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 |
|---|---|
| MS SQL MCP Server akashcf/mcpdemo A bridge that allows AI assistants like Claude to directly query and explore Microsoft SQL Server databases without requiring coding experience. | |
| emr-mcp-server akashdeep01/emr-mcp-server Provides intelligent guidance for EMR cluster management, configuration recommendations, and monitoring capabilities | |
| akapal-mcp-portfolio akashh94/akapal-mcp-portfolio MCP server exposing portfolio and brokerage data through SSE transport, with tools for account summaries, holdings, quotes, market data, and order previews, backed by mock data with live quote fallback. | |
| bangumi-mcp akashic-plugins/bangumi-mcp MCP server for Bangumi that queries collections, marks anime as watching/watched, and updates per-episode progress via official API, with secure token handling. | |
| MCP Smart Scheduler & Todo App akashkumar-behera/mcp-testing-todo Enables scheduling and todo management via MCP, allowing users to add reminders, view tasks, and mark completion through natural language. | |
| SonarQube MCP akashlomas/sonarqubemcp A lightweight MCP for SonarQube reports | |
| MCP Data Catalog Server akashmanjini/mcp_data_catalog Enables composable search and filtering over an enterprise data catalog, with tools for lineage, sample data, profiling, history, quality rules, and AI-driven classification. | |
| codexray akashmark8-cloud/codexray Enables AI coding agents to quickly search and navigate large codebases by indexing symbols and references, offering tools for fuzzy symbol lookup, file outlining, and reference discovery without a language server. | |
| bambu-mcp akashnaren/bambu-mcp Enables LAN-based monitoring and control of Bambu Lab P2S/P1S printers, including confirm-gated print, pause, resume, stop, file upload, and slicing workflows. | |
| kalshi-readonly akashnaren/kalshi-mcp Enables read-only access to Kalshi Trade API v2 for exchange status, markets, cash, positions, fills, and resting orders, with optional mutating order tools gated behind a safe mode and explicit confirmation. | |
| azure-boards-mcp-testcases akashnaykude/azure-boards-mcp-testcases This MCP server lets GitHub Copilot fetch Azure Boards work items by URL or ID and generate QA test cases from the ticket content. | |
| mcp-second-opinion akashpersetti/mcp-second-opinion Lets MCP-aware agents consult rival LLMs mid-conversation, sending questions to a specific provider or fanning out to OpenAI, Gemini, Anthropic, and xAI/Grok in parallel for second opinions. | |
| nucleo-mcp akashrajpurohit/nucleo-mcp Enables AI assistants to search, retrieve, and save Nucleo icons from the user's local library directly into projects. | |
| ServiceNow Incident Copilot akashreddi/servicenow-incident-copilot Enables conversational triage of ServiceNow incidents via Claude Desktop, automatically classifying and routing them based on company knowledge. | |
| FinSight akashsadamwar/finsight MCP server for payments analytics, enabling natural language queries on transaction data, merchant summaries, and chargeback anomaly detection with grounded, auditable answers. | |
| advocatehub-mcp akashtrilogy/advocatehub-influitive-mcp MCP server for Influitive AdvocateHub that provides 15 tools across members, groups, challenges, events, rewards, and approvals, enabling read and write operations with confirm gates and audit logging. | |
| Jira MCP Server akashyap3c/jira-mcp Manages Atlassian Jira Cloud projects, issues, sprints, boards, worklogs, comments, and workflow transitions from MCP-compatible clients. | |
| blog-mcp akatjd/blog-mcp 자동으로 네이버 블로그 글을 생성하고 발행하는 MCP 서버로, 사진과 간단한 정보를 입력하면 SEO 최적화된 초안을 작성하고 스타일 학습을 통해 개인화된 글을 쓸 수 있습니다. | |
| DnD WebMCP akatsuki-sayo/dnd-webmcp Enables a minimal multiplayer text TRPG with DM, human, and agent roles, shared room event logs, staged turns, and server-side d20 checks. | |
| Akave MCP Server akave-ai/akave-mcp Enables AI models to interact with Akave's S3-compatible storage by providing tools for managing storage buckets and objects through standardized Model Context Protocol (MCP). | |
| DiffMind akay1121/diffmind An MCP server for Claude Code that forces AI agents to document every change with rationale, rejected alternatives, and trade-offs, ensuring code maintainability and developer ownership during AI-assisted development. | |
| Workers MCP Demo akazwz/workers-mcp-demo A demonstration project that uses Cloudflare Workers MCP to create custom AI tools that can be integrated with Claude, Cursor, and other AI assistants supporting the Model Context Protocol. | |
| sourcegraph-mcp akbad/sourcegraph-mcp MCP server exposing Sourcegraph's AI-enhanced code search capabilities to coding agents, enabling advanced code search, repository discovery, and content fetching. | |
| Codito akbaramd/coditomcp Enables ChatGPT to work with explicitly registered projects on a Windows device through a secure, self-hosted bridge. | |
| AgentRecall akbardizaji/agentrecall A local-first memory for AI coding agents. AgentRecall turns the feedback and failures you run into while coding into reusable rules, then serves the right ones back — on the command line or directly to Claude Code over MCP. Everything stay | |
