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 |
|---|---|
| installed-version-mcp anicodeth/installed-version-mcp Gives coding agents the exact installed version of each dependency in a project from node_modules and lockfile, preventing deprecated API usage by grounding them in reality. | |
| mega-mcp anicodeth/mega-mcp Turn any public MEGA folder into a knowledge source for Claude & other LLMs | |
| opportunities-circle-mcp anicodeth/opportunities-circle-mcp Enables AI agents to search and retrieve opportunities from the Opportunities Circle catalog, including scholarships, fellowships, internships, grants, jobs, and more. Supports filtering by type, country, funding, and tags, with full detail | |
| package-verify-mcp anicodeth/package-verify-mcp Verifies npm package names for safety, detecting typosquats and nonexistent packages before your coding agent installs them. | |
| pkg-api-mcp anicodeth/pkg-api-mcp Provides the real exported API surface and type signatures of any npm package, extracted from its published TypeScript declarations, enabling AI coding agents to use functions accurately and avoid inventing nonexistent APIs. | |
| Cloudivo MCP anielk/cloudivo-mcp Model Context Protocol server that acts as an AI gateway for the Cloudivo ecosystem, exposing tools, resources, and prompts while delegating business behavior to downstream services. | |
| msteams-mcp anielyavuz/msteamsmcp Enables AI assistants to read your own Microsoft Teams chats, listing conversations and retrieving chat messages as plain text through Microsoft Graph. It runs locally with delegated, read-only permissions under your own Entra app registrat | |
| msteams-mcp anielyavuz/teamsmcp A self-hosted, read-only MCP server that lets AI assistants read your own Microsoft Teams chats and messages through Microsoft Graph using delegated permissions. It exposes tools for checking authentication status, retrieving your profile, | |
| Pixel Twin anietex/pixel-twin Enables AI coding agents to read Figma designs through a local plugin and then verify the sections they build in a headless browser, comparing layer-by-layer numbers and screenshots, plus responsive widths, motion and accessibility, until t | |
| webresearcher-mcp-server anihilator1/webresearcher-mcp-server Enables LLM hosts to run DuckDuckGo searches, scrape JavaScript-rendered and cookie-consent-gated pages with a hardened headless browser, and launch non-blocking same-domain BFS crawls whose progress and extracted content can be polled. | |
| medimageparse-mcp anihitk07/medimageparse-mcp Enables AI agents to segment 2D and 3D biomedical images using Microsoft's MedImageParse foundation models via free-text prompts, returning masks and statistics. Supports both local stdio MCP server and a hosted Azure API Management gateway | |
| sales-mcp-ui-poc anihitk07/sales-mcp-ui-poc Enables read-only sales dashboard and opportunity data access, plus Blob-backed quote preview and explicitly confirmed simulated quote saves through MCP tools with a bundled MCP Apps UI. | |
| xarticle-mcp aniirude/xarticle-mcp Enables saving X (Twitter) Articles as Obsidian-faithful Markdown files with locally downloaded images and videos. | |
| asbuilt anijani/asbuilt Asbuilt is an MCP server that verifies code assumptions against live backend infrastructure, checking that tables, schemas, and resources exist as expected before agents act. | |
| MCP Test Server anika536/mcp-test A comprehensive testing server for validating MCP scanner tools and implementations, providing diverse tools, resources, and prompts that exercise various aspects of the Model Context Protocol specification. | |
| finledger anikam13/finledger Enables an agent to query local financial ledgers for expenses, investments, and income, with tools for savings rate, accounts, sync, and reconciliation. | |
| component-mcp-server aniket-sharma27/component-mcp-server Exposes design system component documentation to LLM clients via MCP, allowing listing and retrieving component contexts from Markdown files with YAML frontmatter. | |
| SkillShare MCP Server aniket-think41/skillshare-mcp An MCP server that enables AI agents to interact with the SkillShare registry, including searching, reading, creating, and managing resources like skills, MCP configurations, and notes. | |
| linear-issue-mcp aniket2468/linear-issue-mcp MCP server for Linear that enables creating, searching, updating, and commenting on issues, as well as accessing issues, teams, and user data. Integrates with Claude Desktop and other MCP clients. | |
| Couchbase MCP Server for LLMs aniket310101/mcp-server-couchbase A Model Context Protocol server that enables large language models to interact directly with Couchbase databases through natural language, supporting operations like querying buckets, performing CRUD operations, and executing N1QL queries. | |
| Home Assistant MCP aniketbhondave/home-assistant-mcp Integrates Claude AI with Home Assistant to control smart home devices via natural language. | |
| MCP Server Starter aniketbiswas/mcp-server-starter A starter template for building MCP servers that enable AI assistants to interact with custom tools and data. | |
| Obsidian MCP Server aniketbiswas/obsidian-mcp Enables AI assistants to search, create, and manage notes in an Obsidian vault via 40+ local tools. | |
| Leave Manager aniketdonode/leavemanager Enables managing employee records, leave balances, and leave requests through MCP tools and resources, including submitting and approving leave, checking balances, and adding employees. | |
| Local Workspace Orchestrator aniketmehetre/local_workspace_orchestrator-mcp-server Enables Claude to interact with local workspace files through MCP, including listing files, summarizing CSV datasets, generating plots, executing Python scripts, and running allowlisted shell commands from a chat interface. | |
| mcp-server-crm aniketsingh12/mcp-server-crm An MCP server that gives LLMs tools to manage leads, track pipeline stages, log interactions, and generate reports for a freelancer client pipeline. | |
