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 |
|---|---|
| SAP Released Objects Server clementringot/rosa Enables AI agents to check real-time SAP object release status for ABAP Cloud and Clean Core, and find successor objects, via MCP or REST API. | |
| Email MCP Server clemsai/agents-mcp-servers Give AI agents their own email inboxes. Create, send, receive, and manage email entirely via MCP tools. | |
| Cleo Compliance Skills MCP cleo-labs-ia/skills_library Cleo Skills MCP turns 45 production-grade product-compliance skills into a native MCP server.
Cosmetics, food, electronics, toys, textiles, supplements, medical devices, customs, recalls, claims, sustainability — exposed as MCP resources (s | |
| postgres-mcp cleondev/postgres-mcp Enables MCP clients to inspect and query a shared PostgreSQL database safely, running one read-only statement per call with bounded rows and timeouts. Write tools appear only when explicitly enabled, and the database connection is supplied | |
| @clervo/mcp clervo/clervo A stdio MCP server backed by the TypeScript SDK that exposes frozen Clervo operations for web search and answer functionality, enabling agents to find and understand information through a clean-room outcome infrastructure. | |
| Chaprola MCP Server cletcher/chaprola-mcp Provides AI agents with 40 tools for structured data storage, querying, web search, URL fetching, scheduled jobs, and execution through the Model Context Protocol. | |
| Xpenser cleverbrush/xpenser xpenser.cleverbrush.com is a ln open-source, self-hostable personal expense and income tracking app supporting different currencies, categories, vendors, automated invoice parsing, AI geberated reports and more. | |
| OctaDezx MCP cleverfox-77/octadezx-mcp OctaDezx MCP lets users connect their LLM and AI agents with OctaDezx | |
| Glitchtip MCP Server clevermobi/glitchtip-mcp Enables interaction with Glitchtip error tracking platform through natural language. Provides access to issues, events, projects, teams, and organization management for comprehensive error monitoring and debugging. | |
| drupal-modules-mcp MCP Server cleversoft-it/drupal-modules-mcp This TypeScript-based MCP server implements a simple notes system, allowing the creation, listing, and summarization of text notes using MCP concepts with note:// URIs and metadata. | |
| Drupal-Modules-MCP MCP Server cleversoft-it/drupal-tools-mcp This TypeScript-based MCP server allows users to manage and interact with a note system through Model Context Protocol, enabling note creation and summarization with URIs and metadata. | |
| VeriLock MCP clevertech-os/verilock-mcp Provides read-only access to VeriLock document metadata and cryptographic evidence, enabling clients to list, retrieve, verify, and audit documents through the Model Context Protocol. | |
| Paseo Semantic Index cleverunicornz/paseo-semantic-index Provides worktree-aware semantic code indexing and search via MCP, enabling agents to query indexed code and monitor indexing status while keeping lifecycle operations separate. | |
| mcp-coco clew-code/mcp-coco Bridges OpenClaw and Hermes Agent, enabling multi-turn conversations, messaging via Hermes channels, and health checks through MCP tools. | |
| MCP CoCo clewcode/bus-agent Bridges OpenClaw and Hermes Agent to enable messaging, multi-turn conversations, and health checks via MCP tools. | |
| awesome-coolify-mcp clezcoding/awesome-coolify-mcp Enables managing multiple self-hosted Coolify instances via MCP, with tools for deploying, monitoring, and emergency operations. | |
| dameng-mcp-server clgclg/dameng-mcp-server Enables AI assistants to interact with Dameng databases through MCP, supporting query execution, schema exploration, and connection management. | |
| Snowfort Circuit MCP clharman/circuit-mcp A comprehensive Model Context Protocol (MCP) server suite that enables AI coding agents to automate both web browsers and Electron desktop applications with auto-snapshots and element references. | |
| clicbase clicbase/mcp Enables provisioning and administering Clicbase PostgreSQL databases from an MCP client, including creating databases, running SQL, retrieving credentials, enabling realtime, and configuring OAuth and SMTP. | |
| Prior Authorization System MCP Server click2code/mcp-server End-to-end Prior Authorization decision-support system with a multi-agent AI pipeline, MCP Tool Registry, and PostgreSQL backend. | |
| Notion AI Chatbot + MCP Server clickdzpro1/notion-mcp-chatbot Supercharges any Notion workspace with an AI chatbot and MCP server, enabling natural language interaction, search, summarization, and content generation. | |
| GoHighLevel MCP Server clickmediapropy/gohighlevel-mcp-server Connects Claude Desktop to GoHighLevel CRM with 269+ tools across 19+ categories for complete contact management, messaging, sales pipeline automation, e-commerce operations, and business management through natural language. | |
| Clicks Protocol clicks-protocol/clicks-protocol Autonomous DeFi yield for AI agents on Base. Query APY rates, agent status, payment splits, and referral stats. 4 read-only tools + 1 resource. | |
| ollama-mcp clickt-digital-marketing-inc/ollama-mcp Enables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs. | |
| Clixon MCP Server clicon/clixon-mcp Enables AI agents to fetch and query network device configurations from Clixon-based or other RESTCONF-capable devices. It provides tools to extract specific configuration sections, such as interfaces and routing, through the Model Context | |
| deptrust clidey/deptrust deptrust is a CLI that checks package versions for known vulnerabilities across npm, PyPI, crates.io, Go modules, RubyGems, NuGet, Maven, Packagist, pub.dev, CocoaPods, Hex.pm, Hackage, GitHub Actions, and more.
