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 |
|---|---|
| Famxplor Family Travel Activities alt250/famxplor-family-travel-mcp-server The first MCP server dedicated to families who travel with their kids. Find activities tested by families worldwide | |
| godot-mcp alta01/godot-mcp A comprehensive MCP server that gives AI assistants full control over the Godot game engine, providing 149 tools for runtime code execution, scene manipulation, physics, audio, animation, networking, and more. | |
| eu-ai-act-mcp altanziya/eu-ai-act-mcp Enables AI assistants to check whether a quote from the EU AI Act matches the right version on a given date, compare provisions across the 2024 and 2026 texts, and emit evidence records that anyone can recompute in a browser against signed | |
| Altary MCP Server altary-app/altary-mcp-server Enables Claude to integrate with Altary error management service for retrieving, analyzing, and completing errors directly within the IDE. Supports project management, AI-powered error analysis, and automated completion of similar errors th | |
| Altegio Marketplace MCP altegio/altegio-integrations-hub-mcp Enables automated creation, configuration, rollout, operation, and analysis of Altegio Marketplace applications through public/partner, Developer Cabinet, and optional backoffice APIs, with plan/apply safety, confirmation gates, and secret | |
| Carl altendky/carl Enables AI agents to search and compare Facebook Marketplace listings, collect listing details and photos, organize research workspaces, evaluate promising items with reusable product guides, and refresh or revisit results while preserving | |
| commerce-ops-recovery-mcp althaf-ka/commerce-ops-recovery-mcp MCP server that helps commerce operations investigate and safely recover orders left inconsistent after captured-payment webhook failures, with atomic recovery actions and audit history. | |
| bim-electrical-mcp althafdamara/bim-electrical-mcp MCP server for processing electrical BIM data from DXF and JSON files, sanitizing and storing it in Supabase, and enabling AI-powered querying through a conversational assistant. | |
| PlanTool altheslacker/plantool An MCP server that interviews users to capture project planning facts into SQLite and enforces mechanical gates to ensure structured progress. | |
| STK-MCP alti3/stk-mcp An MCP server that enables Large Language Models or other MCP clients to interact with Ansys/AGI STK (Systems Tool Kit), allowing users to control STK Desktop simulations programmatically or via natural language. | |
| altic-mcp altic-dev/altic-mcp A macOS automation MCP server providing 40+ tools for controlling Messages, Contacts, Notes, Reminders, Calendar, Files, Clipboard, Windows, Safari, Chrome, screenshots, and system settings via natural language. | |
| Tavily MCP Server altinakseven/tavily-mcp-server Provides AI-optimized web search capabilities and direct answers using the Tavily API for MCP-compatible assistants. It enables configurable searches with granular control over search depth, result counts, and domain filtering. | |
| Altinity MCP altinity/altinity-mcp Production-ready MCP server designed to empower AI agents and LLMs to interact seamlessly with ClickHouse. It exposes your ClickHouse database as a set of standardized tools and resources that adhere to the MCP protocol, making it easy for | |
| mcp-server-odoo altinkaya-opensource/odoo-mcp Enables AI assistants to fully interact with Odoo ERP instances over XML-RPC, supporting read and write operations on any model without requiring Odoo module installation. | |
| @altirs/mcp-server altirs/mcp-server Enables MCP-compatible coding agents to screen text for prompt injection, personal data, unsafe content, and hallucinations before acting on it, using the Altirs API. | |
| ADOS MCP altnautica/ados-mcp Enables AI clients to read live drone status, telemetry, and parameters, and to control drone operations with scoped permissions, confirmation steps, and audit trails. | |
| ai-task-tracking altoption/ai-task-tracking Enables AI coding agents to file and track issues, plan epics with steps, comment as they work, and hand decisions back to the user through a local Markdown- and YAML-backed issue tracker. | |
| aegisub-mcp altqx/aegisub-mcp Enables MCP clients to open, read, edit, verify, and save Aegisub/ASS subtitle documents, covering event lines, styles, timing and QC, karaoke, override tags, vector drawings, clipping, and font metrics. Includes a libass-backed verificatio | |
| Jev MCP Proxy altregubov/jev-antigravity-mcp Enables AI agent skills to route state-evaluation requests to TypeSafe AI's Jev System One model, supporting typed questions, choice classification, binary probabilities, and rubric scoring with calibrated confidence. | |
| blastp_mcp altriapendragon49/blastp_mcp Wraps NCBI BLAST+ blastp into a FastMCP service for auditable protein homology searches with local output artifacts and structured metadata. | |
| foldseek-mcp altriapendragon49/foldseek-mcp Enables protein structure and sequence searches using FoldSeek, with support for multiple databases, automatic model downloads, and structured job management. | |
| InterProScan MCP Service altriapendragon49/interproscan-mcp Provides protein family, domain, and functional annotation using InterProScan, supporting local or API backends. | |
| Yandex Wordstat MCP altrnex/yandex-wordstat-mcp Enables keyword research and search trend analysis for the Russian market through Yandex Wordstat API. Provides access to popular search queries, search volume dynamics over time, and regional distribution data. | |
| MCP DB Gateway altsys/mcp-db-gateway Provides governed, read-only PostgreSQL access for AI agents via MCP. Enforces schema/table allowlists, query limits, and audit events. | |
| googleflights-mcp altunoren/googleflights-mcp Enables searching Google Flights and getting structured, price-sorted flight options locally through MCP clients like Claude or Codex, with no API key or central server required. | |
