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 |
|---|---|
| DSH Crew ahart9445/dsh-crew Dispatches work from Claude Code, Codex, Antigravity and Grok to real DeepSeek Harness agent sessions while surfacing them as native subagents with live progress, tier and effort presets, escalation, dispatch guardrails and a jobs board. It | |
| mcp-server-atlassian-bitbucket ahartmann475/mcp-server-atlassian-bitbucket Enables AI assistants to interact with Bitbucket Cloud workspaces, repositories, pull requests, branches, commits, and code for listing, retrieval, commenting, searching, diffing, and repository cloning through MCP tools. | |
| Agentic Commerce MCP Demo aharvard/mcp_agentic-commerce Enables interactive restaurant discovery and ordering through a synthetic commerce flow with rich HTML UI. Demonstrates agentic commerce UX with tools to find restaurants, view menus, place mock orders, and generate receipts. | |
| DHIS2 MCP Server ahasan722/dhis2-mcp-server Connects DHIS2 health information systems to AI assistants via the Model Context Protocol, enabling natural language queries for analytics, metadata, and tracker data. | |
| mcp-idea-capture ahashemm-lang/mcp-idea-capture Enables turning a video URL into a transcript and a concise idea summary using yt-dlp, Groq Whisper, and Gemini. | |
| mcp-memory-search ahashemm-lang/mcp-memory-search Enables local semantic and full-text search over Markdown notes through MCP, returning relevant passages ranked by meaning and exact terms without requiring a GPU or hosted APIs. | |
| d365-dmf-mcp ahaugerud/d365-dmf-mcp Imports CSV or Excel files into Dynamics 365 Finance & Operations data projects through the Data Management Framework, generating manifests, resolving entity targets and dependency order, and waiting for execution results. Also exports data | |
| sql-server-mcp ahaugerud/sql-server-mcp A local MCP server for read-only SQL Server / MS Fabric queries. It authenticates as the user via Entra ID and runs one server process per tenant. | |
| plants ahaverty/plants Enables Claude to manage a self-hosted plant-care tracker through natural language, including adding plants, calculating watering and feeding schedules for the user's climate, logging care, snoozing plants, and attaching photos. | |
| llama-mcp-server ahays248/llama-mcp-server MCP server bridging Claude Code to local llama.cpp. Run local LLMs alongside Claude for experimentation, testing, and cost-effective inference. | |
| bucket-mcp ahbidabs/bucket-mcp MCP server that connects Claude to Bucket, enabling semantic search, browsing, reading, and downloading of saved content like Instagram reels, TikToks, tweets, YouTube videos, and notes, plus saving new URLs into the user's Bucket. | |
| FreeCAD MCP ahelja/freecad-mcp Enables an AI agent to drive a live FreeCAD desktop session, allowing it to create and edit geometry, capture views, and export models through MCP tools. | |
| 鱼泡求职 MCP ahellowyy/yupao-mcp Enables MCP clients to search job listings, read complete job descriptions, manage local search presets and candidate pools, and prepare application or message drafts. Optional session-backed chat reading and human-confirmed single-action e | |
| Browser Tools for Claude Code ahelme/mcp-claude-code-browser-tools Enables browser automation (navigate, screenshot, click, type, etc.) for Claude Code via MCP protocol, with a Chrome extension for configuration. | |
| Multi-Feature MCP Server ahemavathy/mcp Provides comprehensive functionality including weather data, system utilities, Azure cloud management, and AI-powered image generation and editing. Features interactive parameter selection through MCP elicitation for enhanced user experienc | |
| travelmind-mcp aheng0820/travelmind-agent-lab MCP server for multi-agent travel planning, orchestrating parallel expert calls to generate structured itineraries and persist them to SQLite. | |
| buffer-mcp ahernan2/buffer-mcp Enables managing Buffer social media posts via Claude, including creating, scheduling, and viewing posts across connected accounts through Buffer's GraphQL API. | |
| Super Debugger ahernandezvega907-crypto/super-debugger An MCP server that lets AI agents debug Python code by running scripts, setting breakpoints, stepping through execution, inspecting live variable values, and editing or reverting files to verify fixes. It relies only on Python's standard sy | |
| Terminal Control MCP ahernresearch/terminal-control-mcp Enables MCP clients to manage remote Linux terminals over SSH, supporting multi-host and jump-host command execution, background task control, and SFTP file writes, edits, and verified uploads. | |
| vercel-jev-mcp ahesui/vercel-jev-mcp Enables MCP clients to obtain typed Jev judgments (Choice, Score, and Noul answers) through the Vercel AI Gateway with a single API key, using nine deadline-aware tools and offline mock testing. | |
| Agent Evaluation and Red-Team Platform ahines99/agent-eval-redteam Enables users to run synthetic support-agent evaluations, preserve and inspect traces, score results deterministically, inject failures, and enforce release review gates through MCP tools, resources, and prompts. | |
| portco-mcp ahines99/portco-data-onboarding A typed stdio/HTTP MCP server that lets agents drive governed portfolio-company data onboarding: profiling sources, inferring entities and joins, proposing canonical mappings, generating and sandbox-testing dbt artifacts, and publishing onl | |
| Relay ahirmaan/relay-graph Gives MCP-compatible AI assistants one shared, append-only memory stored as a graph, so facts persist across tools and sessions with their full reasoning chain. Enables finding disagreements between tools, resolving them by recording a winn | |
| finn-mcp ahk-coder/finn-mcp An MCP server that provides access to finn.no, Norway's largest online classifieds marketplace, enabling searches and listing retrieval across used goods, real estate, cars, and jobs. | |
