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 |
|---|---|
| ChatGPT Subscription MCP corith37/chatgpt-subscription-mcp Enables Claude Desktop to ask OpenAI questions and generate or edit images through a local Codex bridge, using an existing ChatGPT subscription sign-in without an OpenAI API key. | |
| cork-defi cork-technology/cork-cli Enables interaction with the Cork DeFi protocol for reading live chain state, computing bit-exact math, building unsigned bundles and orders, and managing markets, all without signing or broadcasting. | |
| Cork Protocol Model Context Protocol cork-technology/cork-mcp Typed MCP gateway for Cork Protocol operations, enabling secure and deterministic interaction with operation core and signing gate. | |
| dalicore-mcp-client corlzee/dalicore-mcp-client Streamlined MCP server with 8 essential tools for file operations, code editing, and command execution, covering 97.5% of actual workflow with minimal overhead. | |
| hikvision-mcp cormac-rynne/hikvision-mcp Enables safely inspecting and configuring Hikvision cameras via a local MCP server, with permission enforcement, read-only diagnostics, and supervised mutation flows. | |
| Web Fetch MCP Server cormickkneey/web-fetch-mcp Provides tools to fetch web content in HTML, JSON, text, or Markdown formats via MCP. Supports custom headers, length limits, and start index. | |
| bookmark-lens cornelcroi/bookmark-lens Enables AI assistants to save, search, and manage bookmarks with semantic search, automatic metadata extraction, and optional LLM-powered enrichment, all running locally. | |
| Context Lens cornelcroi/context-lens An MCP server that enables semantic search over local files or GitHub repositories by indexing content into a serverless vector database, allowing AI assistants to understand meaning rather than just keywords. | |
| mcp-data-lens cornelcroi/data-lens Enables users to ask questions about their spreadsheets in plain English and receive instant answers using DuckDB-powered analytics, supporting multiple file formats like Excel, CSV, and Parquet. | |
| French Tax MCP Server cornelcroi/french-tax-mcp Enables AI assistants to calculate French individual income tax and retrieve current tax brackets using official government data. Supports household composition calculations and provides up-to-date tax information for French residents. | |
| batch-coverage corner123/batch-coverage Enables agents to freeze the real inputs of a file or JSONL batch, then audit current outputs for missing, duplicate, unexpected, or malformed results and resume from the item IDs that still need repair. Runs locally over stdio with CPU onl | |
| @aibtc/mcp-server cornerblue/aibtc-mcp-server-orphan Bitcoin-native MCP server for AI agents: BTC/STX wallets, DeFi yield, sBTC peg, NFTs, and x402 payments. | |
| Documents MCP Server corneyc/documents-mcp A production-ready Model Context Protocol server that bridges local document management with cloud synchronization (Notion) for AI agent integration, enabling seamless access and sync of local and cloud documents. | |
| BotDuaChuot MCP cornhub69-x/botduachuot_mcp MCP server that enables ChatGPT to read/write files, run commands, and perform offline investigation tasks (geo, forensics, OSINT) on the host machine, scoped to a workspace with OPSEC controls. | |
| poe2-build-planner cornndawwg/poe2-build-planner-claude-tool Enables Claude Desktop users to turn a Path of Exile 2 character concept into a playable build plan, including skills, supports, passive tree paths, leveling phases, gear/stat priorities, viability estimates, and trade search links. It can | |
| chrome-devtools-mcp-wrapper cornworld/chrome-devtools-mcp-wrapper Shares one Chrome browser across multiple AI coding sessions via an MCP proxy, adding lifecycle management, tool filtering, and anti-detection while wrapping the upstream chrome-devtools-mcp server. | |
| Database MCP Server cornyu/mcp-server-databases Enables SQL queries, schema exploration, and Oracle sequence management across multiple databases including Oracle, OceanBase, and DolphinDB. Supports multiple environments with secure password handling. | |
| Corpo MCP Server corpollc/corpo-mcp Enables AI agents to explore and prototype Wyoming DAO LLC formation workflows in a sandbox environment. | |
| general-agentic-management-mcp corporatetraveldc/agentic-management-tooling-mcp Enables querying aviation weather, FAA TFRs, NWS alerts, flight tracking, and Amtrak train status using public APIs. No API keys or private infrastructure required. | |
| CorporateTravel Dispatch MCP corporatetraveldc/corporatetravel-dispatch-mcp MCP server exposing CS Executive Services dispatch platform and airplanes.live flight tracking as portable, agent-agnostic tools. | |
| CORPUSfm corpusfm/corpusfm Enables AI assistants and automation to inspect, compare, and manage FileMaker schema artifacts via MCP, including exploring objects, tracing references, generating diffs between versions, and automating schema tasks through jobs. | |
| corpusiq corpusiq/corpusiq-docs Cross-source attribution across 37+ business tools. True ROAS in 14 seconds. Not a dashboard. A decision. | |
| Clerk MCP Server correaito/mcp_clerk Enables complete user management for Clerk authentication service through MCP. Supports listing, deleting, locking, and unlocking users with secure API integration. | |
| correctover-runtime-guard correctover/runtime-guard Provides real-time RCE, SSRF, and env leak interception for AI tool calls, with MCP server mode offering diagnostic and repair suggestions. | |
| nooon corrupt952/nooon A lightweight, read-only MCP server for Notion that enables searching, reading pages, and querying databases with token-efficient output and smart caching. | |
| corrupt-cli corruptfun/corrupt-mcp Generates production-ready, white-labeled web architectures (Next.js + Supabase or static) from vertical packs and blueprints. Enables AI agents to scaffold inventory sites, SaaS platforms, and custom verticals, including Supabase provision | |
| Scribe MCP Server cortalabs/scribe_mcp Enables maintaining consistent project documentation and progress logs across development workflows. Provides tools for logging changes, tracking project phases, and keeping architecture docs synchronized with day-to-day development work. | |
| Conduit cortex-app/conduit A Model Context Protocol server that integrates with Phabricator and Phorge APIs, enabling developers to automate and interact with task management systems through both synchronous and asynchronous clients. | |
| CortexScout cortex-works/cortex-scout CortexScout is the Deep Research & Web Extraction module within the Cortex-Works ecosystem.
