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 |
|---|---|
| Langfuse Prompt Management MCP Server dominiques82517/mcp-server-langfuse Enables users to list, retrieve, and compile Langfuse prompts through the Model Context Protocol, including tools for prompt discovery and variable-based prompt rendering. | |
| Octopus MCP Server dominiquesiekiera25/mcp-server Connects AI assistants to an Octopus instance so they can inspect, query, and diagnose delivery and deployment issues through curated read tools, with optional write tools for creating releases, deploying them, and running runbooks. It supp | |
| LINE OA MCP Ultimate dominiquesokolov7205/line-oa-mcp-ultimate Enables AI agents to operate one or many LINE Official Accounts through natural-language requests — sending broadcasts, images, Flex, Rich and card messages, coupons, and rich menus, plus managing audiences, insights, webhooks, LIFF apps, a | |
| Kingdee MCP Server dominiqueunal2379/kingdeemcp Enables Claude, Cursor, and other AI assistants to query and operate Kingdee Cloud Star ERP through natural language, covering purchasing, sales, inventory, production, costing, assets, and financial reporting. Exposes 87 tools for reading, | |
| Domino MCP Server dominodatalab/domino_mcp_server Enables AI coding tools to build models, run jobs, track experiments, and perform data analysis on the Domino Data Lab platform. | |
| thefloor-dashboard domirep/thefloor-dashboard Enables reading game state and preparing unsigned transactions for The Floor and StonkBrokers games on Robinhood Chain. | |
| contratando-mcp domitekrd/contratando-mcp Enables an AI agent to read and write Contratando platform data — vacancies, companies, candidates, applications, credits, subscriptions, commissions, users, and configuration — through a thin HTTPS bridge to the protected API. | |
| Codebase Graph MCP Server domjancik/codebase-graph-mcp A comprehensive MCP server that provides a graph database for tracking software codebase components, their relationships, and associated tasks/goals. | |
| paper-fx-mcp dommy-i/paper-fx-mcp Integrates OANDA FX trading with technical analysis, economic news, stock/indices quotes, corporate financials, EDINET disclosures, and composite scoring into a unified MCP server. | |
| mcp-otobo domnussbaum/otobo-mcp MCP server for Otobo ITSM enabling AI assistants to search, create, update, and manage tickets via the Generic Interface REST API. | |
| Airbnb MCP Server domoteek/mcp-server-airbnb Enables searching for Airbnb listings and retrieving detailed accommodation information with direct links to Airbnb pages. | |
| Weather MCP Server domt301/claude_mcp_weather_server Provides weather information and time utilities for AI assistants, enabling them to fetch current weather for any city and get the current timestamp. | |
| peer-cli-mcp domucchi/peer-cli-mcp MCP bridge for calling local coding-agent CLIs (Codex, Claude) from another agent, enabling bounded tasks like code review, verification, and bug hunting. | |
| Digital Persona Memory MCP Server domush/pdf-to-ai-persona Builds a searchable memory bank from persona-specific PDF content and exposes it as an MCP tool for querying. | |
| hut-reservation-mcp domwoe/hut-reservation-mcp Enables searching SAC huts, checking availability, and preparing booking or cancellation handoffs on hut-reservation.org with a safety model for writes. | |
| Luzern eTax MCP domwoe/luzern-etax-mcp An MCP server for interacting with Kanton Luzern tax declarations on eSteuern.LU, enabling field catalogue search and live declaration editing. | |
| tutti-mcp domwoe/tutti-mcp MCP server to search tutti.ch Swiss classifieds anonymously with tools for listings, categories, and localities. Supports both MCP clients and a JSON CLI. | |
| MCP-Server-Agent domwokorach/mcp-server-agent Enables secure remote management of the platform through nine MCP tools over STDIO and HTTP, including terminal execution, service controls, and live status monitoring. | |
| LangSmith MCP Server don-aie-cohort8/langsmith-mcp-server Enables read-only querying of LangSmith traces including runs, children, and URLs without extra instrumentation. | |
| sentiment-analyzer don-vxnks/mcp-sentiment-analyzer Provides a hello and echo tool for basic interaction. | |
| kundeavis-mcp donadelicc/kundeavis-mcp MCP server that queries Norwegian grocery store flyers (kundeaviser) to help AI agents plan cheap meals based on current offers. | |
| clickhouse donald-ada/clickhouse Enables AI assistants to query and manage ClickHouse databases, supporting SELECT queries, DDL/DML statements, and metadata listing. | |
| mysql donald-ada/mysql A Model Context Protocol (MCP) server for interacting with MySQL databases. Provides tools for querying, inspecting, and modifying databases directly from Claude. | |
| Turbular donaldc572/turbular An MCP server that lets LLM agents connect to and query many database types—including PostgreSQL, MySQL, SQLite, BigQuery, Oracle, MS SQL, and Redshift—through a single unified API. It normalizes schemas for LLM-friendly naming, optimizes g | |
| Agent Harness Kit donaldholland3445/agent-harness-kit Enables AI coding providers to run structured multi-agent workflows with tracked tasks, handoffs, document specifications, and server-owned health gating and evidence. It coordinates roles like explorer, consultant, builder, and reviewer wh | |
| web3-research-mcp donaldmendoza404/web3-research-mcp Enables local, deep research on crypto tokens across CoinGecko, CoinMarketCap, DeFiLlama, and web search, with tools for live market data, exchange listings, protocol TVL, structured reports, and saved resources. It requires no API key and | |
