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 |
|---|---|
| dutch-gov-mcp alishark14/dutch-gov-mcp An unofficial MCP server providing access to Dutch government open data from data.overheid.nl, CBS statistics, and KVK business registry. Enables natural language queries for discovering datasets, inspecting metadata, and querying data with | |
| Agent Rooms alisheraxmedov/agent-rooms A self-hosted MCP server that lets coding agents such as Claude Code, Codex, OpenCode and Antigravity join named rooms, exchange messages, and run writer/reviewer loops without copying text between terminals. Long-poll hooks wake agents whe | |
| review-analyzer-mcp alisherizmukhan/review-analyzer Enables Claude Code to query a trained sentiment model and Amazon Electronics review analytics through typed, read-only tools. Supports sentiment classification, statistics, keyword and similar-review search, product summaries and compariso | |
| xpresso alisheryeginbay/xpresso Xcode MCP server for building, testing, running, and managing simulators directly from Claude Code. | |
| gamelibs-mcp alisoftware/gamelibs-mcp An MCP server that exposes your Steam, Epic Games Store, and IGDB game data as tools, enabling game library queries, install status checks, and metadata enrichment. | |
| mcp-tfl-journey alisonborba/mcp-tfl-journey Provides real-time Transport for London journey data, including routes, alerts, and disruptions, allowing AI assistants to search journeys and get station information. | |
| zotero-mcp alisoroushmd/zotero-mcp MCP server that lets AI assistants search, create, organize, and cite from a Zotero library. | |
| Sentinela alissonandrade1/sentinela-mcp Enables AI agents to run deterministic, fully local static security and compliance audits of code, configurations, and dependencies through 32 MCP tools covering 24 vulnerability categories. It also detects the project stack, generates risk | |
| parliamentary-nlp-mcp alissonf216/parliamentary-nlp-mcp MCP server that audits Brazilian parliamentary speeches for hate speech and offensive language using a fine-tuned BERTimbau classifier, returning classification, confidence, and human review recommendations. | |
| meta-mcp alissonjcdev/meta-mcp Connects Claude to Instagram through Meta's official API, enabling users to retrieve account insights, analyze professional profiles, publish photos/carousels/reels/stories, manage comments, read and respond to Direct messages, and call any | |
| MCProbe alitiknazoglu/mcprobe A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how | |
| HDFS MCP Server alittleyellowkevin/hdfs-mcp A Model Context Protocol server that enables interaction with Hadoop Distributed File System, allowing operations like listing, reading, writing, and managing HDFS files and directories. | |
| MySQL MCP Server alittleyellowkevin/mysql-mcp A Model Context Protocol server that enables agents to execute SQL queries against a MySQL database, supporting operations like SELECT, CREATE TABLE, INSERT, UPDATE, and DELETE with results returned in JSON format. | |
| StarRocks MCP Server alittleyellowkevin/starrocks-mcp A TypeScript implementation of a Model Context Protocol server that enables interaction with StarRocks databases, supporting SQL operations like queries, table creation, and data manipulation through standardized MCP tools. | |
| texchronicle aliutin/texchronicle Enables agents to compile LaTeX documents, manage anchored comments as actionable review tasks, inspect section-level history, and view diff images in a live workspace. | |
| Nika alive2/discord-mcp A comprehensive Discord MCP server enabling AI assistants to run a Discord community through 111 tools for messaging, moderation, roles, channels, forums, webhooks, and more, plus a raw REST API passthrough for full Discord API access. | |
| Rod MCP Server aliwatters/rod-mcp Browser automation for AI agents via the Model Context Protocol, enabling web navigation, form filling, screenshots, and more using Chromium. | |
