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 |
|---|---|
| decroche-mcp casius999/decroche-mcp Deterministic MCP server for job-landing pipeline that parses CVs into validated JSON Resume, detects sections, scores parse confidence, and exposes FR/US market profiles to help beat ATS and LLM screeners honestly. | |
| fine-tuning-os casius999/fine-tuning-os A zero-data MCP server for LLM fine-tuning, providing 64 tools across 10 dimensions to prepare, build, train, evaluate, secure, package, and deliver fine-tuned models without ever accessing client data. | |
| Quantum ADS MCP casius999/quantum-ads-mcp A sovereign Google marketing-agency control plane over the Model Context Protocol, enabling an AI agent to safely operate 20 Google marketing products with read and guarded write capabilities. | |
| CaskMCP caskmcp/caskmcp Turns any web API into a governed, agent-ready MCP server with lockfile-based approval, fail-closed enforcement, and full audit trail. | |
| cas-parser-node-mcp casparser/cas-parser-node Enables AI assistants to interact with the Cas Parser REST API for parsing CAS statements and managing credits. | |
| Unified Ads MCP Server caspercrause/ads-mcp-server A FastMCP-powered server integrating Google Ads and Facebook Ads APIs with automatic OAuth 2.0 authentication, enabling GAQL queries, keyword research, campaign management, and performance analytics. | |
| DV360 MCP Server caspercrause/dv360-ads-mcp-server A Model Context Protocol (MCP) server for Display & Video 360 that provides entity management and performance reporting capabilities. | |
| abrp-mcp casperjuel/abrp-mcp An unofficial MCP server for A Better Routeplanner that enables EV route planning with charging stops, charger search, vehicle models, and live telemetry using the ABRP API. | |
| aula-mcp casperjuel/aula-mcp This server enables MCP clients (LLMs) to access data from the Danish school platform Aula, such as messages, schedules, and child profiles, by authenticating via MitID and running locally. | |
| @cassette.diy/mcp cassette-music-management-tool/cassette-mcp MCP server for managing Cassette music releases and Creator clips through AI assistants via personal access tokens. | |
| Aircall MCP Server cassiaresearch/aircall-mcp-server MCP server providing 83 tools to manage Aircall calls, transcriptions, AI insights, contacts, SMS, users, teams, and more via the Aircall Public API, compatible with Claude Desktop and other MCP clients. | |
| deepseek-mcp-bridge cassiatw1g/modelbridge Exposes DeepSeek as a callable MCP tool, enabling ChatGPT connectors and other MCP clients to invoke it for cross-vendor independent review tasks. | |
| Workflow to MCP cassiomc1/workflow-to-mcp Enables users to record, review, verify, and expose permitted browser workflows as callable MCP tools with typed inputs, isolated Chromium verification, and approval-gated writes. | |
| hermes-oh-my-pi-mcp cassiopeiaym/hermes-oh-my-pi-mcp A tiny Hermes-friendly bridge that exposes oh-my-pi's CLI as MCP tools (prompt and doctor) for code generation and environment verification. | |
| ChemMCP cassiusoat/chemmcp_lite A chemistry computation platform providing 19 professional tools for molecular structure processing, including SMILES conversions, molecular calculations, functional group identification, visualization, and AI-powered molecule generation an | |
| Fireflies MCP Server cassler/fireflies-mcp-server Enables access to Fireflies.ai meeting transcripts with capabilities to retrieve, search, filter, and generate AI-powered summaries of meeting content through the Fireflies API. | |
| notebooklm-mcp cast-ai-tech/cast-notebooklm MCP server that provides ~39 tools to interact with Google NotebookLM's internal API, enabling notebook management, source addition, chat queries, and Studio artifact generation through stdio, HTTP, and SSE transports. | |
| ABCM MCP Server castaliaacademy/abcm Enables interaction with Agent Build Context Manager workspaces through MCP, providing safe file operations, scoped discovery, and an authenticated REST file API for managing project context. | |
| imscc-mcp castaliainstitute/imscc_mcp An MCP server that enables the creation of Canvas Common Cartridge (.imscc) packages from structured course data using the canvas_cc Ruby gem. It allows users to programmatically build course content including modules, assignments, and rubr | |
| gimmick-vision-mcp castellotti/gimmick-vision-mcp Bridges Claude Code to local OpenAI-compatible vision models, enabling image analysis, comparison, and OCR via three tools. | |
| Ruminer Browser Agent casterkay/ruminer-browser-agent Syncs AI conversations from multiple platforms to local Markdown files for your second brain, and provides browser automation tools via MCP for agentic workflows. | |
| MS 365-21V MCP Server castillo1379/ms-365-21v-mcp-server Lets MCP-capable AI clients act as the signed-in user against 21Vianet-operated Microsoft 365 through the China Microsoft Graph endpoints, reading mail, analyzing calendar conflicts, and searching OneDrive and SharePoint files. Access stays | |
| mercadopleis castiquark/mercadopleis AI agents hire people for work they can't finish alone (data curation, red-teaming, scraping, transcription), paid via non-custodial USDC escrow on Base. Returns unsigned transactions and holds no keys. | |
| autodevice-mcp castleeason/autodevice-mcp A local MCP server for repeatable abnormal API-response testing on Android, iOS, and HarmonyOS devices, combining device automation, mitmproxy response mutation, evidence capture, and cross-platform reporting. | |
| mcp-money castletaste/money-mcp MCP server for personal finance tracking, enabling expense/income recording, budget management, and financial summaries through 16 tools. | |
