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 |
|---|---|
| telegram-channel-mcp-server eduard256/telegram-channel-mcp Enables publishing and managing posts in a Telegram channel via the Bot API, including text, media, polls, paid content, and editing/deleting/pinning. | |
| Calculadora MCP eduardabrandao-code/calculadora-mc Provides a basic calculator tool for arithmetic operations (addition, subtraction, multiplication, division) with division-by-zero handling, and a temperature conversion tool between Celsius and Fahrenheit. | |
| Selectel Billing MCP Server eduardguselnikov/mcp_selectel_billing Enables fetching Selectel billing balances and predictions via MCP tools, with automatic token refresh and account management. | |
| Gooseworks MCP eduardkuun/gooseworks-mcp A Model Context Protocol (MCP) server that exposes GitHub tools for repository management, code search, issue creation, and pull request operations. | |
| mcp-invoices eduardmcfly/mcp-invoices An MCP server for managing invoices with DynamoDB, offering tools to create, retrieve, and list invoices, plus a REST API. | |
| Google Search Console MCP eduardmur/gsc-mcp Enables MCP clients to retrieve Search Console search analytics, find multilingual question-shaped queries and SEO opportunities, inspect URLs, and view or manage sitemaps with server-side date resolution and comparisons. | |
| Mailport eduardo-bolognini/mailport-mcp Connects multiple IMAP and SMTP mailboxes to MCP clients like ChatGPT without exposing credentials, enabling email search and thread retrieval via natural language. | |
| MCP Accounting eduardo-lucas/mcp-accounting An API-based accounting analysis tool that identifies financial anomalies like unusually large transactions and duplicate payments from CSV datasets. It allows AI agents to perform automated financial auditing and transaction analysis throu | |
| worldcup-2026-mcp eduardo-lucas/worldcup-2026-mcp Query FIFA World Cup 2026 data including matches, standings, teams, and statistics. | |
| Aspen Plus V15 MCP Server eduardo-mariola/aspen-plus-mcp Enables MCP clients such as Claude Code or Claude Desktop to drive Aspen Plus V15 through its COM interface — opening and running simulations, reading and writing any tree node, editing flowsheets, diagnosing convergence, and designing RadF | |
| AutoCAD Plant 3D MCP Server eduardo-mariola/autocad-plant3d-mcp Enables Claude to build, check and renumber real P&ID sheets through the Plant 3D .NET API, run read-only project-database and live-drawing audits, and use general drafting and 3D-piping query tools. | |
| yampi-mcp eduardo-orsi/yampi-mcp An MCP server that lets you manage a Yampi e-commerce store through natural language, enabling operations like looking up orders, creating products, adjusting stock, and building coupons and offers. | |
| mcp-server-enterprise eduardo-rezende-mdk/mcp-server-enterprise-blueprint Enables AI agents and clients to delegate deterministic operations such as calculations, validation, parameterized queries, and tool execution to a FastMCP-backed service, reducing token usage and hallucinations while supporting local, tunn | |
| dbt-doctor eduardo488/dbt-doctor Enables AI assistants to audit dbt projects for documentation, test coverage, and naming health, profile warehouse data, detect schema drift against the manifest, and non-destructively generate or update schema.yml documentation and tests t | |
| Forge Neo MCP eduardoabreu81/forgeneo-mcp Enables AI agents to generate images on a local Stable Diffusion Forge Neo instance, automatically inferring prompt style and sampling parameters from the user's setup and past generations, and providing tools for LoRA search, model managem | |
| OTRS MCP Server eduardoantoniojunior/otrs-mcp-server An MCP server that enables AI assistants to create, search, and manage OTRS tickets through standardized interfaces. | |
| Blender Open MCP eduardoaraujo2239/blender-open-mcp Enables AI agents to drive a live Blender session through MCP tools for scene and object control, rendering, and PolyHaven asset download. It is provider-agnostic, letting users send prompts to and switch between Ollama, LM Studio, llama.cp | |
| fastmail-mcp eduardobrito21/fastmail-mcp Enables AI assistants to manage Fastmail email accounts via JMAP, including reading, sending, organizing emails, and handling mailboxes, drafts, and masked emails. | |
| knowledge-base-server eduardoc726/knowledge-base-server Enables AI agents to share persistent, searchable memory by ingesting and syncing knowledge from sources like Obsidian, code, documents, and web captures, then serving it through MCP and REST APIs with classification, synthesis, and tiered | |
| DesktopCommanderPy eduardoddddddd/desktopcommanderpy A Python MCP server that provides controlled access to local filesystem, terminal, processes, and SAP HANA Cloud, enabling Claude to interact with your machine and databases securely. | |
| sapmcp eduardoddddddd/sapmcp Enables operating and querying SAP ECC/S/4HANA systems via SAP NetWeaver RFC SDK, exposing MCP tools, resources, and prompts for LLMs. | |
| youtube-music-mcp eduardoddddddd/youtube-music-mcp MCP server for read-only access to YouTube Music, enabling exploration of liked songs, playlists, and catalog searches without exposing credentials. | |
| Secure MCP Server Template eduardodknight/mcp-server-template Provides secure, read-only database queries, HTTP GET requests with anti-SSRF protection, and file reading within a restricted directory. | |
| ReferenceMCP eduardofarina/referencemcp An academic reference manager MCP server that enables searching papers across multiple sources, managing references locally, and formatting citations in 10,000+ styles. | |
| treadle eduardohos/therblig Enables AI agents to read, explain, lint, and edit existing BPMN 2.0 files in a repository while preserving diagram layout and structural integrity through parsed-document patch operations. | |
