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 |
|---|---|
| discord-mcp arrrnmp/discord-mcp Control your Discord server with AI. Lets you manage channels, roles, members, messages, and more through natural language. | |
| vuln_mcp_app arrugit/vuln_mcp_app An intentionally vulnerable, locally-runnable MCP security laboratory (a 'DVWA for MCP') used to evaluate a separate FYP security scanner. | |
| MCP Credentials Broker ars-system/mcp-credentials-broker Provides secure OAuth2-based credential management for MCP servers, allowing agents to obtain short-lived token references without exposing raw secrets. | |
| shopify-inventory-mcp arsalan-arshad/shopify-inventory-mcp Enables AI assistants to compute deterministic inventory demand forecasts, days of cover, stockout dates, reorder points, and safety stock from a store’s read-only Admin API data via local MCP tools. | |
| Theta-MCP arsalannkhann/theta-mcp A comprehensive sales automation platform combining Model Context Protocol (MCP) server with Gemini AI voice interface, featuring 13+ integrated sales tools and AWS deployment capabilities. | |
| conformo arsalmurad/conformo Enables agents to create, validate, and convert legally valid e-invoices in formats like EN 16931, Factur-X/ZUGFeRD, XRechnung, UBL 2.1, and Peppol BIS. | |
| Arsel MCP Server arsel-sa/arsel-mcp Enables AI agents to read and manage contacts, lists, tags, events, templates, campaigns and message logs in an Arsel organization, and to draft email, SMS, push and in-app campaigns for review. It is read-and-draft only, so agents can crea | |
| MGSV MCP arsenal-pt/mgsv-mcp Enables an MCP-capable assistant to search and cite Metal Gear Solid V modding documentation, browse catalogued upstream source at pinned commits, and inspect file headers and hashes. It also stages copies of files into isolated job folders | |
| Amazon Seller MCP Server arseniib-o/amazon-seller-mcp Enables managing Amazon seller accounts directly from an AI assistant, with tools for listings, orders, pricing, inventory, and multi-marketplace switching. | |
| SEO Intellect MCP arseniigruzdev/engine-seointellect-mcp Enables MCP hosts to access 22 SEO Intellect API tools, handling task submission, polling, and retrieval for SEO analysis workflows. | |
| MCP PostgreSQL Explorer arseniytech/mcppostgresqlexplorer Enables AI clients to explore a PostgreSQL database schema and run read-only queries, including listing tables, describing columns, executing SELECT queries, and retrieving foreign key relationships. | |
| ContextVault arsenkylyshbek/context-vault Shared context storage for AI agents. Enables any MCP-compatible model to store, read, and search context entries through the MCP server, with a web UI for management. | |
| Playwright MCP arsenygrozny-blip/playwright-mcp-render-mvf63u1g Enables AI assistants and MCP clients to drive a hosted headless Chromium browser over HTTP — navigating, clicking, typing, and reading pages via structured accessibility snapshots rather than screenshots. Runs as a Render web service behin | |
| Playwright MCP arsenygrozny-blip/playwright-mcp-render-mvf650g1 Provides a hosted, bearer-token-protected HTTP endpoint where any MCP client can drive a headless Chromium instance — opening pages, navigating, clicking, typing, and reading content through accessibility snapshots — without installing a br | |
| Talos MCP Server arshabmohan03-hash/talos-mcp-server Enables AI assistants to perform defensive security tasks such as vulnerability detection, CVE lookup, phishing/link safety checks, and security report generation via MCP tools. | |
| Timesheet MCP Server arshad-khan1/timesheet-mcp Enables automated timesheet management including creating entries, listing work activities, managing daily scrum updates, and viewing assigned projects with automatic authentication handling. | |
| council-mcp arshadalkaladi/council-mcp Enables Alexa+ to request a background deliberation from four independent perspectives, returning a synthesis with preserved dissent and a full audit trail over MCP. | |
| gmail-mcp-server arshdeep54/gmail-mcp Lets users search and read Gmail messages and threads, list labels, and create drafts via the official Gmail API, with self-hosted OAuth for privacy. | |
| ArShield MCP arshield/arshield Exposes six stdio tools that let MCP clients such as Claude or Cursor seal files and short messages into hybrid post-quantum .arshield envelopes (ML-KEM-768 + X25519, ML-DSA-65 signatures) and open them again using the same keys — passphras | |
| OpenPaper MCP Server arshit09/openpaper Lets AI agents design alongside you on a live canvas by reading, writing, styling and inspecting real HTML/CSS designs, capturing pixel-accurate screenshots, exporting assets and PDFs, and managing design tokens, comments and files. It expo | |
| Upwork MCP Server arshiyan-elahi/upwork-mcp-server Enables Claude to search jobs, manage proposals, messages, and contracts on Upwork via browser automation. | |
| plotly-mcp-cursor arshlibruh/plotly-mcp-cursor Enables creating Plotly charts from natural language in Cursor, supporting a wide variety of trace types with full customization. | |
| Storykeeper arshpreet-svg/storykeeper Enables families to interview elders through Alexa, preserve their stories, recipes, health history, and document locations, and query a sourced, conflict-aware family archive. | |
| BridgeMCP arsie-codes/bridgemcp A Python framework for building MCP servers that makes it simple to expose application data and actions to AI clients like Claude Desktop, Cursor, and VS Code through the Model Context Protocol. It wraps protocol handling behind a clean, de | |
| bridgemcp-server-filesystem arsie-codes/bridgemcp-server-filesystem Provides safe filesystem access for AI clients with root confinement, read-only mode, and file operations like read, write, search, copy, move, delete. | |
| bridgemcp-server-weather arsie-codes/bridgemcp-server-weather Provides weather data including current conditions, forecasts, and summaries via Open-Meteo with no API key required, enabling natural language queries through an MCP interface. | |
