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 |
|---|---|
| ClawSouls MCP Server clawsouls/clawsouls-mcp Provides tools for AI agent persona management, safety verification, and efficient swarm memory synchronization across multiple agents. It enables users to search and install personas while utilizing a token-efficient Git-based workflow for | |
| Clawy MCP Server clawypro/clawy-mcp-server Pay-per-use API tools and LLM gateway for AI agents. 15 services (DART, Tabelog, Google Maps, Brave Search, Firecrawl, DeepL, ElevenLabs, and more) + smart LLM routing. No API keys needed, pay with USDC on Base. | |
| OpenLore clay-good/openlore Provides persistent architectural memory and structural cognition for AI coding agents, enabling efficient orientation, graph-aware context, and drift detection across codebase evolution. | |
| Rough Logic clay-good/roughlogic.com Always free field math and reference for the trades. | |
| Sophie Well clay-good/sophiewell.com Always free healthcare utilities. | |
| sciflow-mcp claybarn/sciflow-mcp Enables scientists and their agents to build type-checked, reproducible, interoperable analysis workflows over stamped data along arbitrary parametric axes, with content-addressed artifacts, provenance, dataset pipelines, and session-aware | |
| distru-mcp claygeo/distru-mcp Enables AI agents to interact with Distru's ERP data through read tools and a guarded sales-order draft tool, using realistic fixture data by default or the live public API with an optional token. It provides dry-run writes bound to a confi | |
| multi-mail-mcp claygeo/multi-mail-mcp Local-first MCP server for agents that need to work across multiple Gmail and Microsoft 365 accounts without cloud token storage. | |
| MCP Connection Hub claymore666/mcpconnectionhub A unified Model Context Protocol Gateway that bridges LLM interfaces with various tools and services, providing OpenAI API compatibility and supporting both synchronous and asynchronous tool execution. | |
| hansung-university-regulation-mcp clayop/hansung-university-regulation-mcp Enables searching and retrieving regulations from the Hansung University regulation management system. | |
| korean-university-regulation-mcp clayop/korean-university-regulation-mcp MCP server to search and retrieve regulations from 14 Korean universities' regulation management systems. Supports querying, listing, and viewing full text or specific articles. | |
| agent-crm clayton/agent-crm Enables AI agents to manage CRM data including companies, contacts, prospects, pipelines, forecasts, and tasks via typed MCP tools, with local SQLite storage and a JSON CLI. | |
| MCP Memory claywaterson-main/mcp-memory Enables MCP clients to store and retrieve user preferences, behaviors, and other text-based information across conversations using semantic vector search. | |
| agent-discovery-mcp clayytsai/agent-discovery-mcp An MCP server that lets your AI coding agent (Claude Code, OpenClaw, Codex, Cursor, etc.) discover and pay on-chain agents registered on ERC-8004, using Coinbase's official x402 protocol.
No smart account. No bundler. No relay. Just your E | |
| Xray MCP Server clcc2019/xray-mcp Enables generation and validation of Xray-core proxy configurations using natural language. Supports VLESS, VMess, Trojan, and Shadowsocks protocols with automatic key generation and multiple transport/security options including REALITY. | |
| story-mcp clchinkc/document-mcp Enables writers and researchers to manage large Markdown documents with AI-powered tools, including version history, semantic search, and context management. | |
| Edge Flow Manager MCP Server cldr-steven-matison/edge-flow-manager-mcp-server Provides LLM agents with read-only access to Cloudera Edge Flow Manager (EFM) for MiNiFi edge agents. Enables fleet health monitoring, flow inspection, and deployability validation through GET-only tools. | |
| foodvisor-mcp cldt-fr/foodvisor-mcp MCP server integrating Foodvisor nutrition API for food search, meal logging, daily summaries, and progress tracking via LLM agents like Claude. | |
| OwnContext clean99/owncontext Enables AI clients to read, search, remember, and correct Markdown context stored in a private GitHub repository, with OAuth-scoped writes and SHA-checked updates to prevent overwriting newer edits. | |
| Creator Research MCP cleancod3systems/creator-research-mcp Fetches content data from YouTube, TikTok, Twitter, LinkedIn, articles, and PDFs so LLM clients can analyze content performance and generate insights. | |
| PostgreSQL MCP Server cleancodestar/pg-mcp-server Enables AI assistants to interact with PostgreSQL databases through MCP, supporting multi-database and schema access with security controls like read-only mode and SQL auditing. | |
| pyghidra-mcp clearbluejar/pyghidra-mcp Exposes Ghidra reverse engineering capabilities via MCP, enabling LLMs and agents to analyze binaries, decompile, search, and edit programs headlessly or with GUI integration. | |
| clearcote-mcp clearcotelabs/clearcote-browser Drive Clearcote, a Chromium build with its fingerprint protection patched into the engine, from any MCP client: about 20 tools to navigate, read, extract, click, fill, screenshot and keep sessions, plus a CDP endpoint that hands the same br | |
| clearcote-jet-mcp clearcotelabs/clearcote-jet Enables AI assistants to run complete website tasks in a real browser, returning every step, the final markdown content, and persistent tabs for follow-up calls or concurrent tasks. | |
| MCP C++ Analyzer cleardl/mcp-cpp-analyzer Provides precise C++ code semantic analysis for AI coding tools like Claude Code and Cursor by integrating clangd static analysis, enabling symbol definition lookup, reference tracking, and hover information. | |