| MORAGENT AI Agent Studio eduardomoraga/moragent Turns Claude Code into an AI Agent Studio with a guided menu and 11 tools to design, create, and manage multi-agent projects without coding. | |
| scrcpy-mcp eduardomorris270/scrcpy-mcp Enables AI agents to see and control Android devices through ADB and scrcpy, offering fast screenshots, input, UI automation, app management, file transfer, shell commands, and audio/video streaming. | |
| Pentest MCP eduardororato392/pentest-mcp Enables professional penetration testers to run authorized reconnaissance, web/content scanning, brute-force checks, traffic capture, extraction sweeps, and reporting workflows through MCP-compatible transports. It supports engagement recor | |
| Magg eduardoroussel8389/magg An MCP server that aggregates, manages, and proxies other MCP servers, enabling LLMs to discover, add, configure, enable/disable, and use tools from multiple servers dynamically. | |
| Blender Open MCP eduardosidorov41996/blender-open-mcp Enables AI agents to control a live Blender session through the Model Context Protocol, exposing tools for scene and object management, materials, rendering, and PolyHaven asset downloads. It also lets agents send prompts to a swappable LLM | |
| canvas3d-mcp eduardosm123/mcp-3d-llm Enables AI agents to create, render, and validate 3D scenes, 2D art, and games in HTML canvas using Three.js, WebGL, or Canvas 2D, with multi-angle screenshots, structured validation reports, and interactive playtesting. | |
| cc-bridge eduardruzsa/claude-codex-bridge Enables Claude Code and OpenAI Codex to exchange messages directly within their sessions, including optional cross-review of plans, without copying between terminals. | |
| Odoo MCP Server edubolivar/odoo-mcp-server An enterprise-grade MCP server for interacting with Odoo ERP through AI assistants, enabling guided workflows, native BI, and deep introspection. | |
| mcp-tableau edudutra/mcp-tableau MCP server that automates the publishing and validation of Tableau workbooks and data sources on Tableau Server or Tableau Cloud, enabling an AI agent to discover, build, validate, and publish content without human intervention. | |
| UTCP Documentation MCP Server edujuan/utcp-docs-server Assists AI coding agents in understanding and implementing UTCP by providing documentation search, manual validation, code generation, OpenAPI conversion, and an LLM-powered expert agent. | |
| amocrm-mcp edulabtechnic-source/amocrm-mcp Enables Claude Code to access amoCRM data such as pipelines, deals, contacts, and users via the MCP protocol. | |
| ViaCEP Brasil MCP Server edum-compassuol/viacep-brasil-mcp-server Enables AI tools to query Brazilian addresses by CEP or search CEPs by address via the ViaCEP API. | |
| Instagram MCP Server edunascimentt/insta-mcp Enables managing multiple Instagram business accounts via a single token using Facebook Graph API and Partners model. | |
| knowledge-hub-mcp edunavajas/knowledge-hub-mcp-server Enables MCP clients to query a self-hosted knowledge base through n8n RAG webhooks and Outline, supporting semantic search, full document reads, index health checks, and reindexing of Outline collections or repository Markdown. | |
| edge-forge-mcp eduplopez/mcp-edge-vision-forge Enables AI agents to export PyTorch models to validated ONNX, quantize them to FP16 or INT8, measure fidelity drift and benchmark latency and memory against edge hardware budgets. It also autonomously searches export and precision configura | |
| Sandbox Agent eduresser/sandbox-agent Enables code execution in isolated Docker containers with persistent IPython, Node.js, or R kernels, supporting file import/export and cross-session transfers via MCP tools. | |
| sqlite-mcp eduresser/sqlite-mcp An MCP server that enables AI agents to interact with SQLite databases by querying schemas, executing SQL, and inspecting table metadata. It supports safe database access through configurable read-only modes, query timeouts, and dry-run exe | |
| Biwenger World Cup 2026 Lineup Optimizer edurodelg/biwenger-mcp Optimizes your starting XI for Biwenger World Cup 2026 using fixed prices, with API endpoints for lineup optimization, player comparisons, and captain picks. Operates locally without accessing your actual Biwenger account. | |
| network-mcp-server edutacara/network-mcp-server MCP server for network operations that lets AI assistants interact with Cisco/Juniper network devices through safe, well-defined tools like compliance audits and configuration backups. | |
| postsmith eduumach/postsmith Enables coding agents to act as an Instagram post studio for multiple brands: it builds creative briefs from each brand's palette, fonts, voice and CTA, renders agent-written HTML/CSS slides into correctly sized PNGs with captions, and gene | |
| Anki Card Manager (acm) eduvent/anki-mcp This MCP server connects Claude with Anki, allowing users to create flashcards conversationally and automatically deduplicates, classifies, and uploads them without manual copying and pasting. It runs locally with Ollama for embeddings and | |
| Solibri MCP Server edvardgk/solibri-mcp-server Enables remote automation of Solibri Office tasks including model checking, quantity takeoff, and model management through an MCP SSE interface. | |
| gimp-mcp edvardks/mcp-gimp Enables AI agents to drive GIMP 3 over MCP, covering layers, selections, painting, text, color adjustments, GEGL filters, raw PDB procedures, and free-form Python inside GIMP, with image previews so the agent can see the result of each step | |
| notes-mcp edvardlindelof/notes-mcp A simple MCP server for chatbot/human collaborative management of text content stored as markdown files with YAML frontmatter. | |
| akari-x402-mcp edvyno/akari-x402-mcp Enables MCP clients to call live x402-metered crypto intelligence tools for Hyperliquid funding and market data, TradingView technical analysis, wallet balances, trade plans, and desk state, paid in USDC on Base. It also supports a builder |
47,051–47,100 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.