| Colab MCP aliwoto/colab-mcp Enables agents to open or connect to a Colab browser tab and use notebook tools, resources, prompts, and progress through a local stdio session. | |
| OctSSH aliyahzombie/octssh Provides LLMs with safe, controllable, and stateful SSH access to shell environments, enabling remote command execution and file transfers with async support and security features. | |
| Dribbble MCP Server aliyar-khan/dribbble-mcp Enables coding agents to browse design inspiration and retrieve shots, comments, and user profiles through OAuth-authenticated API v2 access. Supports listing popular, debut, and everyone feeds and searching shots client-side. | |
| light-agent-memory-mcp-server aliyar-khan/light-agent-memory-mcp-server Provides persistent, searchable memory for AI agents across any MCP-compatible client, storing project context, user preferences, and session learnings locally in SQLite with tools to save, retrieve, search, and manage them. | |
| mcp-oauth-proxy aliyoussefi/mcp-oauth-proxy Enables connecting multiple remote HTTP MCP servers through a single local stdio endpoint, handling OAuth authentication, token refresh, and namespace-scoped tools. | |
| salesforce-mcp aliyoussefi/salesforce-mcp Enables interaction with Salesforce through the MCP protocol, handling OAuth authentication and secure token storage for users. | |
| ack-mcp-server aliyun/alibabacloud-ack-mcp-server 阿里云容器服务MCP Server，将ACK集群管理、Kubernetes原生操作和容器可观测性能力统一为AI原生的标准化工具集，支持通过自然语言与AI助手交互完成复杂的容器运维任务。 | |
| Adb MySQL MCP Server aliyun/alibabacloud-adb-mysql-mcp-server A universal interface that enables AI Agents to seamlessly communicate with Adb MySQL databases, allowing them to retrieve database metadata and execute SQL operations. | |
| AnalyticDB PostgreSQL MCP Server aliyun/alibabacloud-adbpg-mcp-server Serves as a universal interface between AI Agents and AnalyticDB PostgreSQL databases, enabling metadata retrieval and SQL execution, with additional capabilities for knowledge graph and LLM memory management. | |
| 阿里云 OpenAPI MCP Server aliyun/alibabacloud-api-mcp-server 远程MCP服务，通过Model Context Protocol为AI应用提供阿里云数万个OpenAPI的无缝集成，支持Terraform、多账号、自定义OAuth等能力。 | |
| DataWorks MCP Server aliyun/alibabacloud-dataworks-mcp-server A Model Context Protocol server that enables AI agents to interact with Alibaba Cloud DataWorks through standardized interfaces, allowing seamless management of DataWorks resources and operations via the DataWorks Open API. | |
| AlibabaCloud DevOps MCP Server aliyun/alibabacloud-devops-mcp-server Enables AI assistants to interact with Alibaba Cloud Yunxiao DevOps platform for managing projects, code repositories, work items, pipelines, deployments, and testing workflows through comprehensive organization, development, and delivery t | |
| Alibaba Cloud DMS MCP Server aliyun/alibabacloud-dms-mcp-server A Model Context Protocol server that enables large language models to access database metadata and perform cross-engine data querying across diverse database ecosystems. | |
| Alibaba Cloud FC MCP Server aliyun/alibabacloud-fc-mcp-server A Model Context Protocol server that enables agent applications like Cursor and Cline to integrate with Alibaba Cloud Function Compute, allowing them to deploy and manage serverless functions through natural language interactions. | |
| Hologres MCP Server aliyun/alibabacloud-hologres-mcp-server A universal interface that enables AI Agents to communicate with Hologres databases, allowing them to retrieve database metadata and execute SQL operations. | |
| TongXiao Common Search MCP Server aliyun/alibabacloud-iqs-tongxiao-mcp-server A Model Context Protocol server that provides enhanced real-time search capabilities by integrating with Alibaba Cloud IQS APIs to deliver clean, accurate results from multiple data sources. | |
| Lindorm MCP Server aliyun/alibabacloud-lindorm-mcp-server An example server that enables interaction with Alibaba Cloud's Lindorm multi-model NoSQL database, allowing applications to perform vector searches, full-text searches, and SQL operations through a unified interface. | |
