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 |
|---|---|
| RISBridge MCP codemonk6/risbridge-mcp Enables users to run Slurm jobs on WashU RIS Compute2 cluster by describing their intent in plain English, without requiring SSH or Slurm knowledge. | |
| EBS CloudWatch Metrics MCP codemonkyu/ebs_performance_mcp Provides tools to query and calculate AWS EBS performance metrics from CloudWatch, including IOPS, throughput, and latency. It also enables users to manage snapshots and retrieve advanced diagnostic data like I/O utilization and burst balan | |
| danxiapi codemzt/danxiapi Enables interaction with Fudan University campus and forum (FDU Hole) APIs, providing tools for timetable, grades, GPA, electricity, ecard, crowdedness, notices, forum search, and more, with proper handling of 2FA and network restrictions. | |
| openclaw-mcp codename-11/openclaw-mcp MCP server for Claude Code to interact with OpenClaw AI agents (Daemon, Soren, Ash, etc.) via the gateway API, providing tools to ask agents, list them, and check their status. | |
| design-compare-mcp codenameakshay/design-compare-mcp An MCP server that measures how faithfully one UI reproduces another, returning a score and actionable findings for improvement. | |
| ai-product-planner codenameju/ai-product-planner Turns product ideas into implementation-ready planning packages including PRD, requirements, user flow, wireframes, data schema, API contracts, and SDK boundaries, with an MCP handoff for coding agents. | |
| Google Drive MCP codenamerey/gdrive-mcp Enables Claude to search, list, and read files in Google Drive, allowing natural language interaction with your documents and folders. | |
| Frappe MCP Server codenetic-tech/frappe-js-mcp-server Enables AI models to securely interact with Frappe Framework/ERPNext instances, supporting document CRUD, RPC methods, file management, workflows, reporting, and more via the Model Context Protocol. | |
| Forgeline codenikhildr/forgeline Read-only Modbus TCP monitoring server that exposes safe MCP tools for AI agents to read holding/input registers, coils, and device identity from industrial devices without write access. | |
| KETI FLOW MCP codeninja1126/keti_flow_mcp Enables querying optimal control values (angle for blowers, control for pumps) to minimize power given a required flow rate, using machine learning models trained on pump/fan operation data. | |
| agent-veille codenolimits/agent-veille MCP server that scans daily AI innovation sources (arXiv, Hacker News, GitHub) and normalizes discoveries into actionable Skill Sheets for domains like code, design, HR, agents. | |
| App Adapter codenoob-jacky/app-adapter An MCP server that translates human GUI actions into machine-executable commands, enabling AI agents to control real software applications like Zoom, Excel, and WeChat via natural language or API calls. | |
| type-the-change codenyangi/type-the-change Enables MCP clients to read bounded workspace files, validate exact replacement plans for the VS Code extension, and check recent typing progress without modifying source or running shell commands. | |
| Code Ocean MCP Server codeocean/codeocean-mcp-server Provides tools to search and execute Code Ocean capsules and pipelines while managing platform data assets. It enables users to interact with Code Ocean's computational resources and scientific workflows directly through natural language in | |
| codepawl-video-lab codepawl/codepawl-video-lab Enables Codex to retrieve YouTube video dossiers, compare videos, access channel performance and retention curves, save analysis reports, and manage experiments through a stateless MCP endpoint. | |
| UI Reviewer MCP codepawl/uxray MCP-first UI/UX review layer for AI-generated frontends. Enables reviewing web pages via URL, capturing screenshots, extracting layout metrics, and generating structured repair plans for agents. | |
| CodePeel MCP Server codepeel/mcp-server Enables AI agents to review code diffs for bugs, security issues, and bad patterns, and generate fixes. | |
| Mind Cloud codependentai/mind-cloud Persistent memory infrastructure for AI systems, running on Cloudflare's edge network with 28 MCP tools for semantic memory, emotional processing, identity continuity, and a subconscious daemon. | |
| Mind Cloud Lite codependentai/mind-cloud-lite Token-optimized persistent memory MCP server for Claude Pro users, providing 9 essential tools for memory management with 87% token reduction compared to full version. | |
| Kultranz MCP Server codephantom-1/kultranz-mcp Enables models to query real US government data (BLS, BEA, Census, IRS 2026) to calculate 2026 take-home pay across all 50 states plus DC, compare cost-of-living-adjusted salaries between 50 US metros, retrieve tax bracket ladders, and look | |
| RankCanon codepharm99/rankcanon Enables AI agents to search and retrieve fresh, cited SEO knowledge from primary sources like Google Search Central documentation and the Google Search Status Dashboard, and to correlate ranking algorithm updates with traffic changes. Suppo | |
| cvrlookup-mcp codepilots-io/cvrlookup-mcp Remote MCP server for the Danish company register (CVR): company lookup, name search, and parsed annual-report financials as structured JSON for 860,000+ active Danish companies. | |
| MCP - Model Context Protocol TypeScript SDK codeplaydata/mcp A TypeScript wrapper library for the Model Context Protocol SDK that provides a simplified interface for creating MCP servers with tools, resources, and prompts without needing to work directly with the protocol. | |
| Math MCP Server codeprimate/math-mcp Provides powerful symbolic mathematics and statistical analysis capabilities, enabling users to solve equations, compute derivatives and integrals, perform statistical tests, and analyze data through natural language requests. | |
| Ask Agent coder-mil/ask-agent Enables any MCP-compatible AI agent to ask humans questions in real time via a mobile-friendly PWA with push notifications, operating local-first without third-party services. | |
