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 |
|---|---|
| pi-search blessium/pi-search MCP server for pi that provides free web search, web fetch, advanced search, and scholarly paper search via hosted Exa and Parallel services without requiring an API key. | |
| llm-council blessthis/llm-council Blind multi-model councils with anonymous LLM seats and direct 1:1 chat as a local MCP server. Enables asking one question to get independent answers from multiple model CLIs, then blind scoring and reveal. | |
| KiCad MCP Server bleugreen/kicad-mcp Enables analysis of KiCad electronic schematics through natural language queries to search components, trace signal paths, explore connections, and analyze multi-board systems. | |
| Linear MCP Server bleugreen/linear-mcp A high-performance HTTP service that bridges Claude Code or other MCP clients with Linear's GraphQL API, enabling natural language interaction with Linear issues, comments, projects, and other entities without dealing with UUIDs. | |
| Aviation Model Context Protocol blevinstein/aviation-mcp Integration platform for aviation data sources including weather, NOTAMs, airport information, and flight planning APIs, enabling comprehensive pre-flight preparation and in-flight decision support. | |
| local-capability-finder blguunbn/local-capability-finder Provides MCP tools to search a cached index of installed agent skills, MCP tools, and plugins, inspect exact results, and activate skills for supported agents. | |
| Codex Ask User blhsing/codex-ask-user Enables Codex to clarify requirements via native MCP elicitation controls, supporting single/multiple-choice and free-text questions with recommended answers and a discuss-first option. | |
| serial-hub blick-winkel486/serial-hub Lets any MCP-capable AI and a human share a single serial port through one resident daemon, so the AI can read device output, send commands, and drive embedded boards alongside an engineer. It also performs atomic expect→send matching to wi | |
| Google Ads MCP Server blievens89/mcpgoogleads Enables comprehensive Google Ads campaign management and analytics through the Google Ads API. Supports querying campaigns, ad groups, keywords, performance metrics, and executing custom GAQL queries with token-efficient implementation. | |
| mssql-mcp blimyj/mssql-mcp A read-only MCP server for Microsoft SQL Server that allows running SELECT queries and analyzing query performance with statistics. | |
| MCPMaestro blindengineermo/mcpmaestro A self-extending MCP server that enables AI agents to browse the web, execute shell and Node snippets, automate browser workflows, access files and git, communicate with other agents, and use dozens of domain-specific calculation and resear | |
| Skills MCP Server blindex09/mcp Exposes 1,334 skills as global MCP tools across Claude Desktop, VSCode, and Cursor, automatically discovering and categorizing skills from a local directory into 18 categories with semantic search capabilities. | |
| CoinGecko blindvibedev/coingeckomcp A powerful and flexible Node.js Express server that provides a comprehensive interface to the CoinGecko cryptocurrency data API. This server supports both the free public API and the Pro API with automatic fallback. | |
| Browser MCP blink-new/browser-mcp An MCP server for browser automation using Puppeteer that enables AI assistants to navigate web pages, interact with UI elements, and capture screenshots. It supports comprehensive web tasks including form filling, content extraction, and e | |
| Blink MCP Server blinkbitcoin/blink-mcp Enables AI assistants to interact with the Blink Bitcoin and Lightning Network API for managing wallets, payments, invoices, and L402 services. | |
| PromptSmith blinkvoid/promptcore An MCP server that provides 'Reasoning as a Service' by analyzing tasks to select and generate meta-prompts from 40 distinct reasoning frameworks. It enables AI agents to optimize their execution strategy based on task complexity and catego | |
| Physics MCP Server blinkzer0/phys-mcp Enables physicists to perform computer algebra calculations, create scientific plots, solve differential equations, work with tensor algebra and quantum mechanics, and parse natural language physics problems. Supports unit conversion, physi | |
| useblip/email blipemail/blip MCP server for disposable email — create inboxes, receive emails, and extract OTP codes. Let your AI agent sign up for services, wait for verification emails, and extract codes autonomously. | |
| Modular RAG MCP Server bliss-fox/rag-knowledge-assistant-archive Enables building production-grade RAG systems with agentic reasoning, hybrid retrieval, and MCP protocol integration for use with Claude Desktop. | |
| Forge blittlemore/forge-rag Local RAG MCP server for searching meeting notes via the vault_search tool, returning pointers to relevant sections entirely on-device. | |
| iPhone MCP blitzdotdev/iphone-mcp Enables AI agents to control real iPhones and simulators on macOS, allowing for UI interaction, testing, and automation. | |
| Teradata MCP Server blitzstermayank/mcp Enables AI agents and users to query, analyze, and manage Teradata databases through modular tools for search, data quality, administration, and data science operations. Provides comprehensive database interaction capabilities including RAG | |
| pivision bliubliuing/pivision Enables AI assistants to recognize images and videos, and generate images (text-to-image, infographics, image-to-image, batch) through MCP tools. | |
| BLIX MCP blixvip/blixtrade Connects AI assistants to a running BLIX Solana terminal through 20 tools for live launches, coin and holder data, candles, Jupiter quotes, narratives, AI research, wallet analytics, Fomo flow, track records, health, and paper trading. This | |
| Task Manager MCP Server blizzy78/mcp-task-manager This MCP server enables agents to manage complex tasks by providing tools for registration, complexity assessment, breakdown into subtasks, and status tracking throughout the task lifecycle. | |