| ckm365 clearkan/ckm365 Enables secure, multi-tenant Microsoft 365 mail and calendar management through Microsoft Graph, with tiered permissions, draft-only compose flows, and support for Claude Code, pydantic-ai, and programmatic access. | |
| minio_mcp clearmind1/minio_mcp A FastMCP-based server that enables uploading text and base64-encoded content to MinIO object storage through an HTTP transport. It supports automated bucket management and secure file path generation to streamline remote storage operations | |
| clr-librenms-mcp clearminds/clr-librenms-mcp MCP server for LibreNMS network monitoring — query devices, alerts, sensors, ports, and more through AI assistants like Claude. | |
| clr-openmanage-mcp clearminds/clr-openmanage-mcp MCP server for Dell OpenManage Enterprise that allows AI assistants to monitor and manage Dell servers, including device health, alerts, warranties, firmware compliance, and jobs. | |
| Task MCP clearner1/task-mcp Enables AI assistants to manage Dida365 (滴答清单) tasks through the Model Context Protocol. It supports full task lifecycle management including creating, updating, and filtering tasks with automatic timezone handling. | |
| clearskies MCP Server clearskies-py/mcp-server Provides AI assistants with tools for code generation, documentation, and project scaffolding when building applications with the clearskies Python framework. | |
| SkyeNet-MCP-ACE clearskye/skyenet-mcp-ace Enables AI agents to execute server-side JavaScript and perform CRUD operations directly on ServiceNow instances with context bloat reduction features for efficient token usage. | |
| Atelier B MCP Server clearsy/atelierb-mcp Connects Claude AI to Atelier B formal methods IDE, enabling typechecking, proof generation, automatic proving, and C code generation for B projects. | |
| DevScope MCP cleberfarias/devscope-mcp Provides project context for AI agents in VS Code by analyzing technologies, structure, AGENTS.md rules, current branch, and source code without allowing arbitrary commands. | |
| XRPL Agent Wallet MCP clecknert/xrpl-wallet-mcp Provides secure, policy-controlled wallet infrastructure for AI agents to autonomously manage XRP Ledger wallets and sign transactions. It features a tiered security model with encrypted key storage, a declarative policy engine, and full au | |
| flink-mcp cledar/flink-mcp Enables interaction with Apache Flink clusters via the SQL Gateway, allowing query execution, session management, and job control through MCP tools. | |
| CSV MCP Server cledupe/mcp-csv Enables AI assistants to answer natural language questions about data in CSV files using Polars filter expressions. | |
| ETABS MCP Server cleisonmanriqueaguirre/mpc-etabs-1.0 Enables users to control CSI ETABS structural engineering software through Claude, allowing model creation, status checks, and engineering checks via COM automation. | |
| cleimesh cleitonaugusto/cleimesh Signed, delegable permissions for AI agents that become the WebAssembly sandbox of each tool call, with a signed, hash-chained receipt per call that anyone can replay. Taint follows the delegation chain to contain prompt injection. | |
| github-pr-mcp clemdevlin/github-pr-mcp Enables GitHub repository operations (list/read files, create branches, commit files, open/list PRs) via an authless remote MCP server that keeps your GitHub token encrypted on Cloudflare, with access limited to allowed repositories. | |
| Wahoo MCP Server clemenshar/wahoo-mcp A Model Context Protocol (MCP) server for interacting with the Wahoo Cloud API, focusing on reading workout information. | |
| apec-mcp clement-igonet/apec-mcp MCP server that exposes the APEC candidate-profile API as tools for any MCP-compatible AI assistant, enabling profile management, job-search updates, and data retrieval. | |
| Weather MCP Server clement-okolo/weather-mcp Provides real-time weather alerts and forecasts for US locations by integrating with the National Weather Service API. Supports both server and client interactions with optional LLM summarization. | |
| swiss-apis-mcp clement8426/swiss-apis-mcp MCP server exposing all major Swiss official public APIs as native tools for any MCP-compatible AI agent. | |
| cascade-mcp clemente-turrubiates/cascade-mcp Exposes a hybrid conflict resolution router as MCP tools, deciding per conflict whether a multi-agent write wins, forks to a human, or must be recomputed. | |
| telegram-agent-mcp clemente-turrubiates/telegram-agent-mcp MCP server that exposes a Telegram bot over stdio transport, enabling LLM agents to discover each other, announce capabilities, and communicate via messages in shared group chats. It provides tools like whoami, announce, list_agents, ping_a | |
| vesper clemente-turrubiates/vesper Vesper provides MCP servers for multi-agent codebase coordination and a versioned, multi-agent-verified tool registry, enabling file/task claims, agent inboxes, and safe tool sharing. | |
| EasyHire AI MCP server clementhu689-a11y/easyhire-codex Enables creating or selecting EasyHire AI jobs and importing complete candidate profiles through a hosted remote MCP server. | |
| text2flink clementlemon02/text2flink A tool that converts natural-language requests into full, deployable, execution-verified Apache Flink SQL jobs by orchestrating an LLM to draft specs, generate Flink SQL, and verify correctness against real Flink clusters and streaming sema | |
| ADAM clementringot/adam Enables an AI assistant to debug ABAP code on a connected SAP system by setting breakpoints, running code, and capturing call stacks and variables, with one-shot or interactive stepping. |
39,251–39,300 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.