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 |
|---|---|
| ralph-wiggum-mcp cbuntingde/ralph-wiggum-mcp An enhanced Model Context Protocol (MCP) server implementing the Ralph Wiggum technique for iterative, self-referential AI development loops. | |
| smart-coding-mcp cbuntingde/smart-agent A stateful MCP server that provides persistent memory, deterministic static analysis, and evolving conventions for AI coding assistants. | |
| OpenDiscourse MCP cbwinslow/opendiscourse_mcp Enables access to comprehensive U.S. legislative and governmental data from GovInfo.gov and Congress.gov APIs, including bills, Congressional records, Federal Register documents, member information, and committee activities. | |
| frida-mcp cbxss/frida-mcp An MCP server that enables AI-assisted mobile security testing by exposing Frida functionality for Android application research. It provides tools for hooking Java methods, manipulating memory, managing device processes, and executing custo | |
| cdash-mcp cbyrohl/cdash-mcp Enables natural language interaction with Kitware CDash for browsing dashboards, triaging CI failures, inspecting build errors and test details, and analyzing coverage. | |
| mcp-server-ads cbyrohl/mcp-server-ads An MCP server for the NASA Astrophysics Data System (ADS) that enables searching, citation graph traversal, and bibliography management for astrophysics literature. It provides tools for computing citation metrics, resolving astronomical ob | |
| moonvy-ui-mcp cc-zzh1/moonvy-ui-mcp Enables frontend developers to read Moonvy design files, extract page lists, layer trees, node styles, design tokens, and download assets such as cutouts and snapshots for precise frontend implementation. | |
| annotation-overlay-mcp cc10143/annotation-overlay-mcp Enables DOM-aware visual annotation of web pages with drawing tools and element selection, submitting structured annotations to Claude Code via MCP for automated feedback processing. | |
| solarAI-X MCP Server cc123-king/solarai-x Enables AI agents to discover and execute solar energy domain tools such as solar cell simulation, perovskite parameter/bandgap/aging prediction, RAG knowledge retrieval, and curve/table generation through MCP. | |
| shared-video-transcriber cc1415926/shared-video-transcriber Enables users to submit Douyin/Bilibili/YouTube links or local audio/video and create reusable processing jobs, then retrieve timestamped transcripts, SRT subtitles, summaries, sampled screenshots, exports, and optional AI-rewritten scripts | |
| CoinCap MCP Server cc3-0/coincap-mcp-server Provides access to CoinCap's cryptocurrency market data and technical analysis tools via MCP, supporting assets, exchanges, markets, and more. | |
| CDB-MCP cc682/cdb-mcp Enables LLMs to perform live debugging, dump analysis, and remote debugging by exposing Microsoft CDB capabilities through MCP. It manages cdb.exe sessions, forwards commands, and returns raw debugger output. | |
| RAD Debugger MCP cc8887/raddebugger-mcp Enables native Windows x64 debugging from MCP clients, including launching or attaching to processes, managing breakpoints, stepping, inspecting call stacks and expressions, and opening crash dumps without requiring Unreal Editor or plugins | |
| UE-Editor-MCPServer cc8887/ue-editor-mcpserver Wraps Unreal Editor as an MCP server, enabling AI agents to automate editor tasks through Python scripts. | |
| Notion MCP Server ccabanillas/notion-mcp A Model Context Protocol server that provides a standardized interface for interacting with Notion's API, enabling users to list databases, create pages, and search across their Notion workspace. | |
| forx ccai40359-wq/agent-skill-forx Enables AI agents to drive the user's own already-signed-in X (Twitter) browser session over CDP, exposing one human-scale action per tool: verify the active account, read a tweet, human-like scroll the timeline, like, follow, quote, reply, | |
| conapesca-db-mcp ccalderong/conapesca-db-mcp MCP server for querying the CONAPESCA historical fishing landings database (2001–2026) from Mexico's Pacific and Gulf coasts, providing tools to extract and analyze standardized landing records (avisos de arribo). | |
| Zotero Chunk RAG ccam80/deep-zotero Enables passage-level semantic search over a Zotero library by extracting, chunking, and embedding PDF text using Gemini and ChromaDB. It provides MCP tools to perform topical searches and retrieve specific document passages with surroundin | |
| Jira Data Center MCP Server ccampora/jira-mcp MCP server that connects to Jira Data Center, enabling issue search, retrieval, creation, comments, workflow transitions, project listing, arbitrary JQL, and turning meeting notes into structured Jira stories, tasks, and bugs. | |
| MCP X++ Server ccampora/mcp_xpp Enables D365 F\&O development including object creation, modification, deletion, and analysis through the MCP standard. | |
| io.github.Hylouis233/bibverify ccampos07564/bibverify Enables researchers and AI assistants to verify BibTeX bibliographic existence and metadata consistency through identifier-first lookup and explainable multi-source matching without destructive edits. | |
| Zettelkasten MCP Server ccarvalho920/zettelkasten-mcp Enables building and traversing a networked base of atomic notes, with bidirectional semantic links, tags, and search, so Claude and other MCP-compatible clients can create, explore, and synthesize ideas. | |
| read-website-fast ccastillo2488/mcp-read-website-fast Enables AI agents to quickly fetch webpages, strip noise, and convert content into clean, link-preserving Markdown with caching and optional multi-page crawling for token-efficient web scraping. | |
| AutoCAD MCP Pro ccatalano138/autocad-mcp Enables AI agents to create, read, validate and edit CAD drawings through a single typed contract, driving either a live AutoCAD seat over COM on Windows or a headless ezdxf engine on any platform. It covers mechanical parts and ISO-complia | |