| Alibaba Cloud Observability MCP Server aliyun/alibabacloud-observability-mcp-server Provides tools for accessing Alibaba Cloud observability products including SLS (Log Service) and ARMS (Application Real-time Monitoring Service), allowing any MCP-compatible AI assistants to quickly interact with these services. | |
| PolarDB-X MCP Server aliyun/alibabacloud-polardbx-mcp-server A Model Context Protocol server that enables AI agents to interact with Alibaba Cloud PolarDB-X databases through SQL queries, database inspection, and schema exploration. | |
| Alibaba Cloud RDS OpenAPI MCP Server aliyun/alibabacloud-rds-openapi-mcp-server A server that provides management and connectivity for Alibaba Cloud RDS database services via OpenAPI, enabling users to create, query, and modify RDS instances through MCP integration. | |
| Alibaba Cloud Supabase MCP Server aliyun/alibabacloud-supabase-mcp-server Enables AI assistants to manage Supabase projects deployed on Alibaba Cloud through natural language commands. Supports project creation/deletion, database querying, security configuration, and table management operations. | |
| Alibaba Cloud Yaochi DB MCP Server aliyun/alibabacloud-yaochi-db-mcp-server Enables AI coding assistants to manage Alibaba Cloud databases by creating instances, executing SQL, and more directly from the IDE. | |
| ESA MCP Server aliyun/mcp-server-esa An implementation of the Model Context Protocol server that enables AI models to communicate with Edge Security Acceleration (ESA) services, allowing models to manage routines, deployments, routes, records, and sites through standardized pr | |
| Aliyun RDS Supabase MCP Server aliyun/rds-supabase-mcp MCP server for Supabase instances running on Aliyun RDS, enabling AI assistants to interact with your Supabase instance hosted on Aliyun cloud infrastructure. | |
| agent-honeypot alizafarbati/agent-honeypot Enables defenders to deploy a decoy MCP tool server that records and fingerprints how LLM agents probe, escalate, and persist, without exposing real systems. | |
| ISNAD alizahidraja/isnad Grades the transmitters and the chain, not just the claim — grade_claim grades a claim against your local rijāl registry (ordinal + provenance, never numeric confidence). AI audit trail for RAG and multi-agent systems. | |
| SQL Database Bridge alizaimovic/sql-database-bridge MCP server that connects to SQL databases (SQLite, PostgreSQL, MSSQL, MySQL) and provides tools to run read-only queries, list schemas/tables, and manage connections via stdio transport. | |
| Documentation Crawler & MCP Server alizdavoodi/mcpdocsearch Toolset that crawls websites, generates Markdown documentation, and makes that documentation searchable via a Model Context Protocol (MCP) server for integration with tools like Cursor. | |
| zhihu-mcp alizeeblack-code/zhihu-mcp Enables AI agents to search, read, and analyze Zhihu content including questions, answers, comments, and user activities through the MCP protocol. | |
| Planning Data GOV.UK MCP Server alizoli/planningdatagovuk-api Auto-generated Model Context Protocol server that provides an interface to the planning.data.gov.uk API, allowing users to interact with UK planning data resources through natural language commands. | |
| snowflake-cost-mcp alizubairs/snowflake-cost-performance-mcp-server Provides read-only visibility into Snowflake warehouse cost and query performance, including credit usage by warehouse, expensive queries, and heuristic right-sizing recommendations. | |
| ZenBiz MCP Manager aljon-zb/mcp-manager Acts as a multi-tenant MCP gateway, letting multiple AI clients access tenant-specific tools and integrations through a single public endpoint, with configuration and secrets managed via YAML and environment variables. | |
| mcp-multiclient-platform aljon-zb/mcp-multiclient-platform Enables deploying multiple isolated Odoo MCP connector containers from a single shared codebase, each with its own configuration and credentials for different clients. |
26,651–26,700 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.