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 |
|---|---|
| threejs-devtools-mcp claralim33401/threejs-devtools-mcp Enables AI agents to inspect a running Three.js scene in the browser and try out live edits to objects, materials, shaders, lights, camera and animation without touching project files. Every change is recorded and can be exported as ready-t | |
| Semantic Scholar MCP Server clarapetridis/semantic-scholar-fastmcp-mcp-server Enables users to search academic papers, retrieve paper and author details, explore citation and reference networks, and get paper recommendations via the Semantic Scholar API. It also supports batch operations, field customization, and aut | |
| Juror Cloud MCP claraw49004/juror Enables an OAuth-signed-in user to list their workspaces and inspect concise, workspace-scoped review findings and hosted run summaries. It can also prepare a pull request review and start or rerun an existing hosted review once the user ex | |
| TON Tolk Compiler MCP Server claraxyb/tolk-mcp-server Integrates Tolk compiler tools into AI assistants, enabling compilation of Tolk contracts, conversion from FunC, and version checks without manual terminal work. | |
| Open-Meteo MCP Server clarehancock/open-meteo-mcp Enables AI assistants to look up live weather data, including current conditions and up to 16-day forecasts, by converting place names to coordinates and fetching data from the Open-Meteo API without requiring an API key. | |
| rdap-mcp-server clareliguori/rdap-mcp-server Model Context Protocol server to look up domain names and IPs using RDAP. | |
| MCP Connection Test Server clarencez1011/mcpservertest A simple cloud-hosted MCP server for verifying upstream MCP connectivity via Streamable HTTP, exposing a single tool that returns a fixed success message. | |
| VeyraX MCP clarenous/veyrax-mcp Provides unified access to all tools integrated with the VeyraX platform through a single authentication. Eliminates the need for multiple logins by connecting once to access all your tools across any MCP-compatible environment. | |
| cms-datagov-mcp-server clarifyhealth/cms-datagov-mcp-server Enables AI assistants to search, query, and analyze CMS healthcare datasets from data.cms.gov, supporting features like dataset discovery, filtering, and CSV download for large-scale analysis. | |
| SQL Server MCP Server claritas-llc/mcp-cla-sqlserver2019 Enables AI agents to inspect schemas, analyze performance, check security, and troubleshoot SQL Server 2019+ databases through a safe, controlled interface. | |
| tailwindcss-mcp-server clarity-contrib/tailwindcss-mcp-server A comprehensive MCP server providing TailwindCSS utilities, documentation, conversion tools, and template generation to assist AI in TailwindCSS development. | |
| CLRTY-1 ALE clarity-fintech/clrty-1-ale-atomic-liquidity MCP server for executing atomic liquidity swaps via 1inch Fusion, enabling CLRTY-1 token to USDT settlement with fail-closed safety and dry-run mode. | |
| AgentPhone clark-bridgeworks/agentphone Enables two native agent sessions to explicitly exchange messages and inspect delivery receipts through MCP tools. Supports agent discovery, sending, reading, and conversation retrieval while keeping each agent in its original chat. | |
| OncoSignal MCP Server clark94/oncosignal Enables MCP clients to search oncological evidence, retrieve records, generate quality reports, and inspect trial-publication links through four read-only tools over stdio. | |
| Fibonacci MCP Server clarkeg02/fibonacci-mcp A secure Model Context Protocol server that provides tools for calculating Fibonacci numbers, BMI, and generating code review prompts with comprehensive security measures for production deployment. | |
| MControlProgram clarkehackworth/mcontrolprogram An MCP gateway that enables AI agents to use controlled SSH, web, and proxied MCP tools while credentials and access policies stay isolated in plugins. It supports per-server authentication, logging, and human approval for risky tool calls. | |
| cortex-cloud-docs-mcp-server clarkemn/cortex-cloud-docs-mcp-server MCP server for asking questions about Cortex Cloud documentation | |
| prisma-cloud-docs-mcp-server clarkemn/prisma-cloud-docs-mcp-server MCP server for asking questions about Prisma Cloud documentation | |
| google-ads-mcp clarkstamina-max/ads-mcp-2 Enables LLMs and AI agents to query Google Ads accounts via the Google Ads API, including searching account data, retrieving resource metadata, and accessing API discovery documents, metrics, segments, and release notes. | |
| Kommo CRM MCP Server clarkstamina-max/kommo-mcp Centralized MCP server for Kommo CRM multi-tenancy, enabling AI assistants to interact with multiple client accounts via SSE and dynamic client routing. | |
| Google Ads MCP Server clarkstamina2-cpu/ads-mcp-2 Enables LLMs and AI agents to query Google Ads accounts, inspect resource metadata, list accessible customers, and retrieve reporting metrics, segments, discovery documents, and release notes via the Google Ads API. | |
| Piazza MCP Server clarsbyte/piazza-mcp Enables interaction with Piazza to fetch posts and course information directly through Claude. Users can list configured courses and retrieve recent posts from specific classes via natural language commands. | |
| WashedMCP clarsbyte/washedmcp Token-optimized semantic code search with automatic context expansion for AI coding assistants, enabling efficient discovery of code relationships and reducing token usage. | |
| Deep Code Reasoning MCP Server clarsson327/deep-code-reasoning-mcp Enables Claude Code to escalate complex code analysis tasks to Google's Gemini AI for large-context execution tracing, cross-system impact analysis, performance bottleneck detection, hypothesis testing, and AI-to-AI conversational debugging | |
| Context Zero Engine classevelabs/context-zero-engine A local code-intelligence engine for AI agents that indexes repositories into a PostgreSQL-backed code graph and serves structured, token-budgeted context over MCP and HTTP, enabling targeted queries on symbols, dependencies, contracts, and | |
