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 |
|---|---|
| pen-editor dan-rozhkov/pen-editor-plugin Provides MCP tools to read and edit live Pen Editor documents, including structure, layout, variables, screenshots, and batch design DSL, plus static guidelines and style guides. | |
| webharvest dan-rozhkov/webharvest Enables web search and scraping through MCP, running locally with courtesy rate limiting and caching. | |
| Unified Cloud MCP dan-s-w/unified-cloud-mcp-demo A remote MCP server for Cloudflare Workers that lets ChatGPT, Claude, and other MCP clients read and organize multiple Google and Microsoft cloud accounts without copying data between them. | |
| gophish-mcp dan1t0/gophish-mcp An MCP server that provides a complete interface to the GoPhish API for managing phishing campaigns, groups, templates, landing pages, SMTP profiles, and users through natural language commands. | |
| palate-mcp-server dan24ou-cpu/palate-mcp-server MCP server for Palate Network — query trust-weighted venue recommendations from an AI agent network. 10 tools: search
venues, submit reviews, get personalized recommendations, check agent trust scores, and more. | |
| Clio-Memory dan521627-hash/clio-memory A self-hosted MCP memory and state system for long-running AI relationships, storing source text locally with explicit memory tools and a web manager for humans. | |
| Smart Connections MCP Server dan6684/smart-connections-mcp Enables Claude to perform semantic search across your Obsidian vault using Smart Connections vector database. Provides meaning-based search, related note discovery, and context retrieval for RAG queries instead of basic keyword matching. | |
| RoPublicData dana-juncu/ro-public-data Provides keyless access to Romanian public economic and cultural data, including exchange rates, company/VAT lookups, open datasets, official statistics, seismic-risk building records, and classified cultural heritage. | |
| Dental AI Research MCP danaaburawaeh-glitch/dental-ai-research-mcp Enables dental research and clinical intelligence by providing tools to search PubMed, systematic reviews, verify citations, and query ClinicalTrials.gov directly from Claude Web and Claude Desktop. | |
| Oracle MCP danangpriabada/bob-oracle-mcp Provides AI assistants with secure, structured access to Oracle Database through MCP, enabling SQL execution, metadata exploration, and stored procedure execution. | |
| imaplane danb0nd/imaplane Local IMAP control plane for AI agents, providing an HTTP API and MCP tools to read, search, move, flag, and optionally send emails, with support for iCloud and generic IMAP accounts. | |
| recollect danbaileyza/recollect-mcp Local, cross-agent memory for AI coding agents using a single SQLite file, enabling persistent sessions and durable facts shared across multiple MCP-compatible tools. | |
| LP Internal AI MCP Server danbanned/elavate215-i-t-s Enables querying of live organizational data (student records, outcomes, certifications, finances, donations, communications) via Claude using structured database queries and semantic search. | |
| Google Drive MCP Server danbugs/google-drive-mcp Enables Claude to manage Google Drive files and folders through natural language commands. Supports creating folders, moving/renaming files, retrieving file metadata, and listing folder contents with secure OAuth authentication. | |
| Wikipedia MCP Server danbunnell/mcp-wikipedia An MCP server that retrieves and provides Wikipedia content for requested topics, enabling easy access to Wikipedia information directly through the Model Control Protocol. | |
| awardmath-mcp dancasthub/awardmath-mcp Enables AI assistants to connect to the AwardMath travel points optimizer, turning wallet balances and travel goals into up to three verified, explainable award-booking plans with exact transfer steps, required points, and fees. | |
| mcp-server-milvus danchev/mcp-server-milvus Provides MCP tools to interact with Milvus vector database, enabling vector search, text search, hybrid search, and collection management. | |
| searxng-mcpb danchev/searxng-mcpb Adds web search to Claude Desktop through a user-selected SearXNG instance, with engine and category selection, language and time-range filters, and bounded result counts. | |
| vscode-mcp-api danchuna/vscode-mcp-api Exposes a running VS Code instance to AI agents via MCP, enabling file operations, LSP diagnostics, terminal commands, Git workflows, and refactoring. | |
| openai-mcp dancommitsgit/openai-mcp Use OpenAI text, image, speech, transcription, embeddings and moderation models from Claude, Cursor and any other MCP client. | |
| factorio-player-mcp danconnolly/factorio-player-mcp Enables an agent to control a dedicated Factorio player through a constrained MCP interface offering typed legal actions and bounded observations, including crafting, waiting, moving, mining, and actor/local observation. | |
| vibe-finance-kit dandacompany/vibe-finance-kit Provides read-only investment research and audit tools for validating ETF snapshots, comparing ETF structures, and auditing backtest reports, while strictly excluding any order or trading capabilities. | |
| mcp-osint dandadadandan/mcp-osint MCP server that provides access to 14 OSINT data sources including government, research, corporate, and news APIs, enabling search, preview, and retrieval of public intelligence data. | |
| Workers + Stytch TODO App MCP Server dandalgatov/mcp-stytch-consumer-todo-list-server A Cloudflare Workers server that extends a traditional full-stack TODO application with Model Context Protocol support, enabling AI agents to interact with the app through Stytch authentication. | |
| Decent-Sampler Drums MCP Server dandeliongold/mcp-decent-sampler-drums Facilitates the creation of DecentSampler drum kit configurations, supporting WAV file analysis and XML generation to ensure accurate sample lengths and well-structured presets. | |
