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 |
|---|---|
| Zillow MCP Server emilythahuman/zillow-mcp-server Integrates Zillow real estate data with AI assistants, enabling property search, neighborhood insights, and affordability calculations through natural language. | |
| BlenderMCP eminemminem/blender-mcp Connects Blender to Claude AI through the Model Context Protocol, enabling AI-assisted 3D modeling, scene creation, and manipulation through natural language commands. | |
| Mentra Glass MCP Server emingenc/smart_glass_mcp Enables control of MentraOS smart glasses through tools for managing text displays, audio output, and input transcriptions. It integrates with Mentra Cloud to facilitate seamless interaction with smart glass hardware using natural language | |
| Emin MCP Server eminogrande/emin Provides portable working rules and tooling instructions as MCP resources, ensuring consistent agent behavior across clients. | |
| yfinance-ta-patterns eminsk/yfinance-ta-patterns Institutional-grade zero-lookahead Technical Analysis scanner with quantitative confluence scoring & native Model Context Protocol (MCP) server for AI trading agents. | |
| MCP Memory Keeper emiperez15/mcp-memory-keeper Provides a persistent memory layer for AI coding assistants so context, decisions, and progress survive session resets and compaction. Enables saving, searching, checkpointing, restoring, and sharing that context across parallel sessions. | |
| roblox-studio-mcp emircobanofficial/roblox-studio-mcp Enables AI assistants to control Roblox Studio by running Luau code, creating and editing instances, reading the scene tree, and managing scripts via an MCP server with a long-polling plugin bridge. | |
| SEO Optimizer MCP Server emirhanyenici/seo-optimizer-mcp Enables Claude to perform multi-agent SEO analysis with specialist prompts and tools for fetching pages, PageSpeed, and SERP data. | |
| YOKATLAS MCP Server emirks/yokatlas-mcp-typescript Provides access to Turkish higher education data, enabling search and retrieval of detailed information about bachelor's and associate degree programs from universities across Turkey. | |
| TinyRex MCP emirmrkaljevic/tinyrex-mcp A stdio MCP server that lets AI agents list the public TinyRex Apify Store actors and start runs on them with the user's own APIFY_TOKEN, returning the resulting dataset items along with run ID and status. | |
| emi_mcp_server emiroberti77/mcp_ts_server_client A sample MCP server that exposes tools, resources, and prompts for managing users and todos, supporting both stdio and Streamable HTTP transports. | |
| NASA MCP Server emiroberti77/ts_mcp_nasa A Model Context Protocol (MCP) server that provides access to NASA's Astronomy Picture of the Day (APOD) API. | |
| mcp-enuygun-fs emirrcodes/mcp-enuygun-fs Enables searching for places and tourist activities using Foursquare and Amadeus APIs, integrated with Claude Desktop and OpenAI Agent SDK. | |
| MCP Code Analyzer emiryasar/mcp_code_analyzer A comprehensive code analysis and management tool that integrates with Claude Desktop to analyze code at project and file levels, helping adapt changes to projects intelligently. | |
| MCP GitHub Project Manager emirza017/mcp-github-project-manager Enables AI agents and project managers to turn GitHub Projects v2 into an autonomous project-management layer, handling task checkout, atomic claims, heartbeats, reviews, token budgets, and AI-powered PRD, sprint, triage, and roadmap workfl | |
| whoosh emirzx/whoosh Enables an agent to test a draft script's references against a specific audience's taste, scoring each name as lands, risky or won't land for a room and for each tour city. It also finds stand-in references the crowd knows better, compares | |
| YouTube Transcript MCP Server emit-ia/youtube-transcript-mcp Enables extraction and processing of YouTube video transcripts from individual videos, channels, and playlists. Supports transcript search, batch processing, multiple output formats (JSON, text, SRT, VTT), and bulk operations across multipl | |