| mcpstead ahkohd/mcpstead MCP Gateway that aggregates multiple upstream MCP servers into a single endpoint with persistent connections, tool registry, and authentication. | |
| Snicksnack-mottagare ahlstrominfo/snicksnackserver Enables agents such as Claude Code, Cursor, and claude.ai to search and read received speech recordings and retrieve signed audio links, using an agent key or OAuth. | |
| LeetCode MCP Server ahm215/leetcode-mcp An MCP server that provides tools to interact with the LeetCode API, enabling problem fetching, code template generation, and solution execution/submission. | |
| Nasl3yn DataHub MCP Server ahm22004/nasl3yn-datahub MCP server for cinematic context platform, enabling video asset management, lineage tracing, and pipeline orchestration via DataHub. | |
| commit-brief ahm3d-karim/commit-brief MCP server that turns git commit history into concise standup summaries, exposing tools to summarize and list commits with filters like repo, author, and time range. | |
| SilverBullet MCP Server ahmad-a0/silverbullet-mcp Enables LLMs to interact with SilverBullet notes and data through a bridge server. Provides secure access to read and manipulate your SilverBullet space via standardized MCP tools and resources. | |
| Leave Manager MCP Tool Server ahmad-act/local-ai-with-ollama-open-webui-mcp-on-windows A centralized employee leave management system that allows users to check leave balances, apply for leave, and view leave history through an OpenAPI interface. | |
| MCP Server with Authentication ahmad-act/mcp-server-with-authentication-and-testing-with-inspector Implements a secure MCP server with API Key and JWT authentication, providing tools like echo, login, secure_action, and admin_action. Includes MCP Inspector integration for testing and debugging. | |
| Multiple MCP Servers Framework ahmad-act/multiple-mcp-servers-using-fastapi-and-testing-with-inspector Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector. | |
| co-scientist-plugin ahmad-jaradat-space/co-scientist-plugin MCP server that lets AI assistants like Claude Code and Codex drive the co-scientist engine to generate, review, rank, and evolve scientific hypotheses via an Elo tournament. | |
| snowmcp ahmad-shafique/sn-mcp-hermes-combo Enables agents to interact with a ServiceNow instance through thirteen consolidated tools covering records, schema, CMDB graph traversal, catalog, attachments, code, operations, knowledge, and administration, with a local store for notes, c | |
| ds-mcp-server ahmad-zurih/ds-mcp-server Provides data science, plotting, statistics, system, and web tools via MCP, with interactive CLI clients for OpenAI-compatible and Anthropic providers. | |
| MCP Server Examples ahmad-zurih/mcp-examples A collection of Model Context Protocol implementations ranging from a minimal hello-world to an autonomous AI agent for software development. | |
| IDA-MCP ahmad009/ida-mcp An MCP server that runs inside IDA Pro for AI tools, exposing reverse-engineering capabilities like function listing, decompilation, and analysis via HTTP. | |
| Seq MCP Server ahmad2x4/mcp-server-seq The Seq MCP Server enables interaction with Seq's API endpoints for logging and monitoring, providing tools for managing signals, events, and alerts with extensive filtering and configuration options. | |
| ledger-mcp ahmadadam97/ledger-mcp Enables AI agents to create accounts, record balanced double-entry transactions, query balances, and reconcile accounts against a SQLite-backed ledger through four MCP tools. | |
| seo-agent ahmadaimee/seo-agent Enables AI agents to access self-hosted SEO data and workflows, including keyword research, rank tracking, competitor insights, backlinks, site audits, and AI visibility. | |
| agy-image ahmadarif-lab/agy-image An MCP server that generates images using the Google AI Pro quota from an existing Antigravity CLI login, calling the image endpoint directly for fast, headless generation from any MCP client. It also reports status without consuming quota | |
| MCP Task Manager ahmadbilal339/todo-mcp-server Enables creating, listing, retrieving, completing, and deleting locally persisted tasks, with filtering by pending, completed, or all status. It also exposes pending tasks as read-only data for clients to inspect. | |
| Proposal Generator MCP ahmaddeveloper17/client-proposal-generator-mcp Generates professional client proposals including timeline, tech stack, price estimate, and milestone breakdown from client requirements. | |
| SEO Audit MCP ahmaddeveloper17/seo-audit-mcp Enables running comprehensive SEO audits on websites, checking meta tags, sitemaps, robots.txt, broken links, headings, duplicate titles, and keyword density through MCP tools. | |
| Apple Style MCP Server ahmadeko2017/apple-style-mcp Enables AI coding agents to audit Apple HIG compliance across macOS, iPadOS, and iOS, extract multi-format design tokens, compare UI patterns, and scaffold production-ready React/TypeScript components. | |
| ReelFarm MCP Server ahmadelsaeedd/reelfarm-mcp Enables creating slideshows, managing automations, publishing to TikTok, and searching Pinterest via the ReelFarm API from any MCP-compatible AI client. | |
| codex-bridge ahmadjz/codex-bridge Enables MCP clients such as Claude Code to use the latest Codex CLI as a tool, starting new Codex threads and continuing them with replies, including approvals handling and progress notifications. It keeps the classic codex and codex-reply | |
| Fluid MCP Server ahmadmardeni1/fluid-mcp-server A production-ready MCP server that enables AI agents to interact with the Fluid DeFi Protocol for lending, borrowing, and DEX trading across multiple chains. | |
| MCP n8n API Server ahmadsoliman/mcp-n8n-server Enables listing and triggering n8n workflows, and calling webhooks via the Model Context Protocol. |
24,701–24,750 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.