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 |
|---|---|
| DeepLaw eysn0130/deeplaw A read-only Chinese legal evidence MCP server that provides deterministic retrieval of authentic legal sources with chain-of-custody receipts, designed for Codex, Claude Code, and OpenCode. | |
| gsc-mcp-rs eyupcanakman/gsc-mcp-rs MCP server for Google Search Console. 21 tools for search analytics, keyword opportunities, URL inspection, sitemaps, indexing, and property management. | |
| AI Memory eyyit/ai-memory Enables MCP clients to retrieve relevant memories and save confirmed durable facts through authenticated access backed by PostgreSQL provenance and Qdrant semantic search. | |
| K-Stock MCP ez2sarang/kstock-mcp Enables MCP agents to retrieve Korean stock quotes, charts, account balances, disclosures, financials, and IPO schedules, including equal-allocation estimates, via KIS and OpenDART APIs. It is read-only and data-only, with no order tools or | |
| Totem ez4me14/totem-whoop Enables MCP-compatible AI clients to read and write wearable data through Whoop's private iOS API, covering recovery, sleep, strain, journal, strength training, live heart rate, and more via 55 tools. Write operations default to a preview g | |
| GovCon ezbiz-services/mcp-govcon Federal procurement intelligence toolkit that searches SAM.gov contract opportunities, analyzes agency spending patterns, tracks competitor wins, and monitors small business set-aside programs (8a, HUBZone, SDVOSB, WOSB). 4 tools using SAM. | |
| SEO Marketing ezbiz-services/mcp-seo-marketing SEO and marketing intelligence toolkit for keyword research, SERP analysis, backlink checking, content optimization, technical site audits, and content brief generation. 6 tools to improve search engine rankings. | |
| Social Media Analytics ezbiz-services/mcp-social-media Social media analytics toolkit that analyzes profiles, scores engagement, detects trending topics, researches hashtags, generates content calendars, and benchmarks against competitors. 6 tools across all major platforms. | |
| Browser-Agent MCP Farm ezboom1111/browser-agent-mcp-farm Enables AI agents to capture and hash-register browser evidence, enforce cite-or-fail claim checks against registered bytes, and export Merkle-rooted evidence bundles that other agents can re-verify fully offline. | |
| ChatGPT To Codex ezbuilder/chatgpt2codex A local MCP runtime for macOS and Windows that enables ChatGPT to read, edit, search, run tests, and capture screenshots in your local project folder while keeping your source code on your machine. | |
| Image2Flutter MCP ezbuilder/image2flutter-mcp Converts UI screenshots into validated, editable Flutter widgets, with visual diff comparison and preview. | |
| ns-bridge eze-godoy/mcp-server-ns-bridge An MCP server that enables AI assistants to interact with the Netherlands Railways (NS) API for route planning, pricing, and real-time departure information. It provides tools for searching stations, planning trips with connections, and vie | |
| Neo4j MCP Server ezedinff/neo4j-mcp Enables interaction with Neo4j databases from the Cursor IDE by executing Cypher queries, managing connections, and retrieving database information. | |
| pixalate_open_mcp ezedonovan/pixalate-open-mcp Enables AI assistants to query Pixalate's analytics, fraud detection, and enrichment APIs for reporting, risk scoring, and data enrichment. | |
| RankedLM MCP Server ezeh8/tool-access-controller An auditable MCP gateway with JWT authentication and PostgreSQL audit logs, exposing 4 tools for permission validation, audit logging, access request, and history queries. | |
| Tesla Tessie MCP Server ezellm/tessie_mcp Provides access to Tesla vehicle telemetry data via the Tessie API, enabling real-time monitoring of battery status, charging state, climate controls, location, and other vehicle metrics through 30+ tools with intelligent caching. | |
| SharePoint MCP Server ezemriv/sharepoint-mcp Enables interaction with Microsoft SharePoint sites, document libraries, and files through the Microsoft Graph API. Supports browsing, searching, uploading/downloading files, managing lists, and creating sharing links with secure OAuth auth | |
| erickwendel-contributions-mcp ezequiel-da-silva/erickwendel-contributions-mcp An MCP server that exposes tools to query Erick Wendel's talks, blog posts, and videos, supporting filters and pagination, plus prompts and resources for content discovery and summarization. | |
| mcp-documentacao ezequiell22/mcp_rag MCP server that indexes technical documents and provides hybrid search (vector + BM25) for retrieval only, without generation. | |
| shadcn-ui-mcp-server ezequielpereirae/shadcn-ui-mcp-server Provides AI assistants with comprehensive access to shadcn/ui v4 components, blocks, demos, and metadata across React, Svelte, Vue, and React Native, enabling efficient component integration and code generation. | |
| casebook ezerutp/casebook Enables read-only investigation of support cases with an agent by querying OpenSearch, CloudWatch Logs Insights, and MySQL under cost and read-only guards, while providing a live local viewer, resumable sessions, and shared technical memory | |
| VERA MCP Server ezesubu/vera Enables AI clients like Claude Code, Cursor, or VS Code to drive the Unreal Editor: execute Python, capture screenshots, tail logs, check status, and run VERA commands. | |
| FHIR MCP Server ezhdanov825/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to perform full CRUD operations on FHIR resources and query or manipulate clinical data using natural-language prompts. It also supports document ingestion, semantic search, LOINC terminol | |
| Garmin Connect MCP Server ezhil2k/mygarmin_mcp Enables read-only access to Garmin Connect health, activity, profile, and device data through local stdio or streamable HTTP transports for MCP clients. | |
