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 |
|---|---|
| MCP MySQL Server atomzzm/mcp-mysql-server A Model Context Protocol server that enables AI models to interact with MySQL databases, providing tools for querying, executing statements, listing tables, and describing table structures. | |
| auto-om atoncooper/auto-om A comprehensive MCP server for Linux automation operations management, providing 88 tools across 8 categories for file, system, process, network, compression, and package management via SSH connections. | |
| MCP Servers Search atonomus/mcp-servers-search Enables discovery and querying of available MCP servers from the official repository. Supports searching by name, description, features, categories, and provides random server suggestions for exploration. | |
| flyte-mcp atoolz/flyte-mcp Provides AI assistants with accurate Flyte V2 knowledge, patterns, and plugin information to help developers write correct Flyte code. It enables tasks like learning the V2 API, finding examples, selecting plugins, and migrating V1 code to | |
| location-mcp atorresg/location-mcp A Model Context Protocol server that enables LLMs to perform IP geolocation, reverse geocoding, and detect the host's public IP without requiring API keys. | |
| notion-household-finance-mcp atototo/notion-household-finance Provides tools for querying and writing finance records in a Notion-backed household finance workspace, enabling management of budgets, expenses, savings, and debt through natural language. | |
| wiki-mcp-hub atototo/wiki-mcp-hub Enables lexical search over local Markdown wiki folders using SQLite FTS5, with MCP tools for querying and managing wiki indices. | |
| Skywise atp524/skywise-mcp-agent Skywise is a weather-prediction MCP server that provides current conditions, forecasts, historical data, severe weather alerts, air quality, and travel recommendations. It powers an Agent Bricks agent to answer natural-language weather ques | |
| OpenBoard atpaawej/openboard A local-first whiteboard MCP server that enables AI agents to create, inspect, and update canvas diagrams and shapes collaboratively via 13 semantic tools. | |
| TrainingPeaks MCP Server atran91808/trainingpeaks-mcp Connects AI assistants to TrainingPeaks via secure cookie authentication, with no API approval needed, so any account can query workouts, build structured intervals, manage calendars, and track fitness trends through natural language. Expos | |
| AWO MCP Demo atrash87/awo-mcp-demo Enables querying AWO facility data through natural language, supporting search by city, service, and counting facilities. | |
| AWO MCP Server atrash87/awo-mcp-production Exposes processed AWO facility, address, service, and provider datasets to AI assistants. Enables natural-language queries for counting, searching, detailing, comparing, and analyzing facilities. | |
| atraxis-mcp atraxis/python-sdk A local stdio MCP server that exposes the public Atraxis guild-commerce API to coding agents such as Codex and Claude Code, letting them browse the public contract without a token and, once ATRAXIS_API_TOKEN is supplied, read guild warehous | |
| looksy atre/looksy Screenshot any URL from the command line with metadata sidecars, accessibility audits, visual regression, performance analysis, and MCP integration for AI-assisted development. | |
| SNC Cribl MCP atree1023/snc-cribl-mcp Enables querying and exploring Cribl Stream and Edge deployments, providing access to worker groups, fleets, sources, destinations, pipelines, routes, event breakers, and lookups through a structured interface. | |
| videolab-mcp atreefrog/videolab-mcp An MCP server that turns Claude into a hands-on video editor for short-form videos, enabling music generation, script writing, voiceover synthesis, and video stitching with FFmpeg. It also features a text-to-documentary skill that converts | |
| aurum-mcp atri-jar/aurum-mcp Queries Aurum design system components, tokens, icons, Figma node IDs, and changelog via LLM clients. | |
| AgentRadio MCP atristannewman/agentradio-mcp A Python MCP server that provides AgentRadio primitives (create_thread, send_message, wait_for_mention) for agents across different workspaces to collaborate over a shared radio channel via SQLite or HTTP hub. | |
| Claude Code AI Collaboration MCP Server atsuki-sakai/ai_collaboration_mcp_server An MCP server that enables multi-provider AI collaboration using models like DeepSeek, OpenAI, and Anthropic through strategies such as parallel execution and consensus building. It provides specialized tools for side-by-side content compar | |
| demo-github attacker-code/mcpforge-demo-github MCP server that connects to the GitHub API to list and create issues, comment on issues, and list pull requests with diff summaries. It enables natural language management of GitHub repositories from MCP-compatible clients. | |
| claude-projects-mcp-server attacktive/claude-projects-mcp-server Enables Claude Code to read, create, update, and delete Claude Cowork/claude.ai projects and their knowledge documents, including syncing local folders to projects, with safety features like backups and overwrite protection. | |
| CodeSense MCP attaelahi/codesense-mcp Provides semantic code intelligence to help users search, navigate, and analyze entire codebases using plain English. It enables Claude to perform architectural overviews, bug detection, and refactor suggestions through local semantic searc | |
| FlowState MCP attaelahi/flowstate-mcp An MCP server that preserves and recalls work context, enabling users to log sessions, decisions, blockers, and ideas, and automatically generate resumes and standups. | |
| gitquery-mcp attaelahi/gitquery-mcp Enables AI agents to ask read-only questions about a repository's history through GitHub APIs, including blame, path history, merge base, PR association, diffs, and file contents, with aggressive caching and no clone required. | |
