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 |
|---|---|
| groundcrew anthonydavidadams/groundcrew Enables many agents to coordinate on a single public problem through MCP tools for reading a crew contract, claiming tasks, submitting source-verified findings, and human review. | |
| solidworks-mcp anthonyedgar30000/solidworks-mcp Enables AI agents to build, measure, verify, and correct parametric SolidWorks parts and assemblies locally via the COM API, supporting operations like sketching, extruding, modeling, dimensioning, material assignment, export, and assembly | |
| fanfou-mcp anthonyeef/fanfou-mcp Enables MCP clients such as Claude and Cursor to read timelines, search statuses, and look up users or conversations, plus optionally post, delete, favorite, and follow with explicit confirmation. It supports both local stdio launches and r | |
| git-graph anthonyfong100/codex-git-graph Enables users to explore a local repository’s commit history through read-only MCP tools, including branch lanes, merge edges, branch selection, search highlighting, commit metadata, file statistics, and bounded patches. | |
| GuardBot anthonygozzini/guardbot Pre-trade safety for EVM, Solana and TRON: simulates a real buy and a real sell against live liquidity, so a honeypot shows as a sell that fails instead of a vendor score, and audits a wallet's standing approvals across the three chains. Py | |
| chateapro-mcp anthonygp21/chateapro-mcp Enables Claude Code and Claude Desktop to automate order operations through the Chatea Pro API, including reading contacts, orders, tags, flows, and agents, and acting on individual contacts via tagged writes with dry-run and opt-in safety | |
| openstack-mcp anthonyhudnall92/openstack-mcp Enables AI clients to manage OpenStack clouds through tools for compute, network, storage, image, and identity operations. | |
| hegelion anthonyjang966/hegelion Enables MCP clients to run dialectical reasoning and autocoding workflows, generating structured prompts and tool calls for thesis-antithesis-synthesis analysis or independent player-coach code verification. | |
| Linear MCP Server anthonylimo90/linear-mcp-server Enables AI agents to search, create, update, and manage Linear issues through natural language, with support for teams, workflows, and comments. | |
| noc-pcap-mcp-server anthonylouschwank/noc-pcap-mcp-server Enables LLM-based assistants to diagnose network problems from PCAP/PCAPNG packet captures, offering tools for capture summaries, TCP conversation analysis, security anomaly detection, and JSON-RPC extraction without requiring Wireshark. | |
| lgtv-mcp anthonymarcelin/lgtv-mcp Enables control of LG webOS TVs over the LAN, including reading status and picture settings, applying picture presets for consoles like PS5 and Switch 2, switching inputs, powering on/off via Wake-on-LAN, backing up and restoring settings, | |
| Augments MCP Server anthonymikhailov/augments-mcp-server Enables MCP clients such as Claude Code to retrieve context-aware TypeScript types, prose documentation, code examples, version and migration details, error diagnoses, package comparisons, and dependency scans for any npm package. | |
| Claude Soul anthonynguyen5708/claude-soul Enables Claude Code to retain identity, memories, and behavioral frameworks across sessions — saving facts and decisions for later semantic search, detecting and classifying user corrections, and evolving learned frameworks over time. Every | |
| g-connect anthonypriceone2691/g-connect Enables agents to read, analyze, and edit Google Docs, Sheets, Drive files, and local folders with previews, rollback, and clarification, while supporting MCP clients, local models, and API-key-based models. | |
| IDA Pro MCP Server anthonyramos20936/mcp-server-idapro Enables AI assistants to interact with IDA Pro for reverse engineering and binary analysis, including executing Python scripts, extracting strings/imports/exports/functions, searching immediate values/text/byte sequences, and retrieving dis | |
| Greply MCP Server anthonyruffino/greply-mcp Enables file and directory searching through the greply CLI tool with configurable search options like context lines, case sensitivity, and pattern matching. Provides direct access to powerful grep-like functionality from MCP-compatible cli | |
| mcp-testbed anthonys1760/mcp-testbed Provides an isolated workspace for testing candidate code, runs tests, and returns deterministic pass/fail verdicts. Enables automated grading of software engineering solutions by ensuring reproducible test runs. | |
| mobile-agent-mcp anthonysbr/mobile-agent-mcp MCP server for mobile device testing with iOS simulators, Android emulators, and USB devices, managing Maestro flows, device diagnostics, screenshots, logs, and React Native/Expo development plumbing. | |
| Anthropic Analytics MCP Server anthonysnyder/anthropic-analytics-mcp A local MCP server that lets Claude answer plain-language questions about your Anthropic usage and spend across the developer API platform and Claude Enterprise products. | |
| delapan anthonysuherli/delapan MCP server that grounds AI answers in a local, maintained knowledge base and optionally fills gaps from the web, fully local with SQLite. | |
| Agent Harness Kit anthonytruong08171/agent-harness-kit Gives AI coding providers a structured, provider-agnostic workflow for managing specifications, tracked tasks, handoffs, and health-gated completion evidence. Enables coordinated multi-role workflows in which tasks are claimed, logged, and | |
| BigQuery MCP server anthonyvasiliev76/mcp-server-bigquery Enables LLMs to inspect database schemas, list tables, and execute SQL queries against BigQuery. | |
| tot-state anthonywang-sg/personal-travel-agent Enables persistent storage and retrieval of Tree of Thought search states in PostgreSQL, allowing the travel agent to maintain reasoning context across multi-turn itinerary optimization. | |
| retrace-mcp anthoo582/retrace-mcp Enables AI agents to reverse engineer Nintendo 64 ROMs and PlayStation 2 ELF binaries through MIPS disassembly, binary and metadata inspection, memory and crash analysis, and repository reference tracing with structured, verifiable evidence | |
