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 |
|---|---|
| AI Gateway MCP Server ayatec/ai-gateway-mcp-server Provides unified access to multiple AI providers through Vercel AI Gateway, enabling question answering, web search, multi-model research, and model listing. | |
| Antigravity MCP Server ayato964/antigravity_mcp Enables external agents like Gemini Spark to control Google Antigravity CLI (agy) via Model Context Protocol, supporting multimodal inputs and automatic session management. | |
| Cloudways MCP Server ayaz/cw-mcp-fork Enables AI assistants to manage Cloudways infrastructure, including servers, applications, monitoring, and security via the Cloudways API. | |
| App Store Connect MCP Server ayberkozz/appstoreconnectmcp Lets Claude interact with the App Store Connect API to manage apps, builds, version submissions, sales reports, and Game Center leaderboards and achievements. | |
| klayout-mcp aycandv/klayout-mcp Read-only MCP server for KLayout that opens GDS/OAS layouts, inspects geometry and hierarchy, renders deterministic PNGs, and runs batch DRC with structured JSON output. | |
| sigenergy-mcp aydho/sigenergy-mcp Enables local monitoring and control of a Sigenergy energy system over Modbus TCP, exposing live solar, battery, grid, load and EV charger data plus optional write tools for remote EMS modes, power and SOC limits, grid import/export caps an | |
| Feedback Hub MCP aydin-omer/feedback-hub-mcp Lets AI assistants query a live feedback collection database in plain language, retrieving entry counts broken down by type and classification status, and listing individual submissions filtered by type, urgency, or sentiment. Access is rea | |
| Spline MCP Server aydinfer/spline-mcp-server An interface that enables Claude to interact with Spline 3D design tool, allowing operations like exporting scenes, importing models, and creating animations through natural language commands. | |
| Maya MCP Server aydji/autodesk-maya-mcp Enables AI assistants to programmatically control Autodesk Maya via natural language using over 30 tools for 3D modeling, lighting, and animation. It connects through Maya's command port to facilitate procedural scene generation and complex | |
| Eidola MCP Server ayejk/eidola-runtime Middleware that gives AI personas a visible, reactive presence inside editors like Cursor, Claude Code, and Cowork. | |
| Unreal Engine Code Analyzer MCP Server ayeletstudioindia/unreal-analyzer-mcp Provides deep source code analysis for Unreal Engine codebases, allowing AI assistants to understand C++ class structures, search code, and analyze subsystems. | |
| stitch-mcp ayemish/stitch-mcp A CLI and MCP server to preview, build, and integrate AI-generated UI designs from Google Stitch into your local development workflow and coding agents. | |
| VSAX MCP Server ayeschully/vsax-mcp-server Provides comprehensive access to the Kaseya VSAX (VSA 10) REST API v3 through 67 specialized tools. It enables users to manage devices, run workflows, execute scripts, and oversee organizational data using natural language and OData query s | |
| LinkedIn Profile Scraper MCP Server ayesha0300/linkedin-profile-mcp MCP server that fetches LinkedIn profile information using the Fresh LinkedIn Profile Data API, allowing users to retrieve profile data in JSON format by providing a LinkedIn profile URL. | |
| sure-but-wrong ayesha458/sure-but-wrong Enables users to benchmark AI models across English, Urdu, and Roman Urdu by running question sets, grading answers, measuring confidently wrong and hedged responses, and producing reports, comparisons, and CSV exports through an MCP client | |
| testrail-mcp ayesha458/testrail-mcp Enables Claude to create and upload test cases directly into TestRail by finding the right section, checking required fields, and creating cases with steps, expected results, references, custom fields, and optional images from chat or a cas | |
| YouTube MCP Server ayeshaahmed29/youtube-mcp Enables Claude Code to search YouTube, retrieve video transcripts and metadata, explore channels, playlists, comments, and trending videos, and analyze engagement and replayed segments. | |
| @archsmith/mcp-server ayeshlk/archsmith MCP server that exposes ArchSmith's diagram rendering and validation as tools, along with schema and registry resources, enabling AI agents to generate consistent SVG architecture diagrams from validated JSON descriptions. | |
| a207-clinical-calc-mcp ayeyouok/a207-clinical-calc-mcp MCP server for pediatric CKD clinical calculations, providing eGFR-Schwartz estimation and KDIGO 2024 CKD staging, restricted to doctors. | |
| a207-followup-mcp ayeyouok/a207-followup-mcp MCP server for pediatric CKD follow-up management, providing tools to schedule follow-ups based on KDIGO 2024 guidelines, retrieve follow-up records, compute adherence scores, and access PEW history. | |
| a207-his-mcp ayeyouok/a207-his-mcp Read-only MCP server providing pediatric CKD patient master data with tools for patient profiles, diagnosis, nutrition ceilings, guardian verification, and patient lists, designed for the CKDNutri project. | |
| a207-lis-mcp ayeyouok/a207-lis-mcp MCP server for pediatric CKD lab data, providing lab panel queries, critical value alerts, trend analysis, and write operations with role-based permissions. | |
| a207-meal-plan-mcp ayeyouok/a207-meal-plan-mcp Generates multi-day CKD meal plans for children based on PRNT targets (energy, protein, potassium, phosphorus, sodium), providing nutrient summaries and target achievement rates for dietitians. | |
| a207-nutrition-assessment-mcp ayeyouok/a207-nutrition-assessment-mcp Enables pediatric CKD nutrition assessment by calculating PRNT energy/protein targets, evaluating dietary intake against those targets, and screening for PEW risk, with support for dialysis, vegetarian diets, and edema corrections. | |