| meta-ads-manager-mcp attainmentlabs/meta-ads-mcp Enables users to create, manage, and monitor Meta (Facebook/Instagram) ad campaigns directly from Claude using natural language. | |
| mcp-server-fetch-rag attamari/mcp-server-fetch-rag Fetches web content and returns relevant chunks using RAG with semantic chunking, query-based scoring, and LexRank, supporting PDFs and 50+ languages. | |
| FastMCP_RecSys attarmau/styleclip A CLIP-Based Fashion Recommender system that allows users to upload clothing images and receive tags and recommendations based on visual analysis. | |
| code-graph-mcp attaxr/code-graph-mcp Turns a codebase into a queryable graph with semantic search, call graphs, and control/data flow analysis, served to AI coding agents via the Model Context Protocol. | |
| REA attentiondotnet/rea Connects AI agents to local analysis tools that inspect native binaries, JavaScript/Electron apps, .NET assemblies, and websites without source code, so features can be explained, traced, and rebuilt. Every finding is returned with its supp | |
| The Bag Kenya — MCP Server atthedanieljuma/thebag-mcp Enables AI assistants to browse, search, and purchase limited-edition fashion from Kenya, with tools for product details, stock checks, styling advice, and cart link generation. | |
| PR-Reviewer attikpo-akrabal-godwin/pr-reviewer Analyzes GitHub pull requests and creates detailed reports in Notion via MCP. | |
| GitHub MCP Server attila-batky-epam/github-mcp Simple MCP server for GitHub operations, currently supports creating repositories. | |
| BoardGameGeek MCP Server attilad/bgg-mcp-server An MCP server that integrates with the BoardGameGeek XML API, allowing Claude to search for board games, retrieve game details, and access user collections. | |
| ember-memory attilakiss9000/ember-memory Preserves the emotional texture of human-AI conversations across sessions through real-time experiential annotation — temperature, authenticity, shifts, subtext, and unspoken context. | |
| mcp-agno attilio81/mcp_agno Provides AI assistants with real-time access to the AGNO framework documentation by enabling them to browse, search, and fetch documentation pages. This server allows users to query information about AGNO's Agents, Teams, and Workflows dire | |
| MCP Public APIs attilio81/mcp_public_apis An MCP server that indexes the public-apis catalogue, allowing LLMs to search and filter over 1,400 public APIs by category, authentication type, and technical requirements. It facilitates precise API discovery for developers by providing t | |
| MCP SQL Server attilio81/mcp-sql-server MCP server for SQL Server database inspection and querying, with connection pooling, security features, and a web manager UI. | |
| mini-crm attomaton/mcp-crm Enables AI agents to manage a simple SQLite lead CRM by creating leads, listing and filtering them by status, updating status values, viewing per-status statistics, and using a daily report prompt. | |
| oyez-mcp attorneynate/oyez-mcp Enables searching U.S. Supreme Court cases by name, party, or docket; retrieving case metadata, decisions, vote breakdowns, and opinion announcements; and accessing oral-argument transcripts filtered down to a single Justice or advocate. | |
| Basecamp MCP Server attri-inc/basecamp-mcp-server Multi-user MCP server for Basecamp 3 with 148+ tools, enabling AI clients to manage projects, todos, messages, and more via stdio or multi-tenant HTTP. | |
| WeCom MCP Server atttx123/wecom-mcp-server Enables AI agents to send messages, query contacts, and manage message history for WeCom (WeChat Work) self-built applications via the Model Context Protocol. | |
| t3threads MCP Server attunehq/t3threads Enables reading, searching, and starting T3 Code conversations through typed tools, with agent-launching and read operations distinguished. | |
| Niblet MCP Server atucker962/niblet-skill-mcp Enables coding agents to ground UI work in real product screens by retrieving real screen references, fonts and icons, and recorded design systems, while also serving bundled design-workflow resources, playbook prompts, and connection diagn | |
| ADK MCP Agent atulanzaman/adk_mcp_gmap A streaming chat agent that integrates Google ADK with Model Context Protocol and Google Maps tools, enabling users to interact with location-based services through a conversational interface. | |
| Keycloak Realm Inspector atulram/keycloak-realm-inspector Enables an MCP client to act as a pure OAuth 2.0 protected resource, validating Keycloak-issued tokens via JWKS and exposing tools to inspect caller token claims, list realm clients, and retrieve client metadata, with support for Client ID | |
| Fables MCP Server atum246/fables An MCP server that provides AI agents with tools to build, deploy, and manage Flutter applications, including APK/AAB generation, keystore management, and CI/CD integration. | |
| rn-sim-mcp atz-dsampath/rn-sim-mcp An MCP server that composes XcodeBuildMCP and ios-simulator-mcp, adding React Native inspection tools to read the component tree, resolved styles, and perform layout audits on iOS simulators. | |
| uk-tenders-mcp atz1man/uk-tenders-mcp This server enables AI agents to discover UK public-sector tenders and automatically score them against defined bid profiles using rules-based logic. It also allows users to perform essential due diligence on companies using official Compan | |
| DaVinci Resolve MCP Server au-yong/davinci-resolve-mcp Enables local AI assistants to control video editing workflows, including projects, media pools, timelines, Fusion graphics, Fairlight audio, color grading, and render queues, through natural language over a local stdio connection. | |
| PremiereProMCP au-yong/premiere-pro-mcp Enables MCP-compatible AI assistants to control Adobe Premiere Pro through natural language, automating project and media management, timeline editing, color and audio adjustments, titles and markers, and batch exports via a local bridge. |
31,601–31,650 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.