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 |
|---|---|
| Unified Multi-Tenant MCP aljon-zb/mcp-zenbizsolutions Enables a single authenticated MCP endpoint to resolve users to the correct tenant, role, permissions, and tenant-specific backend integration, with support for shared, individual, and hybrid identity modes. | |
| peltierpro-mcp aljon-zb/peltierpro-mcp OAuth-enabled read-only MCP server for Odoo 19 ERP that allows Claude to search and retrieve CRM opportunities, sales orders, products, and inventory data via the Odoo JSON-2 API. | |
| tplink-omada-mcp aljopro/tplink-omada-mcp MCP server that lets AI assistants monitor and manage TP-Link Omada controllers. It provides analytics and read-only queries plus write operations such as rebooting devices, blocking clients, and changing network or firewall settings. | |
| Talk to Figma MCP alkaness/talk-to-figma-mcp Enables AI agents to read, inspect, and edit Figma files through a Model Context Protocol server with 107 tools, visual snapshots, fidelity tools, and optional REST API access. | |
| Alka Search MCP alkasima/alka-search-mcp Free web search, web-page reading as Markdown, and llms.txt documentation retrieval for MCP clients. Runs locally with Node.js over stdio using @alkasima/alka-search-mcp. Searches DuckDuckGo, Mojeek, and Brave; default providers require no | |
| MCPishCode alkindivv/mcpishcode A self-hosted MCP server that brings a Codex-style coding workflow to ChatGPT, allowing it to read, edit, search, and run code in your local projects. | |
| LLM Council MCP alkrcaaa/llm-council-mcp Enables AI coding agents to consult a multi-model deliberation council before irreversible, high-stakes decisions, returning structured architectural decision records with consensus and dissenting risks. | |
| local-model alkrcaaa/local-llm-mcp Enables MCP clients like Claude Code to delegate coding tasks to a local model through a configurable coding-agent CLI backed by any OpenAI-compatible endpoint, with tools for health checks, task execution, and context-aware file modificati | |
| comfyui alksef/comfyui-aiassistant Enables local AI assistants to read the current node selection in ComfyUI and, on request, insert text into text-like widgets of the selected node. | |
| vault-vector all-zen/vault-vector Enables semantic and full-text search over markdown notes, with tools to create, edit, move, and delete notes, all through MCP. Runs entirely locally using Ollama for embeddings and SQLite for storage, working with Obsidian or standalone. | |
| omnisearch-mcp all3yp/omnisearch-mcp Enables LLM agents to search academic literature across multiple sources (IEEE, arXiv, ACM, Semantic Scholar, CORE, Scite, Consensus) and index/search local PDFs. | |
| MCPGame allaboutai-yt/mcpgame A multiplayer first-person 3D virtual house environment with interactive elements including a TV with image display system and computer terminal for accessing MCP systems. | |
| CyberSec MCP allalg/cybersec-mcp Enables AI agents to run cybersecurity reconnaissance and analysis tools through controlled containerized sandboxes, with input validation, policy allowlists, timeouts, structured JSON output, and immutable audit logging. | |
| n8n MCP Server allanbchancery/n8n-mcp-server MCP server for managing n8n workflows and executions. Enables listing, activating, deactivating, and executing workflows, as well as monitoring executions and instance health. | |
| Azure DevOps MCP Server allanbrunobr/mcp-azure-devops Enables management of Azure DevOps work items including Epics, Features, User Stories, Tasks, and Bugs through natural language. Supports CRUD operations, WIQL queries, work item relationships, and retrieval of project metadata such as iter | |
| NORA Data MCP Server allanhale/nora-mcp-server Enables read-only access to NORA dashboard data from Upstash Redis, covering OKRs, initiatives, KPIs, and financial summaries. It allows users to query and analyze business performance metrics and organizational alignment through standardiz | |
| Dial In allankirsten/gt-pilot Enables users to build and tweak BOSS GT-1 guitar tones and patches through plain-language conversation, with Claude writing amp, drive, and effect settings over USB. It can also listen to the pedal's audio, adjust levels and noise suppress | |
| InventorySystem MCP Server allansjoseph/inventorysystem_mcp_server A Python MCP server that connects to an Inventory Management System, providing 15 tools for CRUD operations on users, inventory items, and bills. | |
| foundry-cli allardhoeve/foundry-cli MCP server for managing Foundry VTT journal content (entries, categories, pages) and listing actors, enabling AI-assisted world-building via natural language commands. | |
| MQScript MCP Server allegiant/mqscript_mcp Enables AI applications to generate and execute MQScript mobile automation scripts for controlling mobile devices. Supports touch operations, UI creation, color detection, file operations, and system control functions. | |
| Prefect MCP Server allen-munsch/mcp-prefect A Model Context Protocol server that allows AI assistants to interact with Prefect's workflow automation platform through natural language, enabling users to manage flows, deployments, tasks, and other Prefect resources via conversational c | |
| DailyBot MCP allen-n/dailybot-mcp Enables Littlebird to read and submit DailyBot check-ins through the DailyBot CLI. | |
| Corvus allen-saji/corvus Solana DeFi Intelligence MCP server enabling natural language queries for wallet analytics, DeFi positions, protocol metrics, and token prices. | |
| fulfillment-review-mcp allen-saji/fulfillment-review-mcp Streamable HTTP MCP server for investigating partial-fulfillment holds and preparing complete human-review cases. It provides read-only tools to preview source-supported fulfillment options with delivery-date and shipping-cost effects, and | |