| a207-nutrition-calc-mcp ayeyouok/a207-nutrition-calc-mcp MCP server for pediatric CKD nutrition and food calculations, enabling energy/protein targets, food nutrient lookup, substitutions, meal summaries, and drug-nutrient interaction checks. | |
| a207-report-mcp ayeyouok/a207-report-mcp Aggregates pediatric CKD patient data from multiple modules to generate unified timeline reports with structured sections, markdown summary, and overall status. Enables clinicians to obtain a comprehensive patient snapshot. | |
| a207-router-mcp ayeyouok/a207-router-mcp Provides deterministic intent routing and safety gating for multi-agent systems, enforcing P0 critical word detection, mutually exclusive hard rules (MX-1/2/3), and a permission matrix as pure functions via four MCP tools. | |
| callput-agent-mcp ayggdrasil/options_trading_base MCP server for spread-only options execution on Base L2, enabling AI agents to trade options via a defined tool loop. | |
| overleaf-mcp ayghri/overleaf-mcp Enables AI agents to read, edit, and compile LaTeX documents in Overleaf projects with tracked changes via the Model Context Protocol. | |
| boston-harbor-ferries aygp-dr/boston-harbor-ferries MCP server to track Boston Harbor commuter ferries in real-time, providing vessel positions, routes, and schedules. | |
| liquidus-005 aygp-dr/liquidus-005 An MCP server implementing F5 governance-tuple wrapping for composable provenance, providing tools for interacting with the liquidus system. | |
| gsc-seo-mcp ayhammouda/gsc-seo-mcp Secure, read-only Google Search Console MCP server with exact property allowlists and a hardened TypeScript runtime. | |
| OBD MCP Server ayhammouda/obd-mcp-server A local-first, read-only MCP server for vehicle diagnostics that exposes structured OBD-II tools for reading PIDs, DTCs, and ECU snapshots without raw protocol access. | |
| MCPDemo - Visual SQL Chat Platform ayi456/visual-mcp An AI-driven data visualization and SQL chat platform that enables natural language to SQL conversion, interactive chart generation, and database querying through a comprehensive MCP interface. Supports multiple databases, intelligent chart | |
| aseprite-mcp ayigityol/aseprite-mcp MCP server for Aseprite — create, edit, and export pixel art sprites, animations, and sprite sheets from any AI assistant. | |
| Gamma MCP Server aykansal/gamma-mcp-server Enables generating presentations, creating from templates, and managing Gamma resources via MCP tools. | |
| YÖK Atlas MCP Server aykutbuyukkaya/yokatlas-mcp-server MCP server that provides Turkish university preference guide data, enabling users to query provinces, universities, and program groups, and to search university programs with filters, while reminding users to verify results against official | |
| cairn aylee1024/cairn Self-hosted personal context layer that gives AI agents shared memory via MCP. | |
| pinterest-mcp aymandakirgh/pinterest-mcp Enables AI assistants to read and manage an account's boards, pins, sections, and analytics, run full-text search over its own content, and complete OAuth token flows through the Pinterest API v5. It exposes 35 typed tools that run either a | |
| stackadapt-mcp aymanshaikh/stackadapt-mcp An MCP server for querying StackAdapt's GraphQL API. Gives AI assistants like Claude direct access to your campaign data, delivery metrics, advertisers, and more. | |
| MCP-Powered Video RAG aymanz12/-mcp-powered-video-rag- Enables asking natural language questions about local videos, using Whisper transcription, ChromaDB vector storage, and Groq for timestamped answers via MCP. | |
| LunarGarden MCP aymaratedesko-hue/lunargarden-mcp Provides astrology-aware garden care planning by combining lunar phase, Vedic panchang, weather, and soil forecasts into structured care plans with rationales and confidence scores. | |
| bricks-use aymenfurter/bricks-use MCP server for executing Databricks SQL queries and comparing table data, supporting CLI and VS Code integration. | |
| Packet Tracer MCP aymenmerabta5/mcp-packet-tracer Enables MCP-capable AI clients to turn natural-language network requests into validated, deployable Cisco topologies and to read back device state from the live simulator. | |
| DriftScope aymenrahmanii/driftscope-mcp Enables LLMs to audit data drift and model degradation in tabular ML pipelines through deterministic statistical tests such as Kolmogorov-Smirnov and Population Stability Index, plus reusable prompts and standards resources. | |
| pocketbase-mcp aymeridev/pocketbase-mcp Enables Claude to manage a self-hosted PocketBase instance: querying and editing records, inspecting and changing collection schemas, handling files, users and backups, and auditing API rules for exposure risks. Writes are gated by a read-o | |
| ainu-mcp aynumosir/ainu-mcp A hosted Model Context Protocol server for the Ainu-language toolchain, enabling LLMs to edit the Itak-uoeroskip glossary, search corpora, dictionaries, and grammar resources, and perform script conversion. | |
| Care Circle MCP Server ayoadecreations/care-circle Exposes five tools over Streamable HTTP that let family caregivers capture a free-text update as proposed tasks, confirm and save them, view open tasks grouped by urgency, mark tasks complete or reopen them with an audit trail, and generate | |
| One Click for ChatGPT ayobamih/oneclick-chatgpt-plugin Enables conversion of business briefs or authenticated saved projects into structured handoffs for the Lovable plugin, with both anonymous basic mode and authenticated full mode including knowledge base, SEO, WCAG, security, and roadmap gui | |
| Health Reminder MCP Server ayon1997/health-reminder-mcp Sends periodic system notifications to remind users to take breaks and move around, with customizable intervals, messages, and cross-platform notification support. |
32,201–32,250 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.