| Altus Commonware Research MCP altuslabsxyz/altus-commonware-research-mcp A stdio MCP server that queries Commonware blockchain research via NotebookLM, enabling users to ask research questions, get code-backed implementation suggestions, search reference repositories, and validate documents against source code. | |
| Aerodrome MCP for Base alubiama/aerodrome-mcp-base Enables users to compare current Aerodrome veNFT voting positions, bounded claimable rewards, and selected pools' voting evidence on Base against a saved local baseline, with retryable, atomically stored change reports. All tools are read-o | |
| Figma MCP alucardeht/figma-mcp Enables interaction with Figma files through intelligent API access, providing navigation, asset extraction, and design token retrieval with 95% token-optimized compact tree output format. | |
| VisualAI MCP Server alucardeht/frame-forge-mcp Enables local AI image generation on Apple Silicon Macs using MLX and Stable Diffusion. Supports conversational design iteration, asset generation, and wireframe creation with zero API costs through the Model Context Protocol. | |
| ISIS MCP alucardeht/isis-mcp A local web scraping MCP server with RAG capabilities that provides intelligent web search, content extraction, and screenshot tools without requiring API keys. | |
| fluig-mcp alucardigo/fluig-mcp Operates a TOTVS Fluig environment via AI agents or terminal, managing datasets, forms, global events, and BPM process definitions without Fluig Studio. | |
| quick-mcp-example alucek/quick-mcp-example Demonstrates an MCP server with tools, resources, and prompts for a knowledgebase chatbot that queries a ChromaDB vector database for RAG responses. | |
| mcp-demo-server alucsky/mcp-demo-server This is a demo MCP server exposing SQLite-backed task management (CRUD), a calculator, and server metadata tools via the Model Context Protocol, and can be interacted with through natural language via any MCP-compatible client. | |
| Alumnx MCP Server alumnx-ai-labs/agrigpt-backend-mcp Provides agricultural intelligence tools for pest/disease lookup, government scheme discovery, and SME knowledge retrieval via semantic search. | |
| quiz-mcp-server alumnx-ai-labs/quiz-mcp-server Enables interactive quiz sessions via natural language, supporting user registration, question retrieval, answer validation, leaderboard generation, and answer review, with optional MySQL persistence. | |
| VignanUniversity MCP Server alumnx-ai-labs/vignan-university-mcp-server Enables semantic search over the Vignan University knowledge base using Pinecone vector storage and Sentence Transformers. | |
| aki-mcp-sv alunoconnections0-coder/aki-mcp-sv Enables Claude AI to securely access files, run shell commands, and search through a Windows computer with explicit user permission. | |
| mcp-dagster aluriak/mcp-dagster Enables querying a Dagster instance's GraphQL API for overviews, assets, partition states, runs, sensors, and schedules, with write operations refused by default. | |
| hedgedoc-mcp aluriak/mcp-hedgedoc Enables reading HedgeDoc notes, retrieving note metadata, revisions, and history, and creating new notes through a shared service account, with an optional read-only mode. | |
| Umami MCP Server alurith/umami-mcp-server MCP server exposing Umami analytics (Cloud + self-hosted) | |
| Aluvia aluvia-connect/aluvia The Aluvia MCP server exposes browser session management, geo-targeting, and account operations as Model Context Protocol tools for AI agents. | |
| mcp-corp alvaradojuanm/mcp-corp A corporate MCP server template in Python, built with FastMCP for stateless, scalable deployment behind a load balancer with health/readiness endpoints and JSON structured logging. | |
| samsung-tv-mcp alvarengajr1/samsung-tv-mcp Enables AI agents to control a Samsung Tizen smart TV on the local network directly over its local APIs, with no cloud account or hub required. Agents can check power and volume status, switch the TV on or off, send remote keys, type text, | |
| Ombre Brain alvarez05516/ombre-brain Enables Claude to keep and recall persistent long-term memories across separate conversations by tagging them with Russell's valence/arousal emotional coordinates, storing them as Obsidian-compatible Markdown, and letting them decay and res | |
| cloakbrowser-mcp alvarez207/cloakbrowser-mcp Enables AI agents to perform browser automation through Playwright-compatible tools on a specialized Chromium runtime, with npm/Docker deployment, persistent profiles, proxy matching, and stdio or Streamable HTTP transport. | |
| Agent Search MCP alvarez29125/agent-search-mcp Enables English and Chinese web search without an API key, returning compact multi-source evidence with provenance, visible provider failures, and bounded request and evidence budgets, while optionally using paid providers under an explicit | |
| Claude Soul alvarez4658/claude-soul Enables Claude Code to retain facts, decisions, and lessons across sessions through local semantic search, and to automatically detect, classify, and trend user corrections as behavioral patterns. It also runs reflection cycles that promote | |
| AutoCAD MCP Pro alvarez577/autocad-mcp Enables AI agents to drive a live AutoCAD seat over COM or run fully headless through ezdxf, producing mechanical parts, floor plans, and P&ID sheets with ISO-compliant dimensions, tolerances, frames, and title blocks. It also reads existin | |
| Joplin MCP Server alvarez75/joplin-mcp Enables AI assistants to search, read, create, update, and delete notes, notebooks, and tags in the Joplin note-taking app through a standardized interface. It also supports file imports, trash recovery, and pattern-based notebook allowlist | |
| MS 365-21V MCP Server alvarez798/ms-365-21v-mcp-server Enables MCP-capable AI clients to access 21Vianet Microsoft 365 mail, calendar, OneDrive, SharePoint, Teams, contacts, and search as the signed-in user through Microsoft Graph China. It preserves user permissions and supports OAuth, tool fi |
27,751–27,800 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.