| inventor-mcp allen2123231/inventor-mcp Enables natural-language control of Autodesk Inventor to create parametric parts, sketches, holes, and sheet-metal features, and to inspect, save, or export models. | |
| Vibe Coder MCP Server allen271/vibe-coder-mcp Enables AI assistants to research topics, map and analyze codebases, curate context, and generate PRDs, user stories, task lists, and fullstack starter projects through natural language commands or an interactive CLI/REPL. It also provides | |
| Frappe MCP allen81514/mcp Enables Frappe Framework applications to act as Streamable HTTP MCP servers by exposing decorated Python functions as callable tools for LLMs. | |
| freellmpool allen84226/freellmpool Exposes a pooled set of free LLM chat routes behind a single OpenAI-compatible endpoint, so agents and tools can query many providers with automatic failover, latency-aware routing, and local usage tracking. It also surfaces capacity and pr | |
| MCP System Info Server allenbijo/mcp-sysinfo A lightweight server that provides real-time system information including CPU, memory, disk, and GPU statistics for monitoring and diagnostic purposes. | |
| claude-memory allenc84/sapience A persistent semantic memory system for Claude Code, using vector search and a judgment ledger to surface prior decisions and calibrate predictions. | |
| docsearch allencomm/mcp-docsearch MCP server that enables searching and reading binary document files (PDF, DOCX, PPTX, XLSX, ODT, ODS, ODP, RTF, EPUB) using regex patterns and retrieving content by sections. | |
| Solr MCP allenday/solr-mcp A Python server that enables AI assistants to perform hybrid search queries against Apache Solr indexes through the Model Context Protocol, combining keyword precision with vector-based semantic understanding. | |
| xiaomi-device-control alleneee/xiaomi-device-control MCP server for controlling Xiaomi/Mi Home smart devices via natural language, supporting device listing, property read/write, action calls, and camera snapshots. | |
| Tilt MCP Server alleneubank/tilt-mcp Enables AI assistants to interact with Tilt development workflows, including monitoring resource status, managing resources (enable/disable/trigger), accessing logs, and configuring Tiltfile arguments through natural language. | |
| Sonar-MCP allengeorge08/sonar-mcp Enables natural-language interaction with Solana blockchain data—including network status, wallet balances, transactions, and token supply—via the Helius RPC API in MCP clients like Cursor. | |
| repo-map MCP server allengox1994-creator/cursor-token-saver Provides a unified context layer for Cursor's agent with lossless token savings and verifiable memory, enabling efficient code exploration and cross-session continuity. | |
| allenhoem-mcp allenhoem/allenhoem-mcp Remote MCP server exposing tools to explore Allen Hoem's professional record, including patents, media, and contact requests. | |
| AIND Metadata MCP Server allenneuraldynamics/aind-metadata-mcp Provides access to Allen Institute for Neural Dynamics (AIND) metadata and data assets through MongoDB queries, aggregation pipelines, NWB file exploration, and AI-powered data summaries. | |
| Home Assistant MCP allenporter/mcp-server-home-assistant Expose all Home Assistant voice intents through a Model Context Protocol Server allowing home control. | |
| nd-quirks allenrobel/bug-tracker-mcp An MCP Server that leverages notes written in Markdown, tailored for developing Cisco Nexus Dashboard applications using the REST API. | |
| davinci-resolve-mcp allensandiego/davinci-resolve-mcp Enables external AI agents and CLI tools to control DaVinci Resolve Free and Studio through a local file-polling Lua bridge, exposing project, timeline, media, marker, and render operations as typed MCP tools. | |
| postgres-mcp-server allensandiego/postgres-mcp-server MCP server for PostgreSQL, providing schema discovery, catalog introspection, read-only querying, and optional safe write operations to AI assistants. | |
| Codebase RAG MCP Server allentcm/mcp-codebase-rag Enables semantic search and retrieval of code files using embeddings stored in PostgreSQL. Supports intelligent codebase exploration through natural language queries, file listing, and content retrieval. | |
| dynamodb-mcp-server allentgt/dynamodb-mcp-server An MCP server that gives LLM agents full access to Amazon DynamoDB, supporting table management, querying, scanning, and item CRUD operations. | |
| OpenSpec MCP allenvissong-source/openspec-mcp Enables AI coding assistants to drive spec-driven development through slash-command workflows for planning, exploring, implementing, updating, and finalizing changes, with local daemon and project registry support. | |
| Health Records allenyllee/health-records Enables authenticated owners to capture, review, correct, and export bodyweight and strength-training data through a ChatGPT interface, including bounded multi-image/multi-session batch review, typed metrics with explicit provenance, pendin | |
| munich-mensa-mcp allesklardy/munich-mensa-mcp Remote MCP Server for listing and getting the menus of the official mensas in munich | |
| Swagger MCP alleyway-boop/swagger-mcp High-performance server for exploring Swagger/OpenAPI specifications with dynamic session management, lightning-fast endpoint search, and efficient caching. Enables AI assistants to discover, search, and generate code from REST APIs. | |
| MCPControl allezsung/mcp-control Windows control server for the Model Context Protocol, enabling programmatic control of mouse, keyboard, window management, screen capture, and clipboard operations to allow AI models to interact with and automate Windows desktops. | |
| agr_postgres_mcp alliance-genome/agr_postgres_mcp Enables interaction with PostgreSQL databases via psql, supporting SQL queries, table management, and database insights. |
26,701–26,750 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.