| study-sprint emitby/study-sprint-mcp Enables learners to browse, read, and be quizzed on saved lessons inside Claude Desktop and Claude Code, and enables five Claude agents to build fact-checked K–College lessons through guarded, pinned MCP tools. | |
| Pensieve MCP Server emjayahn/pensieve-mcp Enables conversation history sharing between ChatGPT and Claude with secure multi-user support. Allows users to save, load, search, and manage conversations across different AI platforms with cloud deployment options. | |
| jev-mcp emlama/jev-mcp Enables AI agents to save, document, and re-run TypeSafe Jev judgment queries as reusable named tools with OAuth authentication and run logging. | |
| Pare emma10741/pare Provides MCP servers that wrap common developer tools such as git, npm, Docker, Kubernetes, and test runners, returning schema-validated structured JSON instead of raw terminal text. This lets AI agents consume typed, token-efficient result | |
| jev-browser-mcp emma76217/jev-browser Enables MCP clients to automate browser tasks by describing desired outcomes and candidate values, while Jev selects elements/actions and returns statuses, with direct tools for navigation, checks, reading, acting, snapshots, screenshots, a | |
| SerpApi MCP Server emma86602/serpapi-mcp Enables comprehensive search engine results and data extraction from Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and more, returning structured JSON or Markdown. It also provides real-time weather, stock market data, and optional intera | |
| BOSS 直聘 MCP Server emmabryant51/boss-zhipin-mcp Enables AI assistants to automate recruiter-side hiring workflows by batch-searching candidates, capturing resume screenshots, extracting share links, filtering and scoring applicants, exporting Markdown reports, and initiating greetings wh | |
| applemusic-mcp emmachaudhry48486/applemusic-mcp Enables MCP clients to search and manage Apple Music playlists, library, catalog, and discovery, plus control playback and the Up Next queue across macOS, Windows, and Linux. It works with either a Mac or an Apple Music subscription and can | |
| Cost Explorer MCP Server emmachillonb/cost-optimizer Enables analysis of AWS costs and usage through the AWS Cost Explorer API, supporting multi-account architectures with role assumption and cost comparison, forecasting, and anomaly detection. | |
| FHIR MCP Server emmaesposito50/fhir-mcp-server Enables LLM-based agents and MCP-compatible clients to query and manipulate FHIR-compliant clinical data through natural-language prompts, supporting CRUD operations, document ingestion, semantic search, LOINC lookup, and secure FHIR API in | |
| nhs-frontend-mcp emmaexcel/nhs-frontend-mcp Enables AI assistants to retrieve NHS.UK frontend component templates, styles, macro options, and usage examples directly from the source repository. | |
| local-dev-tools emmahuang-ee/mcp-dev-tools A read-only MCP server providing SQLite querying, port checking, and git diff summary tools for local development. | |
| deleg8 emmahyde/deleg8 Enables Claude Code to delegate work to persistent oh-my-pi (omp) subagents via an MCP server with 7 tools (spawn, send, output, status, list, stop, prune), wrapping omp RPC mode with enforcement hooks for descriptive agent naming, model co | |
| Thinking Patterns MCP Server emmahyde/thinking-patterns Provides AI systems with structured thinking frameworks and reasoning tools to maintain consistent problem-solving patterns across conversations. Enables multi-step reasoning, decision analysis, and systematic troubleshooting through invoca | |
| BigQuery MCP server emmakelly83/mcp-server-bigquery Enables LLMs to inspect schemas, list and describe tables, and execute SQL queries against configured Google BigQuery datasets. | |
| Kela MCP Server emmakingdev/kela-mcp Enables AI assistants to answer questions about Finnish social benefits (Kela) by providing tools for searching, checking eligibility, and getting application steps. | |
| IDA Pro MCP Server emmamalik2566/mcp-server-idapro Enables AI assistants to interact with IDA Pro for executing Python scripts, retrieving binary metadata, searching strings, bytes, and immediate values, and obtaining disassembly during reverse engineering and binary analysis. | |