| Everything MCP Server castleyu/everything-mcp-server Enables AI assistants to search local files and folders via the Everything search engine, with support for advanced queries, file metadata, text previews, and service status. | |
| Platform-MCP castlezjc/platform-mcp An internal MCP server providing Database (SQL execution) and Server (Linux SSH/SFTP) skills with 11 tools, enabling remote execution, risk control, and full audit via Claude Code or other clients. | |
| muster castor-o7/muster Enables Claude Code sessions to discover and exchange live messages on one machine or across paired machines, waking idle sessions via hooks without dangerous flags, with durable message storage and secure TLS pairing. | |
| dots-kanban castor6/dots-kanban Enables a personal task board to be shared across a web view, MCP tools, and an MCP App UI, with task, project, dependency, comment, archive, search, filter, and drag/drop management. It persists data in a Sites-hosted D1 database with owne | |
| Siigo MCP Server castrillon89/mcpsiigo Enables interaction with the Siigo API to manage products, customers, and invoices with enterprise-grade security features like RBAC and audit logging. It supports financial reporting operations and secure data handling through the Model Co | |
| mcp-stockpile casualbrooks/mcp-stockpile The autonomous commerce platform where AI agents and human curators operate real e-commerce storefronts, curate scouted physical items, appraise collectibles, manage orders, and route customer inquiries. | |
| VoltageInputMcp casualkre/voltage-input-mcp Enables a frontier model to drive a desktop at input speed by delegating rapid sequences of keyboard and mouse actions to small local models running via a state-machine playbook, without per-action round-trips. | |
| schrift casvanleijden/schrift Enables AI assistants to read, search, create, edit, move, and version Markdown notes, folders, tags, tasks, and attachments. It also supports generating meeting reports and bulk-importing notes through authenticated MCP connections. | |
| Agent Exchange cat-people-82/agent_exchange_mcp An MCP server that lets an AI client send messages to and hold multi-turn conversations with other AI models such as Claude, GPT, and Grok, switching providers per call and persisting each conversation to disk. | |
| sds-mcp-server cat-people-82/sds-mcp-server MCP server that lets users search Safety Data Sheets (SDS) by chemical or product name, returning records with direct links to SDS documents. | |
| EuiccBridge cat0513/euiccbridge Enables management of eSIM profiles, SMS, and cellular modem diagnostics on Linux through a CLI and MCP server with safety defaults. | |
| PromptMotion MCP catais/promptmotion-mcp Enables creating complete product presentation videos from a single ChatGPT request, with browser-based rendering and export to multiple aspect ratios. | |
| Leonardo MCP catalanicd/leonardo-ai-mcp Enables submitting image generation jobs and polling their status to retrieve generated image URLs through Streamable HTTP MCP tools. | |
| waha-fast-mcp catalanicd/waha-fast-mcp Connects MCP hosts and LangChain agents to a local WAHA (WhatsApp HTTP API) instance, exposing tools for session management, chats, messages, contacts, and sending text, images, or files. It also provides an operational skill prompt coverin | |
| waha-langchain-mcp catalanicd/waha-langchain-mcp Enables LangChain ReAct and deep agents to manage WhatsApp sessions, chats, contacts, and messages—including sending text, images, and files—through MCP tools backed by a local WAHA instance. | |
| mcp-server-starrocks catalano19572/mcp-server-starrocks Enables AI assistants to query and explore StarRocks databases, inspect schemas, metrics, and sample data, and generate Plotly charts from query results without complex client-side setup. | |
| catalora-mcp cataloraxyz/catalora-mcp An MCP server for trading agents that provides eight tools to trade under enforceable limits, local paper trading, and comprehensive risk management. | |
| spanner-mcp-server catalyst-edu-llc/spanner-mcp-server Enables read-only SQL queries and schema introspection for Google Cloud Spanner, supporting both GoogleSQL and PostgreSQL dialects. | |
| MCP Read Images catalystneuro/mcp_read_images An MCP server for analyzing images using OpenRouter vision models, offering capabilities like automatic image resizing, model configuration, and handling custom queries about images. | |
| dothub catancs/dothub Publish your Claude Code setup, browse a public feed, and pull setups in. Remote MCP server + web feed in one FastAPI app. | |
| vision-bridge-mcp catapult291/vision-bridge-mcp Enables text-only LLMs to analyze, OCR, and compare images by forwarding them to vision-capable models via OpenAI or Anthropic APIs. | |
| idescat-mcp catbru/idescat-mcp Provides access to Catalonia's statistical data via the IDESCAT Tables API v2. It enables users to navigate catalogs, inspect metadata, and query data with territorial filters and resolved labels. | |
| BEA catbyte-security/bea Enables AI agents to dynamically observe and test running Windows x64 user-mode programs through Frida instrumentation, memory scanning, hardware watchpoints, Ghidra address mapping, in-process oracle calls, and Unicorn emulation diffs. | |
| MCP Selenium Grid catchnip/mcp-selenium-grid Enables browser automation by managing Selenium Grid browser instances (Chrome, Firefox, Edge) in Docker or Kubernetes environments. Provides secure, scalable browser control for AI agents and testing workflows. | |
| Todo MCP Server cateland/poc_todo_mcp_server A robust Model Context Protocol server for managing todos with capabilities for task creation, filtering, and statistical analysis. It enables AI assistants to interact with todo datasets through specialized tools, structured resources, and |
37,051–37,100 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.