| ssh-mcp-server classfang/ssh-mcp-server Enables secure remote command execution and bidirectional file transfers on SSH servers through the Model Context Protocol. It features robust security controls including command whitelisting, credential isolation, and support for multiple | |
| Cloudflare Remote MCP Server Template classhopperapp/classhopper-mcp-server A template for deploying remote Model Context Protocol servers to Cloudflare Workers without authentication. It enables hosting custom tools via Server-Sent Events for integration with clients like Claude Desktop and the Cloudflare AI Playg | |
| classifinder-mcp classifinder/classifinder-mcp Enables AI agents to scan text for leaked secrets and prompt injection markers, and redact them before reaching an LLM. | |
| classix-mcp-proxy classix/classix-mcp-proxy Accepts incoming websocket connections and creates unique POST API endpoints for each one, enabling classix to interact with MCP tools. | |
| claude-subagent-mcp claude-abounegm/claude-subagent-mcp Enables MCP clients such as Cursor to hand a bounded task to a scoped, non-interactive Claude Code session billed to a Claude subscription rather than Cursor model credits. Runs read-only by default, with optional file edits or Bash, plus b | |
| MCPControl claude-did-this/mcpcontrol A Windows control server built using nut.js and Model Context Protocol (MCP), providing programmatic control over Windows system operations including mouse, keyboard, window management, and screen capture functionality. | |
| pathways-mcp-server claude-marie/pathways-mcp-server Exposes health segmentation data from the Pathways platform, enabling natural language queries about population segments, metrics, and geographic distributions across countries like Senegal and Kenya. | |
| hub-bus claude-max-agent/hub-bus An MCP broker that provides local communication between Manager and Lead agents for message routing and coordination. | |
| IDA-instances-MCP claude-reverser/ida-instances-mcp Enables MCP clients to drive IDA Pro through a stability-hardened server that hosts multiple headless idalib instances, with per-session isolation, configurable HTTP/stdio transports, and API-key authentication. | |
| notebooklm-skill claude-world/notebooklm-skill Bridges NotebookLM's research capabilities with Claude's content generation, enabling creation of notebooks, deep research queries, and structured content output from URLs, PDFs, or trending topics. | |
| trend-pulse claude-world/trend-pulse MCP server for trend-pulse, an agentic trend intelligence platform that fetches and analyzes trending topics from 37 sources, provides search, historical data, and lifecycle prediction via 29 tools. | |
| qqmail-mcp claude89757/qqmail-mcp Gives AI assistants OAuth-secured access to a single QQ Mail mailbox over IMAP and SMTP, letting them search, read, organize, draft, and send email with attachments. Supports folder management, flag changes, threaded replies, and forwarding | |
| provenance-mcp claudechen95/provenance-mcp Answers why code exists by tracing file:line or natural-language questions through git blame, commits, PRs, and linked issues, providing cited evidence from history. | |
| bangla-news-radar claudefarid/bangla-news-radar Enables monitoring Bangladeshi newspaper headlines and articles via MCP, with tools to scan recent coverage, compare story presence across outlets, and search Prothom Alo's archive in Bengali or English. | |
| bd-finance-mcp claudefarid/bd-finance-mcp Enables AI assistants to access Bangladesh's financial markets, including both stock exchanges, cross-exchange price spreads, company fundamentals, sector performance, financial news, and taka exchange rates. | |
| dse-stock-mcp claudefarid/dse-stock-mcp Enables AI assistants to retrieve live Dhaka Stock Exchange data, including prices for all listed shares, top gainers/losers, and market summary, through natural language queries. | |
| prothomalo-mcp claudefarid/prothomalo-mcp Enables AI assistants to search and read Prothom Alo news, including keyword search, latest articles, full story retrieval, and section browsing. | |
| sky-spine-mcp claudeskydream-hash/sky-spine-mcp Automates Spine asset pipeline tasks such as export, texture packing, resource validation, and file summarization through the Spine CLI. | |
| claude-wilder-mcp claudewilder/claude-wilder-mcp Description: AI-authored book and software reviews, plus news and data investigations with downloadable CSV datasets and an open response protocol. AI agents and humans can read content, analyze raw data, and respond through an open signal | |
| WooCommerce MCP Server claudia204/woocommerce-mcp-server Enables interaction with WooCommerce stores through the WordPress REST API, offering tools to manage products, orders, customers, shipping, taxes, discounts, and store configuration via JSON-RPC 2.0. | |
| Android Source Explorer MCP Server claudia2388/android-source-explorer-mcp Enables AI tools to query precise, on-demand AOSP and AndroidX source code for class and method inspection, inheritance, source searches, and optional LSP-powered cross-file navigation. | |
| Augments MCP Server claudia9503/augments-mcp-server Provides real-time, context-aware documentation for any npm package — TypeScript types, prose, and code examples — directly to Claude Code and other MCP clients. It also enables version comparisons with real changelogs, cross-version migrat | |
| Charlotte claudiad02293/charlotte Enables AI agents to browse and interact with the web through compact, structured page representations—arrival orientations, targeted element queries, and on-demand detail—instead of dumping full accessibility trees. Supports navigation, cl | |
| Stock SDK MCP Server claudiafransson0233/stock-sdk-mcp Enables AI assistants to retrieve and analyze real-time and historical market data across A-shares, Hong Kong, US stocks, funds, futures, and options, including technical indicators, sector data, screening, and composite analysis. It also p | |
| Zettelkasten MCP Server claudiagunduz3448/zettelkasten-mcp Enables creating, linking, searching, exploring, and synthesizing atomic notes as a knowledge graph through MCP-compatible clients such as Claude. Supports tags, note types, semantic relationships, Markdown storage, and an SQLite index for |
39,151–39,200 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.