| Medical Research MCP Suite ezhou89/medical-research-mcp-suite Enables comprehensive medical research by querying and analyzing data across ClinicalTrials.gov, PubMed, and FDA databases with AI-enhanced cross-database insights, risk assessments, and competitive intelligence. | |
| BACnet MCP Server ezhuk/bacnet-mcp A lightweight MCP server that connects LLM agents to BACnet devices for building automation, enabling real-time monitoring, actuation, and task orchestration. | |
| MQTT MCP Server ezhuk/mqtt-mcp Enables LLM agents to securely monitor and control MQTT devices for building automation, industrial control, and smart home systems through a standardized MCP interface. | |
| Local MCP Study Tools Server ezitounioussama/mcp-study-tools Enables a study assistant to explain topics, build study plans, and generate revision checklists, with read-only access to course outline and status resources. | |
| bumi-digital-mcp ezmakeai/bumi-digital-mcp MCP server for Bumi Digital that enables AI image, video, and audio generation and upscaling directly from MCP-compatible assistants like Claude Desktop and Cursor. | |
| MCP Gateway eznix86/mcp-gateway Aggregates multiple Model Context Protocol servers into a single gateway to provide unified search, description, and execution of tools. It reduces context limit issues by dynamically fetching specific tool schemas only when needed rather t | |
| claude-sync ezp41nb0w/claude-sync This MCP server enables Claude session to retrieve full project context in a single call by listing projects, reading per-project handoffs, searching the local knowledge base and indexed code, recording cross-project lessons, and rebuilding | |
| SmartSend MCP server ezpost-org/smartsend-mcp Enables any MCP client to operate a SmartSend workspace through its REST API — looking up and searching customers, managing tags, lists, custom fields and blacklists, and sending or scheduling WhatsApp template messages, flows and push noti | |
| XCAutokit ezra-black/xcautokit First-party MCP server and CLI for Xcode and iOS Simulator automation. Enables control of Xcode and iOS Simulator via MCP tools for tasks like building, testing, and automation. | |
| Monarch Money MCP Server ezra-quemuel/monarch-mcp An MCP server that connects Claude (and other MCP clients) to your Monarch Money financial data, allowing you to query accounts, transactions, and budgets, or update transactions and budget amounts through natural language. | |
| local-agent-mcp ezra-y/local-agent-mcp Enables ChatGPT to work directly on local projects by reading files, editing code, running tests and commands, inspecting Git state, and managing durable workflows, with optional delegation to local Codex agents for complex tasks. | |
| switchboard ezraapple/switchboard Enables managing native Codex and Claude Code sessions through a shared interface, allowing agents in one harness to create, read, continue, update, search, and delete sessions in the other. | |
| financecontext-mcp ezrazhang7/financecontext-mcp A remote MCP server that lets LLM agents reason over a user's real financial data using the user's own Supabase JWT for security, offering tools for reading accounts, transactions, spending summaries, and drafting rules with human approval. | |
| google-sheets-mcp ezrazhang7/google-sheets-mcp An MCP server that lets Claude read, edit, and format Google Sheets in place, including cell updates, formula filling, row/column operations, and find & replace. | |
| Google Tasks MCP ezrazhang7/google-tasks-mcp An MCP server that lets Claude manage Google Tasks, including listing, creating, updating, completing, moving, and deleting tasks and task lists. It supports both local and remote deployments and can be used with Claude Desktop or as a Clou | |
| legislation-nz-mcp ezydubs/legislation-nz-mcp Enables MCP clients to search New Zealand legislation, browse point-in-time versions of Acts, Bills, and secondary legislation, and read the text of sections or schedules via the official legislation.govt.nz developer API. | |
| seek-mcp ezydubs/seek-mcp Enables MCP clients to search New Zealand job listings and read full ads without signing in, and—once authenticated—manage the account profile and résumés, save or list jobs, inspect application requirements and submit real applications wit | |
| tradingview-mcp ezydubs/tradingview-mcp Enables AI-assisted chart analysis, Pine Script development, and live order execution on TradingView Desktop via Chrome DevTools Protocol, supporting connected brokers for trading workflows. | |
| ui-mcp ezzcodeezzlife/ui-mcp Enables agents to render shadcn-styled dashboards, forms, charts, and comparisons in a local browser via MCP tools. | |
| mcp-server ezzeay/mcp-server Production-ready TypeScript MCP server exposing utility, GitHub, and Microsoft Teams tools over stdio. | |
| House of Wisdom MCP ezzohamdan/house-of-wisdom-mcp Enables querying multiple AI models simultaneously and returns all answers unmerged for the user to weigh. | |
| mcp-surveys ezzysoft/mcp-surveys Public MCP server for agent-created, human-friendly, short-lived surveys. Enables agents to ask structured questions and retrieve answers. | |
| tradingview-mcp-review f-e-u-e-r/tradingview-mcp A review-only MCP server that provides tools for reviewing trade records against a live TradingView Desktop chart over Chrome DevTools Protocol on localhost. | |
| Ableton Copilot f-fischer/ableton-copilot Enables AI-powered music production in Ableton Live through natural language, with tools for composition, arrangement, mixing, and sound design. | |
| MCP Easy Copy f-is-h/mcp-easy-copy A Model Context Protocol server that automatically reads the Claude Desktop configuration file and presents all available MCP services in an easy-to-copy format at the top of the tools list. | |
| mantis-mcp f-liva/mantis-mcp Enables natural language interaction with MantisBT issues and notes via CRUD operations and semantic search. |
49,251–49,300 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.