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 |
|---|---|
| expo-docs ception/expo-local-docs-mcp Enables fast, offline search and retrieval of Expo documentation from local .mdx files, with tools for searching, getting content, listing sections, API references, and quick start guides. | |
| cerase-media MCP cerase-ai/cerase-media-mcp Provides multimodal understanding tools including OCR, image description, audio transcription, UI screenshot analysis, and screenshot comparison via async tools on a multimodal endpoint. | |
| cerase-search MCP cerase-ai/cerase-search-mcp Enables web search and deep multi-source research for Cerase agents via LiteLLM proxy, with billing attribution per agent. | |
| Cerase Tasks MCP cerase-ai/cerase-tasks-mcp A tasks and projects board MCP server for agents, providing create, list, and status update tools with agent-scoped access via control-plane proxy. | |
| Ceratops-Blender-MCP ceratops-code/ceratops-blender-kit Enables local, versioned Blender character and shot production through fixed immutable stage transitions — reference import, blockout, mesh, retopology, look development, groom, rigging, animation, and rendering — with review gates, approva | |
| InterAgentMail cerberusgamelabs/cgl-interagentmail Enables durable message passing between Codex project agents with MCP tools and automatic wake-up delivery, storing messages as JSON on disk. | |
| Okta MCP Server cerberustrainer/okta-mcp-server Enables natural language management of Okta organizations, allowing users to perform administrative tasks such as user management, group operations, and application monitoring through AI agents. | |
| Tshark MCP Server cerby0n/tshark-mcp Analyzes pcap files using tshark to detect network attacks and security threats. | |
| gdb-cli cerdore/gdb-cli A GDB debugging tool designed for AI Agents (Claude Code, etc.) | |
| Cerebral Valley MCP Server cerebralvalley/cv-mcp Enables discovery and submission of AI community events, hackathons, and meetups through search by location, type, and date range, plus newsletter subscription capabilities. | |
| Cerebras Code MCP Server cerebras/cerebras-code-mcp This MCP server is designed for planning with Claude Code, Cline, or Cursor and making changes with Cerebras to maximize speed and intelligence while avoiding API limits. It uses the Qwen 3 Coder model for high-quality code generation and c | |
| cerebrochain-mcp-server cerebrochain/cerebrochain-mcp-server The first logistics/WMS MCP server for AI agents. Rate shopping, inventory management, order tracking, fleet logistics, AI-powered route optimization, demand forecasting, and supply chain analytics. 18 tools across 3 tiers. | |
| CRM MCP Server cerennly/claudemcp_server Enables querying and managing a CRM database through natural language conversations with Claude Desktop. | |
| collectible-vault cereos20/collectible-vault Enables AI assistants to manage a universal collectibles vault with natural language, supporting item lookup, addition, valuation, and portfolio summary via FastMCP. | |
| Cerevox MCP Server cerevoxai/cerevox-mcp-server Model Context Protocol server for Cerevox AI that exposes document parsing (Lexa), RAG and semantic search (Hippo), and account management APIs, enabling AI agents to parse documents, search and query document collections with RAG, and mana | |
| GitHub Workflow Fix-and-Retry MCP Server cerios-techlab/github-workflow-opencode-fix-and-retry-mcp-server Monitor failing GitHub Actions workflows, auto-fix them with OpenCode, and retry the run — driven by a workflow_run webhook, coordinated through an MCP server. | |
| Quality Transformation Coach Assistent MCP server cerios-techlab/quality-transformation-coach-assistent Helps with cicd work, failed tests in automation and also tmmi/iso scans en reports. | |
| Test assistent MCP server cerios-techlab/test-assistent-mcp-server MCP server voor het maken van testcases. Maar ook voor het inzetten van test technieken en heuristieken. | |
| ARGUS cerisonautomation/argus-mcp Enables AI agents to perform comprehensive, zero-infrastructure codebase analysis through 24 MCP tools, covering security, quality, architecture, type safety, git history, and dead code detection with high precision and local privacy. | |
| Unified Apps Script MCP cerisonautomation/google-workspace-mcp Enables comprehensive Google Apps Script project lifecycle management (creation, content, versions, deployments, execution, metrics) and controlled access to Google Workspace APIs (Sheets, Docs, Drive, Gmail, Calendar, Tasks, Forms, Slides) | |
| Apex Log MCP Server certinia/debug-log-analyzer-mcp An MCP server that gives AI assistants tools to analyze Salesforce Apex debug logs for performance bottlenecks, slow methods, and governor limit usage. | |
| Se7e MCP Server cesar-carlos/plug_mcp MCP server that enables an AI to query the Se7e ERP via the plug-server API, supporting authentication and catalog reconciliation. | |
| scplus-mcp cesar514/scplus-mcp A local code-intelligence MCP server that provides structural, exact-query, related-search, and research capabilities from a validated repo-local index, enabling agents to perform deterministic lookups, semantic search, and code analysis. | |
| mr-model MCP Server cesario121125/mr-model-mcp Standalone Model Context Protocol (MCP) server for the mr-model platform, offering 5 tools to query video lists, comments, OCR transcripts, search, and blogger opinions via a web API. | |
| Codex LSP Bridge cesarpetrescu/lsp-mcp Exposes Language Server Protocol (LSP) features as MCP tools, enabling IDE-grade semantic navigation including go-to-definition, find references, hover info, and symbols across multiple programming languages (Python, Rust, C/C++, TypeScript | |
| agente-traduccion-mcp cesarreynab/agente-traduccion-mcp MCP server for translation and localization workflows. It exposes tools for glossary lookup, translation memory reuse, segment alignment, and demo multicloud translation. | |