Designed for agent workloads that require token-efficient web retrieval, reliable anti-bot handling, and optional Human-in-the-Loop (HITL) fallback | |
| DataForSEO MCP Server cortex8/oyt-dataforseo-mcp-worker Enables AI assistants to access comprehensive SEO data through DataForSEO APIs, including SERP results, keyword research, backlink analysis, on-page metrics, and domain analytics. Supports real-time search engine data from Google, Bing, and | |
| Cortex MCP cortexapps/cortex-mcp A Model Context Protocol server that provides natural language access to Cortex API, enabling users to query information about their system's structure and make faster decisions about services, incidents, and team responsibilities. | |
| NetMCP cortexc0de/netmcp A professional-grade network analysis MCP server that integrates Wireshark/TShark, Nmap, and threat intelligence to enable packet capture, network scanning, threat detection, and credential extraction through natural language. | |
| Cortex Context MCP Adapter cortexguardai/mcp Enables integration with Cortex Context services through the Model Context Protocol. Provides authenticated access to CortexGuardAI's context management capabilities for registered users. | |
| Local RAG MCP Server cortexllms/ai-orchestration-mvp Enables tool-calling over TCP for a local RAG pipeline, allowing document ingestion and querying via MCP tools, fully offline with no cloud dependencies. | |
| Promptest MCP cortexresearch/promptest-mcp An MCP server that grades prompts against a validated rubric, tracks real outcomes, and provides guidance grounded in research on what predicts good results. | |
| Kubecost MCP Server cortezcristian/kubecost-mcp An implementation that enables AI assistants to interact with Kubecost cost management platform through natural language, providing access to budget management and cost analysis features. | |
| Cortivium cortivium/cortivium Enables reliable AI behavior control by registering Ghost Skills as MCP tools that the model reads before every action, providing enforceable behavioral rules with ~95% reliability. | |
| Honeycrisp cortland-suite/cortland MCP servers for your Mac's real data — Mail, Calendar, files — with safety rails you can audit. Local-first, no accounts, no cloud, with dry-run defaults and human approval gates. | |
| mcp-excel corvalon/mcp-excel Provides full read and write access to Excel workbooks (sheets, cell ranges, tables, formulas, formatting, and cross-workbook references) via MCP, running locally or as an HTTP/SSE service. | |
| m365-mcp corvalon/mcp-m365 A Model Context Protocol server that gives Claude Code (or any MCP client) controlled access to Microsoft 365 through the Microsoft Graph API: mail, calendar, contacts, files, notes, tasks, Teams, SharePoint, and the full tenant-admin surfa | |
| agent-3md corvidlabs/agent-3md Exposes an agent's skills as MCP tools, allowing any MCP client to route requests and load skills on demand from a single .3md file. | |
| video-capture-mcp corvus400/video-capture-mcp MCP server for screen recording on macOS, iOS Simulator, and Android, with key-frame extraction via ffmpeg, enabling AI agents to capture UI motion and transient visual states. | |
| Behr Colormapper MCP coryking/colormapper Enables matching digital sRGB colors to the nearest Behr paint colors and searching Behr colors by code or name. | |
| Agent Chef coryshaw/agent-chef-mcp Family meal planning run by your own AI agent: it proposes ten dinners each week, the household votes and leaves feedback from personal links, the top picks win, and a grocery list is built minus what's already in the pantry. Remote MCP ser | |
| cheapinboxes-mcp cosankov/cheapinboxes-mcp MCP server for managing cold-email infrastructure: buy domains via Porkbun, import them into CheapInboxes, provision Google/Microsoft mailboxes, and sync credentials to platforms like Instantly and Smartlead. | |
| Taiwan Price Compare MCP coseto6125/mcp-taiwan-price-compare Enables price comparison across 7 major Taiwanese e-commerce platforms (momo, PChome, Coupang, ETMall, Rakuten, Yahoo Shopping, Yahoo Auction) with advanced filtering for finding the lowest prices on products. | |
| Keepa MCP Server cosjef/keepa_mcp Provides conversational access to Keepa's product and sales data for product research, sales velocity analysis, inventory optimization, and competitive intelligence. | |
| arXiv MCP Server coskun45/mcp Enables searching and retrieving arXiv papers by topic, fetching abstracts by paper ID, and saving markdown content to files. Includes examples of integrating MCP tools with Google Gemini for AI-powered paper research. | |
| open-media-finder coslynxai/open-media-finder Enables AI agents to search seven open media collections for reusable images, artworks, HDRIs, textures and 3D models, keeping only items whose own licence record clearly permits reuse. Returns ready-to-use attribution credit lines and can | |
| Kraken MCP Connector cosmadamianorossetti-png/kraken-mcp-connector Enables MCP clients to access public spot market data—tickers, candlesticks, order books, trades, spreads, instruments, assets, and system status—via remote Streamable HTTP or local stdio. It is read-only and requires no API keys. |
40,451–40,500 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.