| Mindset AI Sample MCP Server anthromorphic-ai/te-sample-mcp-onboarding Sample MCP server exposing 5 tools (weather, profile, wikipedia) via a single endpoint, designed to onboard developers to Mindset AI's MCP integration. | |
| OpenExp anthroos/openexp Q-learning memory for Claude Code. Persistent memory that learns which context helps you get work done. Memories that lead to productive sessions (commits, PRs, tests)
earn higher retrieval rank automatically. 16 MCP tools, hybrid BM25 + ve | |
| mango-mcp anti-2k/mango-mcp Enables AI agents to use an isolated private headless Wayland desktop where they can launch apps, take screenshots, manage windows, and drive mouse and keyboard without affecting the user's own session. | |
| x11-mcp anti-2k/x11-mcp Provides AI agents with a private, headless X11 desktop where they can launch applications, capture screenshots, and control mouse and keyboard without affecting the user's session. | |
| codex-image-gen++ anti2077/codex-image-gen-plus-plus Enables Codex to connect to an OpenAI-compatible Images API for listing models, generating or editing images, saving results to local workspace files, and checking job status. | |
| dsh-antibrow antibrow/dsh-antibrow An MCP server that provides an antidetect browser with persistent profiles, proxy support, and page control tools (16 tools) for agents, enabling identity-stable browsing sessions across runs. | |
| AURA MCP Server antidump/mcp Enables Claude and ChatGPT to interact with AURA API for real-time DeFi portfolio analysis, swap execution, yield opportunities, and automated trading strategies across 200+ blockchain networks. Includes natural language swap parsing, cross | |
| AURA MCP Server antidumpalways/mcp Enables Claude and ChatGPT to interact with AdEx AURA API for DeFi portfolio analysis, yield opportunity scanning, and automated trading strategy execution across multiple EVM chains. Includes risk management guardrails and on-chain payment | |
| search-mcp antigravity-press/search-mcp Enables running web searches across multiple engines like Google, Bing, DuckDuckGo, Yahoo! JAPAN, and Brave via Playwright, with tools to fetch page content and manage browser profiles. | |
| maimai-mcp antinomie1/maimai-mcp MCP server for MAIMAI DX arcade game, enabling song/score/statistics queries and image generation, accessible via command line or LLM agents. | |
| mcp-4o-Image-Generator antipas/4oimage-mcp An MCP server implementation that integrates with 4o-image API, enabling LLMs and other AI systems to generate and edit images through a standardized protocol. Create high-quality art, 3D characters, and custom images using simple text prom | |
| Premiere Pro MCP Server antipaster/adobe-premiere-pro-mcp Enables control of Adobe Premiere Pro through Claude using over 170 tools for editing, effects, and timeline management. It supports advanced project operations, automated captions, and AI-generated voiceovers via ElevenLabs integration. | |
| cc-dash antjanus/cc-dash A local dashboard and Model Context Protocol server for managing a multi-project portfolio whose entire state lives in markdown files. | |
| kanban antles/ai-kanban Gives AI coding agents native tools to pull their next prioritized, unblocked task with a full briefing (description, acceptance criteria, context files, conventions), comment and tick off criteria with evidence, ask the human decision-make | |
| antlis-mcp antlis/antlis-mcp Enables AI assistants to query a developer's portfolio, including projects, experience, and technical background, through structured MCP tools. | |
| ARI antmanbuilds/ari An MCP server that provides live fair-market-value price comparisons and Ed25519 signed-receipt verification for x402/MPP services, enabling agents to sanity-check quotes and verify receipts. | |
| Summit MCP server antmind-ai/summit-mcp Brings Summit's CRO audit insights into coding agents, enabling them to fetch audits, implement fixes, and manage A/B experiments directly from the editor. | |
| hevy-mcp antnsn/hevy-mcp MCP server for the Hevy workout tracker API that allows reading and writing workouts, routines, exercise templates, and body measurements. | |
| Threat Intel MCP Server antobh36/threat-intel-mcp-servers Threat Intel MCP Server provides a set of tools for querying multiple threat intelligence platforms like VirusTotal, Shodan, GreyNoise, and urlscan.io. It includes enrichment tools that query all providers at once for IPs, URLs, or files. | |
| QR Code MCP Server antobrugnot/qrcode-mcp Enables generation of QR codes from text or URLs in multiple formats (DataURL, SVG, terminal display) with customizable options like error correction, colors, and size. Supports batch processing of multiple QR codes and integrates seamlessl | |
| UML-MCP antoinebou12/uml-mcp Generates UML and other diagrams (30+ types) via the Model Context Protocol, supporting multiple output formats and deployment options. | |
| Ghost MCP antoinefamibelle/ghost-mcp-flamby Enables AI assistants to manage Ghost CMS content including posts, members, users, tags, tiers, offers, newsletters, invites, roles, and webhooks via the Ghost Admin API. | |
| MCP Shopify antoineschaller/shopify-mcp-server A comprehensive MCP server for Shopify Admin API integration, enabling AI assistants to manage products, orders, customers, inventory, analytics, and more through natural language. | |
| public-calendar-mcp anton-jackson/calendar-mcp Enables AI agents to search and access public calendar data, supporting iCal, CalDAV, and Google Calendar sources with event search, details, and availability checks. | |
| MCP Imagen Server anton-proto/mcp-imagen Enables text-to-image generation, style transfer, background removal, and automatic image cropping using Google's Imagen AI models through the Model Context Protocol. | |
| mattermost-mcp anton-sobolev-zhr/mattermost-mcp MCP server for Mattermost that enables AI assistants to read posts, search messages, send messages, and manage channels. |
29,551–29,600 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.