It runs locally as a CLI an | |
| whodb-cli clidey/whodb WhoDB CLI - a powerful database management tool with interactive TUI, programmatic commands, and MCP server for AI assistants. | |
| copernicus-mcp clidyn/copernicus-mcp A self-hosted MCP server that gives LLM agents local, reproducible access to Copernicus environmental data including observations, reanalysis, forecasts, and climate indicators. | |
| Google Ads Campaign MCP clientskatbi/google-ads-campaign-mcp MCP server for managing Google Ads campaigns through the official Google Ads API, covering accounts, campaigns, budgets, keywords, search terms, and keyword ideas. It provides tools for both reading and mutating live ads data, such as pausi | |
| AbletonMCP cliffc2/ableton-mcp2 Connects Ableton Live to Claude AI through the Model Context Protocol, enabling AI-assisted music production and direct control of Ableton Live sessions. | |
| mcp-c64 cliffhall/mcp-c64 An MCP server for developing BASIC and Assembly Language programs for the Commodore 64, providing tools to assemble, tokenize, and run programs in the VICE emulator. | |
| Puzzlebox cliffhall/puzzlebox An MCP server that enables coordination of agents through shared finite state machines (puzzles) where clients can create, monitor, and trigger state transitions of stateful resources. | |
| MCP Meeting Agent cliffordru/mcp-meeting-agent Enhances meetings by providing technology trivia questions, interesting fun facts, and current GitHub trending repositories. Generates formatted meeting notes with engaging content to make meetings more interactive and informative. | |
| project-mcp cliffpyles/project-mcp A FastMCP server that exposes predefined artifacts as Resources and project lifecycle operations as Tools for creating, updating, deploying, debugging, testing, monitoring, and configuring projects with minimal token usage. | |
| Alpaca MCP Server cliffsgpt/alpaca-mcp-clone Enables natural language trading operations through Alpaca's Trading API, supporting stocks, options, crypto, portfolio management, and real-time market data access through AI assistants like Claude. | |
| bitbucket-python-mcp clikader/bitbucket-python-mcp An MCP server for BitBucket Cloud operations that enables AI agents to manage repositories, branches, pull requests, and search code. | |
| Airtable MCP Server clikvn/airtable_mcp Provides read and write access to Airtable databases, enabling LLMs to inspect schemas, search, create, update, and delete records, tables, and fields, as well as manage comments on records. | |
| Proma Manager MCP Server climashscape/proma-manager-mcp Enables to manage Proma skills across workspaces, audit MCP configurations, list and delete sessions with safety checks. | |
| rig-gateway climbhilltmr/rig-gateway Enables an AI agent to inspect and operate a remote Windows machine over a private tailnet, listing and reading files, transferring and mutating them within a configured sandbox root, capturing screenshots, and — only when explicitly double | |
| excel-normalizer climik/excel-normalizer Enables normalizing arbitrary Excel spreadsheets with varied headers into 19 canonical fields and clean JSON, with optional LLM disambiguation and offline fallback. Exposes MCP tools for use in Claude, Cursor, and Windsurf. | |
| Linear cline/linear-mcp Enables managing Linear issues, projects, and teams through Cline. Supports CRUD operations, bulk actions, and rich text descriptions. | |
| GIF Chat clinscott/gif-chat Enables an existing Codex or Claude Code conversation to inspect an original GIF as ordered composited PNG frames, timing, coverage, and source hashes through bounded local tools. It also opens a process-owned picker and supports inspecting | |
| websearch-mcp-server clint419/websearch-mcp-server Enables web search through Exa or Parallel APIs for MCP-compatible AI clients like Cursor and Claude Code. | |
| deep-think-mcp clintmoody/deep-think-mcp An MCP server that provides a structured, persistent scratchpad for hard reasoning, with staged reasoning and self-critique, built for local models. | |
| fundgraph clippycommits/fein An MCP server that gives investment teams an entity-resolved knowledge graph of people and organizations, enabling graph-based retrieval like warm introductions and relationship analysis from scattered data sources. | |
| ClipSense MCP Server clipsense/-mcp-server Enables AI-powered analysis of mobile app bug videos through screen recordings. Analyzes crashes, UI issues, and unexpected behavior in React Native, iOS, and Android apps to provide root cause identification and code fix suggestions. | |
| @clipy/mcp clipy-recorder/clipy-mcp Enables AI agents to search and read screen recordings from Clipy, including transcripts, AI summaries, and key moments with frames. | |
| @cliqo/mcp cliqo-link/cliqo-mcp Enables users to manage short links via cliqo.link, including creating, listing, viewing, and revoking links, as well as checking credit balances. | |
| SkillMCP clivechung/skillmcp Enables centralized, versioned management and distribution of AI agent skills through a horizontally scalable MCP server, allowing agents to dynamically discover, search, and retrieve skills over HTTP/SSE. | |
| mobile-debug-mcp clivejefferies/mobile-debug-tools A minimal, secure MCP server for AI-assisted mobile development, enabling build, install, interact, and inspect Android/iOS apps. |
39,301–39,350 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.