| Memory MCP akbarikishan/memory_mcp An advanced cognitive memory agent for AI chatbots that provides long-term, autonomous memory using a four-agent system for monitoring, extraction, reconciliation, and consolidation. | |
| Local Task Manager MCP Server akbarshaik2243/task-manager-mcp A task manager MCP server that enables creating, reading, updating, and deleting tasks persisted in a local JSON file. | |
| Trello Task Manager MCP Server akbarshaik2243/trello-task-manager-mcp Enables AI applications to manage tasks on a real Trello board by exposing four MCP tools for adding, listing, completing, and deleting tasks. | |
| pc-express-mcp akbaruddink/pcexpress-mcp Enables an LLM to search grocery products, compare nutrition data, manage a PC Express cart, check loyalty points and order history, and generate a checkout handoff link across Loblaws banners such as Real Canadian Superstore, No Frills, an | |
| OpenProject MCP Server akbted/project-nexus An MCP server that enables AI assistants to interact with OpenProject, listing projects and work packages and managing resources through natural language. | |
| Solana MCP Server akc2267/solana-mcp-server A server that provides simple RPC endpoints for common Solana blockchain operations, allowing users to check balances, get account information, and transfer SOL between accounts. | |
| vps-ops-mcp akdag94/vps-ops-mcp A safe, structured MCP server that lets AI inspect and operate a VPS through typed, allowlisted tools for nginx, PM2, SSL, UFW, fail2ban, with read-only defaults and opt-in mutations. | |
| Weather MCP Server akdrione/weather-mcp-server Provides weather data from OpenWeatherMap API through MCP tools and a REST API with OpenAPI support. Enables LLM agents to retrieve current weather, forecasts, and temperature ranges by city or coordinates. | |
| Google AI Studio MCP Server akeelbuilds/google-ai-studio-mcp Exposes Google AI Studio models (Gemini, Imagen, Veo) as MCP tools for text generation, image generation, and video generation, integrating with code editors and LLM clients. | |
| Flight + Stay Search MCP akekaratp/flights-mcp-ts Enables searching for flights (one-way, round-trip, multi-city) and hotels using the Duffel API, with support for filtering by cabin class, passengers, dates, and viewing accommodation reviews. | |
| Airbnb MCP Server akekaratp/mcp-server-airbnb Enables searching for Airbnb listings and retrieving detailed property information including pricing, amenities, and host details without requiring an API key. | |
| MySkillDB Job Categories MCP akeledath-gif/msdb-mcp MCP server that pushes job categories into a college org via the MySkillDB API, supporting list, get, upsert, batch push, and delete operations. | |
| SentinelMCP akemi1tr/ai-security-mcp Analyzes inputs and outputs in real-time to protect against prompt injections, data leaks, secrets exposure, and phishing URLs. | |
| Chat with Blender akerdogmus/chat-with-blender Enables AI assistants to control Blender 3D modeling and rendering through natural language commands via the Model Context Protocol. | |
| mcp-business-bot akes102/mcp-business-bot Enables querying company knowledge base using RAG, providing accurate answers from internal documents via MCP. | |
| kubera-mcp akeslo/kubera-mcp MCP server for Kubera that lets LLMs read and update your portfolio data. | |
| akeyless-agentcore-rta akeyless-community/bedrock-agentcore-akeyless-rta Enables AWS Bedrock AgentCore agents to perform secretless database queries and cloud service actions through an Akeyless Gateway, with credentials kept off the agent and tool responses limited to paths, metadata, and results. Provides MCP | |
| Akeyless MCP Interop (OpenID AIIM) akeyless-community/mcp-interop Implements an MCP server with OAuth 2.1 Protected Resource Metadata, enabling token-based authentication for MCP tools like ping. | |
| AREL akgithub2028/agent-reliability-and-evaluation-lab A production-oriented reliability, benchmarking, and evaluation system that layers multi-version protocol negotiation, adaptive streaming, connection pooling, and resilience onto an MCP agent runtime. | |
| codecontext akgithub2028/codecontext-os Enables Claude Code and AI coding agents to retrieve compact, task-shaped code evidence bundles via MCP, combining AST-aware retrieval, hybrid BM25+FAISS search, call-graph traversal, reranking, and token-budgeted context assembly. | |
| Playwright MCP Server akhatorking1/accessibility-playwright-mcp A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots, providing browser automation capabilities without requiring screenshots or visually tuned models. | |
| Apidog Sync MCP Server akhelij/apidog-sync-mcp-server MCP server for reading, writing, and organizing API documentation in Apidog. | |
| IDAPro-MCP Server akhil-chaturvedi/idapro-mcp Exposes IDA Pro's analysis capabilities through the Model Context Protocol (MCP). Provides 247 tools for reverse engineering and binary analysis. | |
| KiCad MCP Server akhil-chaturvedi/kicad-eda-mcp An MCP server for controlling KiCad EDA software, enabling schematics, PCB design, manufacturing outputs, design checks, and library management through any MCP-compatible AI assistant. | |
| bonk-mcp akhil0g/bonk-mcp-e Enables token launching and trading on the Solana blockchain via the LetsBonk launchpad. |
25,501–25,550 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.