| Claude MCP Server Ecosystem coder-rl/claude_mcpserver_dev1 A production-ready MCP server ecosystem providing Claude AI with 150+ specialized tools across enhanced memory, data analytics, security, design, and infrastructure domains with PostgreSQL, Redis, Qdrant, and Docker orchestration. | |
| ChopChop MCP Server coder01128/chopchop-mcp-server Enables AI agents to query tenants, browse catalogue items with pricing, pull recent orders, and add products through the MCP tool-calling interface. | |
| coderadius coderadius-ai/coderadius Enables AI agents to query architecture context, data contracts, and blast radius to prevent cross-repo architectural breakage before merging. | |
| Google Sheets Todos MCP Server coderclub-team/firstmcp Stores todos in a Google Sheet and exposes CRUD tools for listing, getting, creating, updating, and deleting todo items. | |
| verifiable-thinking-mcp coderdayton/verifiable-thinking-mcp MCP server for structured reasoning with cognitive trap detection, verification, and context compression | |
| Claude Infinite Context coderdeep11/claude-memory-mcp Overcomes Claude Code's 200k token context limit by implementing persistent long-term memory using Redis and AI-powered state summarization. Enables seamless checkpoint and resume of project context across sessions. | |
| jev-browser-wingman coderexpert123/jev-browser-wingman Enables attaching to an already-open, logged-in Chrome via Playwright MCP or raw CDP to perform one bounded browser step per call, such as filling forms or clicking through wizards, while keeping planning and text generation with the callin | |
| Task Orchestration coderexpert123/task-orchestrator Elevate your LLM task management with Task Orchestrator, an MCP server that empowers you to define, organize, and track goals and tasks with hierarchical precision. Integrate intelligent task management into your workflow. | |
| Remote MCP Server Authless coderfe/remote-mcp-server-authless A serverless MCP implementation on Cloudflare Workers that doesn't require authentication, allowing you to deploy custom AI tools that can be accessed from Cloudflare AI Playground or Claude Desktop. | |
| Project Tango codergamerunknow/project-tango A local-first Model Context Protocol server that provides LLM agents with structured access to e-commerce data (products, inventory, orders, sales analytics) using a realistic mock dataset, zero configuration, and a swappable DataProvider i | |
| safeguard codergeeta/safeguard Enables checking scam messages, securing accounts, auditing repositories and AI-agent setups for supply-chain risks, vetting packages, skills, and MCP servers before installation, and handling incident response through MCP tools, guides, an | |
| Unrush MCP Server codergirl73/unrush Enables a proactive household assistant to manage calendar events, pantry and meal plans, predict grocery run-outs, build consent-based simulated orders, and expose interactive MCP Apps views through tools and resources. | |
| Basic MCP Server coderianx/basicmcpserver Enables MCP clients to read and write local files, run shell commands, and fetch web pages. | |
| YouTube Music MCP Server coderisshi25/youtubemusic-mcp A production-grade MCP server that connects YouTube Music to AI assistants, enabling music search, library management, playlist creation, and personalized recommendations through 15 tools, 3 resources, and 3 prompts. | |
| Shaka Packager MCP Server coderjun/shaka-packager-mcp-server An MCP server that integrates Shaka Packager with Claude AI applications, enabling Claude to analyze, transcode, and package video files for streaming in formats like HLS and DASH. | |
| MCP Demo — GitHub Copilot + Your Database coderkanasu/mcp-demo An MCP server that enables AI assistants to query and interact with SQLite databases through natural language. It includes built-in security guardrails such as PII redaction, SQL injection blocking, and query rate limiting. | |
| MCP MySQL Server coderleo/mcp_mysql Enables secure read-only access to MySQL databases through SELECT queries via HTTP SSE interface. Provides safe database exploration and data retrieval with configurable timeout settings. | |
| mcp-tool-server coderman002/mcp-tool-server A secure, production-grade MCP server that provides filesystem operations, AST math evaluation, and system diagnostics for LLM agents. | |
| TaskUp MCP Server coderrahul01/taskup-mcp A centralized workspace orchestration server that enables natural language task management across Notion, Google Calendar, and Telegram. It allows users to analyze intent, create database tasks, schedule calendar events, and send instant no | |
| Claude Research Gateway coderrone/claude-research-gateway An MCP server that enables Claude to access paywalled scientific papers through your institutional login (Shibboleth/SAML SSO, EZProxy). | |
| ls-dyna-mcp codersag/ls-dyna-mcp Enables AI clients to build, solve and inspect LS-DYNA analyses, either by driving Ansys Mechanical through PyMechanical or by submitting and monitoring standalone keyword-deck runs. It also reads and audits solver output files such as glst | |
| Mechanical MCP Server codersag/mechanical-mcp Enables natural language interaction with ANSYS Mechanical simulation software via gRPC, allowing users to manage geometry, mesh, boundary conditions, solve analyses, and generate reports through MCP-compatible AI clients. | |
| mcp-route-master codershivamgusain/route-master-mcp Enables Claude, ChatGPT, Gemini, and other MCP clients to find, rank, and vet intercity bus options in India, generate official booking links, interpret seat maps, and guide users through safe booking and pre-payment checks. | |
| Agentic Browser MCP Server codesblobs/custommcps A local MCP server that connects to a Chrome extension to enable AI agents to control browser tabs, execute automation, and interact with web pages via tools. | |
| AgentDB MCP Server codesbyfebin/agentdb Enables MCP clients to discover, list, and call browser-demo tools for SQL-like queries, vector and hybrid search, agent memory, and evidence-ledger operations over a stateless HTTP endpoint. |
39,751–39,800 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.