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 |
|---|---|
| ccdesk asloth/ccdesk Grants Claude Code desktop-control capabilities on Linux, including screenshots, mouse movement and clicks, keyboard input, window listing and focusing, and clipboard access. | |
| Meta Ads MCP Server asm-2023/claude-meta-mcp Enables Claude to fetch and analyze Meta ad accounts, campaigns, ad sets, ads, and performance insights via the Meta Marketing API. | |
| Shipping Cost MCP Connector asm-2023/claude-shipping-mcp Pulls real and estimated shipping costs from Shiprocket and Delhivery into Claude, with rollup summaries for yesterday, last 7 days, MTD, and last 30 days. | |
| hangang-code-graph asm-hangang/hangang-code-graph MCP server for indexing source code from repositories into a Neo4j graph database and enabling Graph RAG-based search and traversal of functions via natural language queries. | |
| resume-tailor-mcp-server asma-amin/resume-tailor-mcp Helps job seekers tailor their resume and generate cover letters against a specific job posting, powered by Claude. | |
| pgscout asmahdy1420-cmyk/pgscout Enables agents to safely inspect a PostgreSQL database read-only: discovering schemas and tables, running guarded SELECT/EXPLAIN queries, and getting plan summaries with index suggestions. Access is constrained by schema allowlists, denied- | |
| android-mcp asmanovlev/android-mcp Enables AI agents to control Android devices via ADB, supporting gestures, input, screenshots, UI analysis, and app management. | |
| PROXY6 MCP Server asmanovlev/proxy6_mcp Enables managing proxies through the PROXY6.net API, including account info, proxy listing, purchasing, prolonging, and checking. | |
| Dispatch asmiia/dispatch This MCP server enables AI agents and teams to coordinate through shared inboxes, threaded conversations, attachments, expiring file reservations, prompts, and live notifications, while replaying missed events after restarts. | |
| mcp-atlassian asmma/mcp-atlassian-confluence-dc Enables GitHub Copilot in VS Code to connect to Confluence and Jira Data Center using Personal Access Token authentication without Docker, supporting natural-language access to those instances. | |
| reasonix-mcp asmodeusx/reasonix-mcp Bridges MCP clients to interactive Reasonix agents, letting you spawn, steer, poll, resume, and manage agents via tools and callbacks. Enables orchestrating long-running AI agents from any MCP host. | |
| asmy-mcp-server asmydev/mcp-server-asmyagent Exposes the Asmy Digital Store product catalog, promo codes, and shop statistics as MCP tools for AI agents. | |
| arialog-mcp asnd/arialog-mcp Enables read-only querying and server-side reduction of VMware Aria Operations for Logs (vRealize Log Insight) 8.18.x data, including event aggregation with spike detection, message signature grouping, and capped raw log search. | |
| Helx MCP Server asno-dev/helx Provides AI agents with 20 tools to create, read, edit, validate, convert, and render documents across formats like DOCX, XLSX, PPTX, PDF, Markdown, HTML, and CSV, including charts, diagrams, templates, and CSV data operations over stdio. | |
| odse-mcp asobacloud/odse-mcp MCP server for converting OEM energy telemetry payloads into ODS-E records and validating them via the odse Python package. | |
| sdlc-integrity-mcp asobacloud/sdlc-integrity-mcp MCP server that provides audit and safety-check tools for enterprise SDLC code integrity, enabling AI agents to scan workspaces for lifecycle gaps, mock-theater tests, DRY violations, and language-specific issues in shell, JavaScript/HTML, | |
| MCP Server for Apache Jena asoler2004/mcp-jena-http Enables AI agents to query and modify RDF data, list named graphs, and access pre-built SPARQL templates on a Fuseki server, with optional HTTP Basic authentication. | |
| Antigravity PDF MCP Server asoluka/antigravity-pdf-mcp Enables intelligent ingestion and querying of PDF, Markdown, and text files using hybrid search that combines keyword matching and semantic embeddings with citations. | |
| ASON MCP Server ason-format/mcp-server Enables compression and decompression of JSON data using the token-optimized ASON format, reducing token usage by 20-60% for LLM applications. | |
| ReActMCP Web Search ason28406/reactmcp Enables AI assistants to perform real-time basic and advanced web searches through the Exa API, returning Markdown-formatted results with titles, URLs, publication dates, and content summaries. | |
| agntcon-2026 asoshnin/agnt_mcp_con_2026 Enables agentic systems to search and retrieve conference talk details, ask grounded questions about the conference, list talks and concepts, and monitor server queue status via native MCP tools. | |
| Public Safety MCP Server asouthern729/tyneside-public-safety-mcp-ts Connects to CAD/AVL database and NERIS API to expose operational tools for public safety data analysis, including incident search, unit tracking, and cross-source correlation. | |
| edgar-mcp asp53826/edgar-mcp An MCP server that enables models to access SEC EDGAR filings, filing text, and XBRL financial facts with caching, rate limiting, and iXBRL stripping. | |
| SmartUp MCP aspanferov/smartup-mcp Enables AI assistants to read orders, stock, prices, contractors, payments, debts, and sales from SmartUp ERP, with optional write capabilities for creating and updating orders and contractors when explicitly enabled. | |
| BWiki MCP Server aspd199/bwiki-mcp-server Enables LLM clients to read and edit pages across the BWiki wiki farm using their own bilibili account credentials, with about 30 tools covering page search and history, page creation, editing, moving, deletion and protection, file uploads, | |
| iMovie MCP Server aspectrr/agent-video-toolkit An MCP server that enables AI-powered video editing with iMovie on macOS. | |