| Blender MCP Server blkdem/blender-mcp Enables AI clients to control a running Blender instance through the Model Context Protocol, allowing scene inspection, object creation and editing, rendering, and execution of Blender Python. It works locally via a WebSocket bridge between | |
| BLMPay MCP Server blmsoft/blmpay-mcp Enables AI assistants to inspect BLMPay balances, payments, payouts, webhooks, and API capabilities through MCP tools, with write/financial tools disabled by default for security. | |
| gemini-computer-use-mcp block-88/gemini-computer-use-mcp An MCP server that enables browser control agents to plan and execute UI tasks using Gemini Computer Use. | |
| google-ads-transparency-mcp block-town/google-ads-transparency-mcp An MCP server that lets AI assistants look up any advertiser's Google ads. Search by domain or company name, retrieve ad creatives, and decode text ad content from Google's Ads Transparency Center. | |
| MCP Gateway block-town/mcp-gateway Reduces LLM context window overhead by proxying multiple MCP servers through a few efficient dispatch tools instead of registering hundreds of individual tool schemas. It supports multi-account routing and tool discovery for both CLI-based | |
| Jupyter MCP Server block/mcp-jupyter Enables AI agents to interact with Jupyter notebooks via MCP tools for querying, modifying, executing, and setting up notebooks, with state preservation and real-time collaboration. | |
| Square MCP Server block/square-mcp A server that enables interaction with Square's API via Goose, supporting queries for locations, customers, and more with context preservation and MCP-compliant responses. | |
| Code MCP Server block/vscode-mcp Enables AI agents and assistants like Goose or Claude to interact with VS Code through the Model Context Protocol. | |
| Xcode Index MCP block/xcode-index-mcp Gives Goose/Cursor access to your iOS/macOS project index through the Model Control Protocol (MCP) and IndexStoreDB. This provides exhaustive lists of function call sites to help your agent with refactoring and code navigation. | |
| blockbeats-mcp blockbeatsofficial/blockbeats-mcp A crypto data gateway for AI assistants, providing real-time newsflashes, articles, on-chain metrics, ETF flows, stablecoin data, macro indicators, and derivatives market data via the BlockBeats Pro API. | |
| tubemcp blockbenny/tubemcp MCP server that lets AI agents search YouTube and fetch transcripts. | |
| bca-mcp blockchainacademics/bca-mcp-python The canonical crypto MCP server for AI agents, providing access to 3,500+ editorial articles, 200+ entity dossiers, 43 academy lessons, and live market data as native MCP tools with full attribution. | |
| LaunchFast MCP blockchainhb/launchfastmcp Enterprise-grade Amazon & Alibaba intelligence for Claude AI, enabling natural language market research, keyword analysis, and supplier discovery. | |
| LinkedIn Scraper MCP blockchainhb/linkedin-scraper-mcp A remote MCP server for job scraping that enables searching LinkedIn and Indeed for job listings using Apify. | |
| actions-xyz-mcp blockchainpreneur/actions-xyz-mcp Extract structured action items from meeting transcripts and notes using the actions.xyz API | |
| Apollo MCP Server blockchainrev/apollo-mcp-server Enables sales intelligence and outreach automation through Apollo.io's 275M+ contact database. Supports prospecting, contact enrichment, email sequences, workflow automation, and pipeline management. | |
| blockchainlab blockchains/blockchainlab-mcp Gives AI agents (Cursor, Claude, Grok and any MCP client) read-only blockchain knowledge and live on-chain tools: chain metadata, DeFi TVL rankings, EIP/ERC/BIP lookups, grants, hackathons and whitepaper search, plus gas prices, transaction | |
| Apify MCP Server blockhabae-blip/mcp-server Enables AI agents and assistants to extract data from social media, search engines, maps, e-commerce sites, and any other website by running thousands of ready-made scrapers, crawlers, and automation tools as callable tools, with OAuth-base | |
| buddyboss-api-doc-mcp blocklienterprise/buddyboss-api-doc-mcp MCP server exposing BuddyBoss REST API contracts grouped by category for activity, members, groups, messages, and more. Enables listing, searching, and exploring endpoints via natural language. | |
| TrendKia MCP Server blockmandev/trendkia-mcp Enables AI assistants to access and search TrendKia articles, retrieving clean markdown content without HTML scraping. | |
| @blockrun/alpha blockrunai/alpha-mcp An AI-powered crypto trading MCP server providing technical analysis, market sentiment, and token swap execution via 0x and DexScreener. It enables users to manage portfolios with built-in risk limits and search historical trade data using | |
| KOI-MCP Integration blockscience/koi-mcp A bridging framework that integrates Knowledge Organization Infrastructure (KOI) with Model Context Protocol (MCP), enabling autonomous agents to exchange personality traits and expose capabilities as standardized tools. | |
| synthv-assistant blockshy/synthv-assistant Enables local AI-assisted tuning of Synthesizer V Studio 2 Pro projects via natural language, providing tools for reading selections, previewing and applying parameter adjustments, recording and comparing audio, and managing sessions. | |
| MCP Google Play Store Server blocktopusltd/mcp-google-play Integrates Google Play Store management tools with AI assistants to handle app listings, releases, and user reviews. It enables users to manage Play Console tasks like updating store information and retrieving performance statistics through | |
| blofin-mcp blofin/blofin-mcp Provides 40 tools for BloFin cryptocurrency exchange, enabling market data, account management, and trading operations via MCP. |
34,701–34,750 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.