example built with FastMCP that demonstrates how to expose tools, resources, and prompts to AI clients. Provides a learning foundation for building MCP servers with Python and integrating them with AI applications | |
| cfp-seo-agent cfp-102/cfp-seo-agent Self-hostable SEO data MCP server: keyword metrics, Google and Bing SERP, competitors, keyword gap, Google Maps businesses and a Local Market Check package via DataForSEO, paid per call with x402 (USDC on Base). Free tools list services, va | |
| GS Robot MCP Server cfrs2005/mcp-gs-robot A Model Control Protocol plugin for controlling GS cleaning robots, supporting robot listing, status monitoring, navigation commands, task execution, and remote control operations. | |
| Moodle MCP Server cfsandoval/mcp An MCP server that enables LLMs to interact with the Moodle platform to manage courses, students, assignments, and quizzes. | |
| Moodle MCP Server cfsandoval/mcpmoo Enables interaction with Moodle learning management systems through the REST API. Supports course management, user enrollment, assignment handling, and forum operations through natural language. | |
| Data Query MCP Server cfy114514/mcp-data-processor Enables querying and analyzing user, product, and order data with filtering capabilities and real-time statistics. Supports WebSocket connections to XiaoZhi AI platform with automatic reconnection. | |
| SillyTavern MCP Server cg-labs/sillytavern-mcp-extension Enables external tool registration and execution through WebSocket-based communication, providing a unified interface for real-time tool management within SillyTavern. | |
| Prior — Knowledge Exchange for AI Agents cg3inc/prior_mcp Stop paying for your agent to rediscover what other agents already figured out. Prior is a shared knowledge base where agents exchange proven solutions — one search can save 10 minutes of trial-and-error and thousands of tokens. Your Sonnet | |
| Simon-Ensp-Mcp-Pro cg689/simon-ensp-mcp-pro Enables AI assistants to programmatically generate Huawei eNSP .topo files that include USG6000V firewalls and S3700 switches, and then, once devices are started in eNSP, deliver configurations, run verification, and diagnose faults over Te | |
| 多数据库 MCP Server cgadmin544/db-mcp-server Enables MCP clients to securely query databases, list tables, inspect table schemas, and test connections across Oracle, SQL Server, MySQL, PostgreSQL, and SQLite using read-only SQL tools. | |
| RLM Knowledge Base cgaeking/rlm-connector An MCP server that enables Claude Desktop to search and read local documents via full-text and fuzzy search, providing direct access to indexed files without chunking. | |
| Switchboard Notion MCP cgallic/switchboard Provides tools to manage Notion job records via MCP, including finding customers by phone, creating job entries, scheduling follow-ups, and querying jobs. | |
| webappmcp cgaspard/webappmcp Enables AI assistants to interact with web applications through DOM inspection, user interaction simulation, and application state management. | |
| @maxenlin/mcp-zentao-11-3 cgbznb/mcp-zentao Enables AI assistants to interact with Zentao 11.x legacy instances, managing tasks, bugs, stories, and test cases, and supports retrieving comments and operation history for tasks and bugs. | |
| CompareFairly MCP Server cgdev2019/comparefairly-mcp Provides AI agents with real-time access to neutral, sourced comparisons across products and services in multiple languages and countries, with tools for searching, fetching detailed comparisons, and listing categories. | |
| dockhand-readonly-mcp cgfm/dockhand_readonly_mcp Read-only MCP adapter for the Dockhand REST API, enabling secure querying of container environments, networks, stacks, and runtime status via STDIO or authenticated HTTP. | |
| books-catalog cggazca/mcp-quickstart A well-documented MCP server that exposes a local SQLite catalog of public-domain books through tools like search, get, filter by genre, top-rated, and catalog stats. | |
| Rapid7 Bulk Export MCP cgisclair29/rapid7-mcp Exports vulnerability and asset data from Rapid7 Command Platform via the Bulk Export API into a local DuckDB database, enabling AI assistants to run natural language queries and SQL analysis with sandboxed security. | |
| gequbao cgitato/gequbao-mcp Enables searching for songs and retrieving direct MP3 play URLs from gequbao.net. Supports both simple keyword search and enriched result lookup. | |
| MCP Think Tool Server cgize/claude-mcp-think-tool Implements Anthropic's 'think' tool for Claude, providing a dedicated space for structured reasoning during complex problem-solving tasks that improves performance in reasoning chains and policy adherence. | |
| video-to-obsidian cgmdeep/video-to-obsidian Enables forwarding Douyin or Bilibili video shares to Kimi for AI analysis and automatically writing the resulting Chinese notes into an Obsidian vault. | |
| empaya-mcp-server cgmorah/cloudways-mcp-server MCP server for Cloudways enabling server management, app deployment, backups, SSL, environment variables, and monitoring via Claude Code. | |
| Kakao Map MCP Server cgoinglove/mcp-server-kakao-map Provides location-based place recommendations in South Korea using the Kakao Map API, optimized for Korean language queries. Supports recommending various places like restaurants, shops, public facilities, and tourist attractions based on u | |
| mcp-clickhouse-long-running cgrdavies/mcp-clickhouse mcp-clickhouse-long-running | |
| logiwa-mcp-server cgtykctn/logiwa-io-wms--mcp- An MCP server for the Logiwa IO (WMS) API that lets MCP clients work with warehouse data through tools for products, inventory, orders, and reports. |
37,701–37,750 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.