| Loyal Spark Loyalty Protocol aspekt19/unboxed-loyalty-spark MCP server for managing on-chain loyalty programs on Base L2. Mint tokens, manage rewards, track balances, tiers and marketplace offers via standard MCP protocol. | |
| gamm asphaltanchors/gamm Lets AI agents query Google Ads freely while routing every write through a passkey-approved, rule-checked, audited change workflow. It issues per-agent keys, validates proposals against configurable guardrails, and applies approved changes | |
| sjtu-canvas-mcp aspirin0000/sjtu-canvas-assistant Provides MCP tools to read SJTU Canvas data, download course files, and access video/subtitle resources without authentication simulation. | |
| Lazy-Loader aspirin106/lazy-loader Starts local MCP backend servers only when their tools are called, exposes their tools through a single stdio gateway, preserves stateful sessions, and can stop safely restartable backends after idle timeouts. | |
| mpp-mcp-gateway aspiring-100x/mpp-mcp-gateway A TypeScript library that lets you build MCP servers whose tools charge stablecoins per call and AI agents that pay for those tools automatically via the Machine Payments Protocol on Tempo. | |
| Aspose.Cells Cloud MCP Server aspose-cells-cloud/aspose.cells-cloud-mcp-server Automates Microsoft Excel spreadsheet creation and editing via MCP tools for any MCP-compatible client. | |
| Aspose.Cells Cloud MCP Server aspose-cloud/aspose-cells-cloud-python-mcp Enables AI agents to process Excel workbooks through Aspose.Cells Cloud, including converting, creating, merging, splitting, replacing text, and reading workbook properties and worksheets, with bundled storage operations for a complete uplo | |
| Aspose.Email Cloud MCP Server aspose-cloud/aspose-email-cloud-python-mcp Enables reading, converting, and managing email messages, calendars, and contacts, along with mail account folder/thread operations and personal name parsing/formatting, via typed MCP tools. | |
| Aspose.PDF Cloud MCP Server aspose-cloud/aspose-pdf-cloud-python-mcp Enables PDF conversion to DOC, merging multiple PDFs, reading document properties, and bundled storage file operations for complete upload-process-download workflows through MCP. | |
| Aspose.Slides Cloud MCP Server aspose-cloud/aspose-slides-cloud-python-mcp Enables AI agents to create, convert, split, inspect, and edit PowerPoint and ODP presentations through typed MCP tools, including bundled cloud storage upload/download operations for a complete workflow. | |
| Aspose.Words Cloud MCP Server aspose-cloud/aspose-words-cloud-python-mcp Enables AI agents to process Word documents through Aspose.Words Cloud, supporting conversion, creation, comparison, text replacement, and retrieval of properties, statistics, and bookmarks, plus bundled storage file operations for a full u | |
| aspose-pdf-cloud-mcp aspose-pdf-cloud/aspose-pdf-cloud-mcp MCP server for Aspose PDF Cloud, enabling PDF storage, conversion, and extraction operations (merge, split, text/table/image extraction) via CLI and MCP. | |
| Aspose.Words MCP aspose-words/aspose.words-mcp Aspose.Words MCP is a FastMCP-based MCP server built on top of Aspose.Words for Python via .NET. It automates Microsoft Word document creation and editing and exposes operations as MCP tools that any MCP-compatible client can call. | |
| usda-mcp asquarer02/usda-mcp An MCP server that provides a USDA-accurate food database with deterministic macro math, enabling tools like list_foods, get_food, calculate_macros, filter_by_diet, build_meal, and list_available_tags. It allows Claude to look up nutrition | |
| casefile-mcp asrgrimmi-cyber/casefile Enables AI assistants to convert screen recordings of test sessions into narrated, captioned, highlighted walkthrough videos and subtitle files, using offline text extraction and local rendering. | |
| Flux asrvd/flux An AI-powered MCP server that enables natural language interaction with AO (Arweave Operating system) for creating, running, and testing code and handlers without manual coding. | |
| GPT Researcher MCP Server assafelovic/gptr-mcp Enhances LLM applications with deep autonomous web research capabilities, delivering higher quality information than standard search tools by exploring and validating numerous trusted sources. | |
| VE-MCP assebler-grkha/ve-mcp Enables AI agents to autonomously edit videos into publish-ready vertical short-form content, including silence removal, subtitle generation, voiceover synthesis, color grading, and composite pipeline creation. | |
| Assembly MCP assemblyarchitects/assembly-mcp Converts PDF to Markdown and Markdown to PDF using PyMuPDF and WeasyPrint engines. | |
| assessorai-dados assessorai/assessorai-dados Enables searching and retrieving Brazilian legislative propositions, reading their full texts, finding related propositions, and accessing dataset releases and downloads with provenance and official source URLs. | |
| assetCLI assetcli/assetcli-init Enables natural language interaction for token launches, liquidity management, and treasury operations on Solana via the Model Context Protocol. | |
| AssetLab MCP Server assetlab-canada/mcp Connects Claude, ChatGPT, Microsoft Copilot, and other MCP clients to an AssetLab asset management account, letting users query and manage work orders, PM schedules, capital projects, infrastructure networks, and other records in plain lang | |
| ollamadev-mcp-server asshat1981ar/ollamadev-mcp-server Companion MCP server for the OllamaDev Android app, providing 36 tools for SDLC phases including filesystem, code intelligence, build, sprint workflow, and agentic self-prompt via a local Ollama model. | |
| Remote MCP Server (Authless) assifayoub/remote-mcp-server-authless A template for deploying an unauthenticated Model Context Protocol server on Cloudflare Workers that can be accessed remotely by MCP clients like Claude Desktop or the Cloudflare AI Playground. |
31,301–31,350 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.