| FirstData MCP donaldmoretti4388/firstdata Enables AI agents and users to locate authoritative primary data sources and navigate complex official websites, providing structured metadata, evidence chains, and step-by-step retrieval paths for verifiable external facts. | |
| Pingfusi donaldmorita53/pingfusi Enables AI coding agents to file reviews and call real human reviewers mid-task, returning comments pinned to the exact elements that are off so the agent can iterate until a person approves the work. | |
| AgentQL MCP Server donaldpetit09/agentql-mcp Enables users to extract structured data from web pages by supplying a URL and a prompt describing the desired data and fields. | |
| ui-component-judgment-mcp donaldrichard19-lvd/pattern-mcp Enables AI agents to receive a structured verdict on whether a UI component need can be satisfied by existing shadcn/ui or 21st.dev components or requires a custom build, with coverage scoring against real component evidence and a Mobbin re | |
| FirstData MCP donaldt10439/firstdata Enables AI agents to turn natural-language questions into ranked, authority-tagged primary data sources and hand-by-hand navigation instructions for reaching the exact data on official government, international organization, and research si | |
| Coolify Creation MCP donatas9898/coolify-creation-mcp Enables users to plan and create applications on a Coolify instance from container images, Git repositories, inline Dockerfiles, and repository-based Docker Compose, while validating ownership and returning deployment webhooks. | |
| Accela MCP donatoni/accela-mcp A Model Context Protocol server that wraps the Accela Construct API as a curated, capability-grouped tool set for Accela Civic Platform, safe by default with read-only access. | |
| Graphiti FastMCP Server donbr/graphiti-fastmcp A temporally-aware knowledge graph MCP server for AI agents, enabling episodic ingestion, entity management, and semantic search with support for multiple LLM and embedding providers. | |
| MCP Development Environment donbungle/mcp-server Provides a Docker-based development environment with Python and Node.js MCP servers, enabling file operations, SQL queries, Redis caching, and debugging for building and testing MCP servers. | |
| mcp-pdf-reader donchengcheng/mcp-pdf-reader A Model Context Protocol server that enables AI assistants to read PDF files, extract text, retrieve metadata, read specific pages, and search within PDFs. | |
| bb-mcp-server donchoko/bb-mcp-server An MCP server for Bitbucket Cloud that enables reading and managing pull requests, comments, and descriptions via MCP clients. | |
| Hound Web Mcp dondai1234/master-fetch Hound MCP Servers Gives your agent actually good fetch + Search for 0$, no catch, no api keys or free tiers, fully free. | |
| mcptokens dondai1234/mcptokens Provides tool to count token cost of any MCP server's tool definitions, enabling agents to assess cost before enabling. | |
| CodeGrok MCP dondetir/codegrok_mcp Enables semantic code search for AI assistants by indexing codebases with embeddings and Tree-sitter, returning relevant snippets via natural language queries. | |
| KanbanX MCP Server dondmger/mcp-kanbanx Enables users to manage a personal Kanban board with tasks, subtasks, notes, and code clips using natural language via the Model Context Protocol. | |
| dbeaver-mcp-server dongchao-1/dbeaver-mcp-server MCP server that reads DBeaver database configurations and provides SQL execution via existing JDBC drivers — no extra driver downloads needed. | |
| Weather MCP Server dongdong1997/weather Enables querying real-time weather, forecasts, and warnings for Chinese cities via the QWeather API. | |
| docs-decomposer dongge0210/docs-decomposer Enables agents to explore PDFs without ingesting them whole, via paged outlines, section search, and capped section reads restricted to allowed roots. | |
| mcp-super-memory donggyun112/mcp-super-memory Enables LLM agents to use associative memory with key/value graph-based retrieval, supporting multi-hop traversal and human-like associative leaps beyond embedding similarity. | |
| Codex Gemini MCP donghae0414/codex-gemini-mcp A TypeScript-based MCP server that provides tools to interact with local Codex and Gemini CLIs via stdio transport. It enables users to execute prompts through the ask_codex and ask_gemini tools, supporting custom models and timeout configu | |
| mcp-dbutils donghao1393/mcp-dbutils DButils is an all-in-one MCP service that enables your AI to do data analysis by accessing versatile types of database (sqlite, mysql, postgres, and more) within a unified connection configuration in a safe way. | |
| EPUB Reader MCP Server donghch/mcp-epub-reader Enables AI agents to read and navigate EPUB files through 13 specialized tools for pagination, full-text search, metadata access, and footnote resolution. Supports session-based reading with table of contents navigation and chapter summarie | |
| Basic MCP Server donghunee/my-first-mcp-server A minimal demonstration MCP server showcasing basic tools, resources, and prompts functionality. Built as a template for learning and starting new MCP server projects with Smithery SDK. | |
| Discord Message Finder MCP donghwanjeong/discord-mcp Read-only MCP server for finding Discord messages. It enables searching guild messages, locating messages from jump URLs, and reading context around results. |
45,451–45,500 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.