| todo list mcp server arslan-codes097/todo-list-mcp-server it is a simple to-do list CRUD MCP Server | |
| tradingview-chart-mcp arslan7371/tradingview-chart-mcp Enables retrieval of chart snapshot images for specified ticker symbols and intervals, with browser pooling for concurrent requests and built-in performance statistics. | |
| BitBucket-MCP-To-Review-PRs arslanismail/bitbucket-mcp-to-review-prs A read-only MCP server for the Bitbucket Cloud REST API v2.0 that enables AI assistants to browse workspaces, repositories, and review pull requests. | |
| Apple Notes MCP Server arslankhanali/apple-notes-mcp Enables interaction with Apple Notes on macOS through AppleScript, allowing users to list, search, read, create, update, and delete notes across accounts and folders. | |
| MCP Reasoning Engine arslanmanzoorr/mcp A production-ready reasoning engine that integrates Claude AI with specialized MCP tools for knowledge retrieval, schema validation, and domain-specific rubric evaluation. It enables structured RAG-based analysis across legal, health, and s | |
| Chinook MCP Server arslanmunawar0/chinook-mcp-server Enables AI assistants such as Cursor and Claude Desktop to explore and query a SQLite database in plain English, with schema inspection, table sampling, and safe read-only SQL execution. Ships with the Chinook sample database and can be poi | |
| azure-devops-attachment-mcp-server arslanmusta/azure-devops-attachment-mcp-server Enables AI assistants to manage work item attachments on Azure DevOps Server (on-premise) via the REST API, supporting listing, uploading, deleting, and downloading attachments. | |
| ars-nova-github-max arsnovasingers/ars-nova-github-max Gloves-off GitHub MCP server providing full REST and GraphQL passthrough, enabling branch deletion, release creation, and asset uploads beyond the stock GitHub MCP server. | |
| ars-nova-wordpress-mcp arsnovasingers/ars-nova-wordpress-mcp Local MCP server for managing arsnovasingers.org via the WordPress REST API, currently providing read-only audit tools for posts, pages, media, users, SEO, and site settings. | |
| forwardemail-mcp arsols-labs/forwardemail-mcp MCP server for Forward Email that provides tools to manage email inbox, send mail, calendar events, and contacts. | |
| SecureAnnex MCP Server arsolutioner/secure-annex-mcp A Model Context Protocol (MCP) server for analyzing browser extension security, providing tools for vulnerability detection, signature checking, code review, and security evaluation. | |
| cdt arsonist-g/cdt Enables driving an isolated, already-logged-in Microsoft Edge browser from the shell by reusing your daily Edge's login cookies through a browser-extension bridge. | |
| MS SQL Server MCP Server arsyadal/mssql-mcp Enables connecting to local or remote MS SQL Server instances and provides tools for testing connections, listing databases and tables, describing schemas, and executing T-SQL queries. | |
| artdaddy art-daddy/artdaddy Enables AI agents to drive a desktop video editor through MCP, providing the same editing operations as the user — placing, trimming, rippling, grading, captioning, and exporting — on the actual project with local rendering. | |
| allinkl-mcp art-design-digital/allinkl-mcp MCP server for All-Inkl KAS API to manage DNS, domains, mailboxes, mail forwards, and databases, including database dumps via SSH+mysqldump. | |
| Kaggle MCP Server art-qalam-fr/kaggle-mcp Enables AI assistants to work with the Kaggle API locally over stdio, covering competitions, datasets, kernels, models, benchmarks, and discussions — including discussion search, solution write-ups, and trending topics missing from the offi | |
| mcp-mux art-qalam-fr/mcp-mux Presents multiple stdio backend tool servers to an MCP client as one aggregated server, sharing those backend processes across concurrent agent sessions through a background broker while namespacing and routing each tool call to the right b | |
| Qdrant MCP Server art-qalam-fr/qdrant-mcp-server Enables semantic and hybrid search over documents and codebases backed by a Qdrant vector database, with collection management, document CRUD, metadata filtering, and AST-aware code indexing using local or cloud embedding providers. Support | |
| (Non-Data-Lake) Sentinel and XDR MCP Server art-r/sentinel-xdr-mcp Provides governed MCP tools for querying optionally restricted Microsoft Sentinel/Log Analytics tables and optional Defender XDR hunting data, retrieving incidents and entities, and—for agent identities only—adding attributed incident comme | |
| delegate-mcp art-ws/delegate-mcp An MCP server that delegates reading of files or long context to a cheap model, returning a tight answer to save the orchestrator's context window. | |
| СДАМ ГИА MCP Server art22017/sdamgia-mcp-server Enables LLMs to search and retrieve exam problems, solutions, and answers from the СДАМ ГИА educational platform across multiple subjects. It supports fuzzy text matching, catalog browsing, and structured data retrieval to assist with acade | |
| MCP-Quant Financial Research art3mis-xo/mcp-quant-financial-research Enables deterministic financial research by retrieving price history, calculating risk metrics such as Sharpe ratio and drawdown, and generating cited, provenance-aware reports. | |
| Agent Bridge art3mk4/agent-bridge Enables two coding agents to exchange tasks, results and bounded goal-driven conversations through a shared local SQLite database over MCP stdio, with atomic claims, expiring leases and optional headless dispatch. It keeps everything local, | |
| pdhapi-image-mcp art793351/pdhapi-image-mcp Enables generating and editing images through the PdhAPI within MCP clients such as Codex, Claude Code, and Cursor, using the user's own API key. Supports text-to-image, single-image editing, multi-reference fusion, and batch editing with c |
30,651–30,700 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.