| Zettelkasten MCP Server ccatalano21/zettelkasten-mcp Enables users to create timestamped atomic notes in Markdown, bidirectionally link and tag them into a searchable knowledge graph, and explore, synthesize, or discover relationships among ideas through Claude and other MCP-compatible client | |
| getnote-web-mcp ccbilly-aipm/getnote-web-mcp This MCP server enables AI tools to read Dedao Brain (formerly Get Notes) web notes from a free account, exposing AI summaries, original transcripts, and audio attachment links or downloads, with an accompanying CLI. | |
| dsapi-mcp-server ccc007ccc/dsapi-mcp-server MCP server for Android automation that captures screen frames via DirectScreenAPI and supports touch gestures and system key operations. | |
| MCP Architect ccc0168/mcp-architect Provides comprehensive architectural expertise through specialized agents, resources, and tools for generating, evaluating, and modifying architectural designs. | |
| Modes MCP Server ccc0168/modes-mcp-server The Modes MCP Server allows for comprehensive management and control over custom operational modes, supporting full CRUD operations, schema validation, and real-time configuration changes for enhanced mode management. | |
| paicli ccc231230/paicli-python Exposes the agent's built-in tools, such as file operations, shell commands, web search, memory, skills, and code search, as MCP tools over stdio or HTTP, allowing external MCP clients to invoke them directly. | |
| WishOS Hub cccat6/wishos-hub Enables agents to discover devices, query their capabilities, invoke system calls, and stage resources or deliver apps to connected WishOS hardware through a self-hosted connector and relay. It routes device-initiated tasks into an existing | |
| GPT-SoVITS MCP Server ccccr231/gpt-soviuts-mcp Bridges a running GPT-SoVITS API into MCP clients for local speech synthesis with reference-audio emotion mapping, dialogue WAV stitching, voice and status inspection, and bounded audio resource retrieval over stdio or Streamable HTTP. | |
| deepddw ccch713/staffwright Exposes shared cross-session memory, company knowledge-base search, and document search as tools that a chat model can auto-invoke, letting a small team on one self-hosted network accumulate and retrieve context. Runs over streamable-http s | |
| Sorftime MCP Server ccchenhuohuo/sorftime-mcp Remote MCP server for read-only Sorftime Enterprise API access, enabling product, category, and keyword data queries with per-user JWT authentication and audit logging. | |
| Washington Law MCP Server ccchow/washington-law-mcp Provides offline access to Washington State's Revised Code of Washington (RCW) and Washington Administrative Code (WAC) for AI agents. Enables fast retrieval, full-text search, and navigation of all Washington state laws through natural lan | |
| Chinese Sensitive Words MCP Server cccpan/chinese-sensitive-words-mcp Detects Chinese sensitive/forbidden words across platforms like Xiaohongshu, Douyin, Kuaishou, and Bilibili, with risk levels and replacement suggestions. | |
| Data Verify MCP Server cccpan/gebaini An MCP server that provides comprehensive data verification in China, including identity, business, vehicle, OCR, and risk assessment services. | |
| mysql-mcp-pro ccct173/mysql-mcp-pro A production-grade MySQL MCP Server that enables AI assistants to securely and efficiently operate MySQL databases through a standardized protocol. | |
| mcp-test ccczss/mcp-test test | |
| FMP MCP Server ccdatatraits/fmp-mcp-server An MCP server that provides tools for financial analysis using the Financial Modelling Prep API. It enables users to retrieve real-time stock quotes, financial statements, valuation metrics, and sector performance data for investment resear | |
| fotmob-mcp ccdejene/fotmob-mcp Enables access to live FotMob football data for fixture lookup, team and player research, match details, lineups, league discovery, and search-based entity lookup. | |
| localagents ccebelenski/localagents Enables Claude Code to delegate agent tasks to local LLMs via llama.cpp or vLLM servers on your own hardware, reducing API usage while maintaining full agent capabilities. | |
| rf-log-mcp cceniam/rf_log_mcp An MCP server for analyzing Robot Framework test results. It provides LLMs with tools to parse, summarize, and search through test execution logs from XML or JSON output files. | |
| sql-explorer ccervantes369/mcp-sql-explorer Enables AI assistants to query SQLite databases using plain language, with strict read-only enforcement and column-level access control to prevent damage or unauthorized data reads. | |
| mcp-response-types-lab cchadha2/mcp-response-types-lab Enables testing how different MCP clients handle tool results containing both content and structuredContent, including outputSchema enforcement and mismatch scenarios. | |
| mcp-youtube-transcript cchamp-msft/mcp-youtube-transcript Enables MCP-compatible assistants to retrieve caption text from YouTube videos as either plain text or timestamped snippets for reading, summarizing, or searching. Supports local stdio and stateless HTTP deployments for integration with Cla | |
| mcp-todo-server cchanquispe08-blip/mcp-todo-server A basic MCP server that exposes a to-do list, letting users read tasks, add new tasks, mark them complete, and generate a daily summary. | |
| web-recorder cchaofei/chrome-web-recorder Records Chrome network requests and responses for LLM knowledge bases, and exposes query and browser control capabilities via MCP tools like list_sessions, navigate, and evaluate. | |
| substack-mcp cchen7/substack-mcp An MCP server that gives Copilot access to Substack posts from your authenticated reader account, including paid subscriptions, enabling daily summary generation by syncing, caching, and summarizing posts. | |
| Google Analytics MCP server on Cloudflare Workers cchesebro-prog/ga_mcp_cf Enables MCP clients to read Google Analytics 4 data, deployed as a Cloudflare Worker with service account authentication. |
37,201–37,250 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.