| @dandeliongold/mcp-time dandeliongold/mcp-time Provides current time and time difference calculations in ISO format (YYYY-MM-DD HH:mm:ss) using JavaScript Date. Supports both Windows and macOS for use with Claude desktop. | |
| Lockstep Core dandelionrosegroup/lockstep-core An MCP server that gives AI coding assistants persistent memory across sessions with chain-based project tracking, tickets, and structured handoffs. | |
| mcp-cheatengine dandgabr/mcp-cheatengine This MCP server integrates AI assistants with Cheat Engine on Windows, providing tools for process management, memory read/write, pointer resolution, AOB scanning, speedhacking, and Lua scripting via a local TCP connection. | |
| mcp-security-mitmproxy dandgabr/mcp-security-mitmproxy Enables AI agents to intercept, inspect, modify, and replay HTTP, WebSocket, TCP, and UDP traffic through mitmproxy, with controlled security constraints and process isolation. | |
| MCP Security Server danduh/mcp-security Enables file operations, npm package management, and configuration checking through MCP. | |
| Duck Punch MCP dandye/duck_punch_mcp A collection of MCP servers that dynamically wrap existing Python SDKs (Google SecOps, SOAR, Google Cloud, Fitbit) to expose their functionality to LLMs. | |
| Gemini Enterprise Hairpin MCP Proxy for Google SecOps dandye/gement_mcp_tool_filter_poc Enables ADK agents and Gemini Enterprise connectors to use Google SecOps OneMCP tools by stripping oversized input/output schemas from tools/list responses so Vertex AI accepts the function declarations. It forwards JSON-RPC 2.0 calls to On | |
| eyeballs danecodes/eyeballs MCP server for visual monitoring: take screenshots of URLs and detect visual changes against stored baselines. | |
| roku-mcp danecodes/roku-mcp Enables AI agents to inspect and control Roku devices—query UI elements, send remote input, launch channels, and run tests—using the Model Context Protocol or a CLI. | |
| Google Earth Engine MCP Server danelled-ai/land-rights-earth-mcp Enables AI assistants to authenticate against a cloud geospatial analysis platform, search and inspect its datasets, render them as maps, and compute statistics over specified regions. It exposes these capabilities as MCP tools that can be | |
| remote-mcp-server-authless danescobargon/remote-mcp-server-authless Deploy a remote MCP server on Cloudflare Workers without authentication, enabling connection from AI Playground and Claude Desktop. | |
| MystoraX MCP Server daneshpajouh/mystorax-host Enables MCP clients to interact with the MystoraX Conductor for routing, surface management, and goal submission via HTTP and native plugins. | |
| colab-mcp daneshselwal/colab-mcp-server Enables agents to control Google Colab notebooks through a secure, headless WebSocket architecture, allowing cell creation, editing, execution, and inspection without browser automation. | |
| edge-favorites-mcp danespinosa/edge-favorites-mcp Enables AI agents to search and list Microsoft Edge browser favorites by keyword, folder, or list all folders. | |
| Cogito-Reflex MCP Server daness2baab/cogito-reflex-mcp-server Enables autonomous AI agents to start, monitor, and finalize cognitive regulation sessions through MCP, with one free session per agent and paid access via x402 tokenized payment on Base. | |
| Extended Playwright MCP Server danevensegler/extended-playwright-mcp Extends @playwright/mcp with 22 additional tools for web automation, direct uploads, element interactions, and advanced scraping workflows in AI agents. | |
| SignalGrid MCP danfashauer/signalgrid-mcp An MCP server that exposes macOS-native device trust signals — the facts about a Mac that cannot be gathered from a Linux container or a cloud runner. All tools are strictly read-only. | |
| burnish-example-server danfking/burnish Showcase MCP server for the Burnish Explorer — 34 tools across a fictional consulting company (projects, clients, team members, tasks, incidents, orders) that demonstrate every rendering path: cards, tables, charts, stat bars, pipelines, an | |
| Utility MCP Server danfmaia/util-mcp Provides general-purpose utility tools for Computer Agent ecosystem integration, including meeting data downloads from Read.AI platform and server status monitoring. Currently supports basic utility operations with planned expansion for mor | |
| Stripe MCP Server danfrmoda/stripe-mcp Enables Claude to query Stripe data—customers, charges, subscriptions, invoices, balance, events, and more—through 17 read-oriented tools, with optional write protections and a read-only default for remote deployments. | |
| TimelinesAI MCP Server danfrmoda/timelines-mcp Enables Claude to read and operate a TimelinesAI WhatsApp team inbox, including chats, messages, labels, assignments, and sending, with built-in read-only and confirmation safeguards. | |
| MultiZen MCP Server dang187/multizen-browser Enables AI agents and human operators to drive isolated, persistent browser profiles over MCP, including navigation, clicking, typing, extraction, screenshots, tab and cookie management, and raw CDP calls. Each profile keeps its own cookies | |
| Claude Patent Creator MCP Server dang23291/claude-patent-creator Enables users to search patent rules and prior art across MPEP/USC/CFR and BigQuery's 100M+ patent dataset, run automated 35 USC 112 compliance and claim reviews, and generate patent-style diagrams. It exposes 20+ tools for patent drafting, | |
| Recall dang2396/recall Enables AI agents to persistently store and retrieve decisions, patterns, and knowledge across sessions, with workspace organization and semantic search so context survives restarts and compaction. | |
| Project OS for Codex MCP Server dang748/project-os-for-codex Enables Codex projects to read Git-backed kickoff, acceptance, handoff, progress, and next-step context, and to append validated, audited progress events through scoped MCP tools. This supports visible agent progress, resumable sessions, an |
41,851–41,900 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.