| jack-map aniketspecter/jack-codex-mcp Enables inspecting J.A.C.K. Map Editor documents and live selections, and previewing or applying limited native brush and entity edits through a stdio MCP client. | |
| Fortnox Doc MCP anikghosh256/fortnox-doc-mcp Provides comprehensive documentation for 377 Fortnox API endpoints and 81 resource categories directly from the official OpenAPI specification. It enables users to search, browse, and explore technical endpoint details and data schemas with | |
| Beziera aniklavida/beziera Enables a coding agent to create, read, write and link HTML-native artboards, capture screenshots of its own rendered output, and collect queued canvas feedback so it can see and refine UI designs in a loop. Provides tools such as screensho | |
| ContextPact aniklavida/contextpact Enables AI agents and tools to share durable, approved knowledge, current decisions, task ownership, and handoffs from a local-first workspace kept outside any single AI product. Markdown holds human-readable rules, goals, and narratives wh | |
| OhMyLife aniklavida/weallhatelife Enables an AI agent over MCP to read, file, and correct a plain-file, self-hosted personal life store — memories, people, money, body, papers, decisions and someday, alongside the usual tasks, projects, goals, habits and areas — recording e | |
| Jenkins MCP Server anil-appari007/jenkins-mcp-langchain Enables AI assistants to interact with Jenkins CI/CD systems through natural language, providing build management, job monitoring, log analysis, and debugging capabilities. | |
| Gemini Omni MCP Server anil-matcha/gemini-omni-1.1-flash-api Exposes video generation and editing tools to MCP-capable clients, enabling text-to-video, image-to-video, video editing, reusable voice and character profiles, and task status queries through natural language. | |
| Grok Imagine Image 2 MCP Server anil-matcha/grok-imagine-image-2-api Enables image generation and editing via the Grok Imagine Image 2.0 API, supporting text-to-image, image-to-image editing, multi-reference generation, local uploads, and asynchronous job polling. | |
| Seedance 2 MCP Server anil-matcha/seedance-2-mcp A focused MCP server for generating Seedance 2 videos via MuAPI. It provides tools for text-to-video, image-to-video, first-last-frame, and omni-reference generation, plus prediction polling and account balance. | |
| Seedance 2.5 MCP Server anil-matcha/seedance-2.5-mcp MCP server for generating Seedance 2.5 videos via MuAPI, enabling text-to-video, image-to-video, first/last frame, and omni reference workflows with 720p/480p resolution selection. | |
| Wan 3.0 Prime API MCP Server anil-matcha/wan-3.0-prime-api Enables MCP-capable clients to generate higher-fidelity videos via Wan 3.0 Prime, supporting text-to-video, image-to-video, multimodal reference-to-video, and async task status polling. | |
| cctx anil7948/cctx Enables Claude Code to reduce token usage by 70-90% using a local LLM for codebase indexing, tool output compression, and turn summarization. | |
| skillsmp-mcp-server anilcancakir/skillsmp-mcp-server This MCP server enables AI agents to search, discover, and install skills from the SkillsMP marketplace, with support for keyword and semantic search, skill content retrieval, and installation to various coding agents. | |
| MCP4Acumatica anilcopilot/mcp4acumaticaanil Enables Claude to access Acumatica ERP 2025 R2 through per-user OAuth and role-governed tools for lookups, discovery, documentation, and optional customer updates. Includes consent, sensitive-field redaction, rate limiting, pagination safeg | |
| Jokes MCP Server anilinfo2015/coding-ccp An MCP server that retrieves jokes from three different sources: Chuck Norris jokes, Dad jokes, and Yo Mama jokes. | |
| RAG MCP Gateway aniliou-85/rag-mcp A smart proxy that aggregates multiple downstream MCP servers and enables natural language search for tools, allowing clients like Claude Desktop to discover and use tools through semantic queries. | |
| riskrouter-recorder aniljangrabe-dev/riskrouter-recorder riskrouter-recorder | |
| MCP Server for CAP anilkeerthi/mcp-server Enables Claude to interact with a document processing backend, providing tools for listing, retrieving, uploading, and processing documents, as well as resources for pending documents and statistics. | |
| ai-armory anilkumarmeena/ai-armory Enables loading plain-Python tool sets for Google Workspace (Gmail, Calendar, Chat, Docs, Sheets, Slides, Drive), Mac control, and clock/time-zone lookups, then exposing them as MCP tools with confirmation gates on sends and deletes. Tool s | |
| GitMCP anillahane/git-mcp Transforms any GitHub repository into a documentation hub for AI assistants, enabling access to up-to-date documentation and code to eliminate hallucinations. Supports repository-specific and dynamic endpoints with smart search capabilities | |
| Apache Druid MCP Server anilpuram/apache-druid-mcp-server Enables querying and managing Apache Druid datasources through natural language, including SQL queries, datasource exploration, and cluster connectivity testing. | |
| WebsiteOps MCP Server anilreddykota/cp-mcp Bridges AI coding assistants with website codebases, local git repositories, and shared hosting via FTP/SFTP, enabling code discovery, file management, git operations, smart deployments, backups, and rollbacks. | |
| manufacturing-graphrag anils123/manufacturing-graphrag Enables manufacturing traceability queries and analysis through GraphRAG, supporting semantic search, graph traversal, natural language to Cypher, defect chain retrieval, requirement traceability, and product health dashboards. | |
| Country Explorer MCP Server anilsharmay/mcp-demo Enables users to create rich country profiles by searching for high-quality images through Unsplash API and gathering country information through web search. Generates beautiful markdown profiles with embedded images and photographer credit |
29,101–29,150 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.