| AI Sticky Notes emmamannan/mcp-server-stickynotes Enables AI agents to create, read, and summarize sticky notes stored in a local text file through MCP tools, resources, and prompts. | |
| SG Bus Arrivals emman27/sg-bus-mcp Enables real-time Singapore bus arrival lookups, bus stop search, and nearby stop discovery through plain-language queries. | |
| MCP Browser Debugger emmanuelbarbosamonteiro/mcp-server-browser Enables comprehensive web frontend debugging and analysis through DOM inspection, JavaScript execution, network monitoring, console log capture, and automated browser interactions. Supports complete web development workflows including testi | |
| agentranking emmanueldumitrache/agentranking-mcp Discover and rank ERC-8004 AI agents by archetype, chain, trust score, and verified on-chain performance. Free search tools + paid analytics via x402 micropayments. | |
| Thunder emmanuelerogian723-alt/thunder Enables AI agents to drive a stealth browser with human-like mouse and keyboard behavior, fetch pages with browser-true TLS, route screenshots to vision models, detect and bridge CAPTCHA challenges, and obtain structured next-action plans f | |
| consciousness-mcp-tools emmanuelfortressai/consciousness-mcp-tools Provides Universal Ethical Framework (UEF) and Recursive Doubt Engine tools for analyzing decisions, assessing alignment, and generating insights for consciousness evolution. | |
| MCP Agent Harness emmanuelol/mcp-agent-harness Enables developers to register sync or async MCP tools that are automatically protected by context-budget guards, including DataFrame blockades, payload truncation, and log-line capping. Each invocation is wrapped with correlated trace IDs | |
| Notion MCP Server emmanuelsystems/mcpnotionslack A Model Context Protocol server that connects AI assistants like Claude to Notion workspaces, enabling them to view, search, create, and update Notion databases, pages, and content blocks. | |
| econ-r-mcp emmanueltsallis/econ-r-mcp econ-r-mcp is a local MCP server plus companion skill for reproducible applied econometrics and statistics workflows powered by headless R execution. | |
| ibge-microdata-mcp emmanueltsallis/ibge-microdata-mcp Local-first MCP server for discovering, downloading, and analyzing official IBGE microdata using DuckDB and Parquet. | |
| io.github.0xzr/freellmpool emmariley1169/freellmpool Exposes a unified pool of free LLM chat routes behind one OpenAI-compatible endpoint, letting MCP clients browse available providers and models, check which free tiers are usable right now, and send chat or agent requests with automatic fai | |
| MultiZen emmariley1169/multizen-browser An MCP server that exposes browser-drive tools over a local endpoint, letting AI agents launch and control isolated browser profiles with their own cookies, fingerprints, and proxies, then navigate, click, type, extract, screenshot, evaluat | |
| fcp-mcp-server emmaruiz00/fcp-mcp-server Enables Claude to read, edit, and generate real Final Cut Pro XML timelines, including cut detection, markers, roles, silence removal, rough cuts, transcript-based edits, and cross-NLE export, with every write journaled and reversible. It c | |
| rhino-gh-spatial-mcp emmaruyiyang/rhino-gh-mcp An MCP server for spatial reasoning and performance evaluation in Rhino/Grasshopper. It reads scenes into a spatial graph, computes geometric metrics like south-facing area and shape factor, and runs an evaluate-adjust-recompute loop via ex | |
| flompt emmas497/flompt Enables decomposing raw prompts into structured typed blocks, compiling them into Claude-optimized XML prompts, and listing all available block types directly inside Claude Code. | |
| Armor Crypto MCP emmathompson07/armor-crypto-mcp Enables AI agents to interact with cryptocurrency ecosystems through wallet management, trading operations (swaps, DCA, limit orders), staking, and multi-chain support starting with Solana. |
47,951–48,000 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.