| Students Architecture MCP Server cesarrl23/mcp Enables CRUD operations on student records via REST API and MCP interface, with configurable JSON or SQLite persistence. | |
| albion-market-ia cesarscf/albion-market-ia Enables querying Albion Online market data to find profitable refining opportunities by analyzing prices, recipes, resource return rates, and taxes. Provides deterministic profit calculations and explains trade-offs through natural language | |
| Alpaca MCP Server cesarvarela/alpaca-mcp MCP server that exposes Alpaca Market Data & Broker API as tools, enabling access to financial data like stock bars, assets, market days, and news through the Message Control Protocol. | |
| PostgreSQL MCP Server cesarvarela/postgres-mcp A TypeScript-based Model Context Protocol server that enables AI assistants to perform secure database operations on PostgreSQL databases through structured tool interfaces. | |
| caton mcp cesarzea/caton-ai Serves a local financial ledger read-only over the Model Context Protocol, enabling AI assistants to query sync status, accounts, balances, and spending without bank access. Responses use exact decimal amounts and indicate whether figures a | |
| Git Prompts MCP Server ceshine/git-prompts-mcp-server A Model Context Protocol server that generates prompts based on Git repository content, including a command to generate PR descriptions from diffs. | |
| openapi-mcp ceski23/openapi-mcp MCP server for loading and exploring OpenAPI/Swagger specifications, enabling AI assistants to dynamically browse API contracts by loading specs, searching endpoints, inspecting schemas, and retrieving operations. | |
| i3X-MCP-Server cesmii/i3x-mcp-server Bridges Claude (or any MCP client) to manufacturing data via the i3X standard, enabling natural language queries about equipment status, hierarchy, and historical trends. | |
| OpenAIRE MCP Server cessda/cessda.ai.mcp.openaire Enables AI assistants to explore the OpenAIRE Research Graph and ScholExplorer citation index, discovering citation relationships and retrieving metadata for publications, datasets, and software. | |
| @cessio/agent-mcp-server cessio-cc/cessio-agent-mcp-server A local, self-custody MCP server that lets an AI agent trade the Cessio RFQ desk as both maker and taker, holding its own key and signing trades with operator-set limits. | |
| FlowNoter MCP Server cestcavision/flownoter Enables saving AI conversation histories as clean, organized markdown notes with automatic filtering of thinking processes and tool execution details, timestamping, and customizable conversation turn limits. | |
| Progresso MCP cetijunior/progresso-mcp Enables MCP clients to interact with a live Progresso workspace for board, CRM, projects, and time tracking via Supabase. | |
| Docker MCP Server cevatkerim/docker-mcp Enables LLMs to safely execute code in isolated Docker containers with resource limits and security controls, supporting session management and automatic dependency installation. | |
| Ceveto MCP Server ceveto/mcp-server Enables AI agents to interact with the Ceveto business management API through MCP, with permission-filtered tools and secure Ed25519 authentication. | |
| find-images-mcp-bridge ceveyne/find-images-mcp-bridge Enables LM Studio Bionic to perform multimodal image search and tagging by bridging to a local Find Images MCP server, including preview download and scratchpad registration for further editing or processing. | |
| Piriod MCP Server cevidallara/piriod-mcp Connects Claude with Piriod.com API to manage invoicing and payments, enabling listing/creating invoices, searching customers, and viewing payments through natural language. | |
| Bambu Printer MCP ceweldy/bambu-printer-mcp Manages, monitors, slices for, and controls multiple Bambu Lab 3D printers with a privacy-focused multi-printer registry and fleet status. | |
| bitwarden-agent-vault-mcp ceweldy/bitwarden-agent-vault-mcp An MCP server for using Bitwarden Secrets Manager as durable credential storage for agent workflows, enabling secure secret storage, retrieval, and injection into trusted executables. | |
| BMAD-MCP cexll/bmad-mcp-server Orchestrates complete agile development workflows from product requirements to QA testing through role-based stages (PO → Architect → SM → Dev → Review → QA). Manages workflow state, generates role-specific prompts, and saves artifacts whil | |
| Code Mode MCP Server cexll/code-mode-mcp Executes TypeScript code in a secure sandbox with IPC-bridged access to MCP tools like filesystem operations and network requests. | |
| Codex MCP Server cexll/codex-mcp-server Connects AI assistants like Claude to the Codex CLI for code analysis, editing, and execution. Supports file references with @ syntax, sandboxed code execution with approval workflows, and structured code changes for automated refactoring a | |
| @cexyio/mcp cexyio/cexy-mcp Enables MCP clients such as Claude to read CEXY.io market data and, with an API key, account balances, orders, trades, deposits, withdrawals, and ledger history. Trading can be opted in with explicitly enabled tools and guardrails, while wi | |
| Claude Merkezi MCP Server ceydrew/claude-merkezi Enables Claude Code to use encrypted FTP/FTPS/SFTP/SSH credentials without exposing passwords, so it can list and download remote files, upload only changed files, run SSH commands with production approval, and read or update a project task | |
| Synology MCP Server ceyeborg/synology-mcp-server Enables AI assistants such as Claude, Cursor, Continue, and Codeium to manage files and downloads on Synology NAS devices through secure authenticated sessions. Supports Docker, PyPI, stdio, Streamable HTTP, and WebSocket deployment modes. |
37,651–37,700 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.