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 |
|---|---|
| GitHub MCP Server awaybreaktoday/mcp-github-actions Enables comprehensive interaction with GitHub repositories, including code management, issues, pull requests, and full GitHub Actions workflow control with triggering, monitoring, and artifact management capabilities. | |
| Local Workspace MCP awe7893625/local-workspace-mcp-hardened Enables self-hosted local file, terminal, document, and named-device tools for MCP clients, with an isolated document mode and a full-access mode. | |
| RSS-MCP awee1453/rss-mcp Professional RSS/Atom feed management system with AI-powered analytics including sentiment analysis, trend detection, auto-categorization, cross-source verification, automated scheduling, and content export capabilities. | |
| invoiceninja-mcp aweher/invoiceninja-mcp Connects AI assistants to an Invoice Ninja v5 instance so users can query clients, invoices, quotes, payments, expenses, dashboard totals, and 25+ native reports in natural language. It runs read-only by default with opt-in writes, secret a | |
| antibanana-mcp awei84/antibanana-mcp 封装了 Google Antigravity 的 Nano Banana 图像生成能力，使 AI 客户端可通过 MCP 调用生成或编辑图片。 | |
| job-hunt-agent awen11123/job-hunt-agent Private Notion-backed recruitment tracker for AI/LLM engineer job hunting, exposed as an MCP server to manage applications, interviews, and contacts securely. | |
| mcp-server-telegram awenas/mcp-server-telegram Integrates Telegram bots as MCP tools for sending messages to staff groups or manager chats, listing buffered messages, and viewing group members. | |
| github-mcp awernick/github-mcp MCP server exposing GitHub tools for issues, pull requests, and code browsing via the GitHub REST API. Designed for local LLM clients with flat arguments and streamable HTTP support. | |
| Elasticsearch MCP Server awesimon/elasticsearch-mcp Connects agents to Elasticsearch data using the Model Context Protocol, allowing natural language interaction with Elasticsearch indices through MCP Clients like Claude Desktop and Cursor. | |
| mcp-ready-data-discovery-tool awesome0w/mcp-ready-data-discovery-tool Enables local data discovery by indexing metadata from SQLite, CSV, and Markdown sources, providing hybrid keyword and TF-IDF semantic search via MCP tools (listSources, indexSource, search, getSchema) and a REST API. | |
| agent-room-mcp awesomeme01/agent-room-v Enables real-time multi-agent AI collaboration in shared rooms over MCP, allowing coding agents to exchange structured messages, track evidence-gated tasks, and export reports for distributed development, code review, and frontend-backend i | |
| portal-api awfusion/portal-api-mcp A read-only MCP server for Portal.io that enables browsing proposals, users, contacts, and catalog items through secure HMAC-signed API requests. | |
| QGIS MCP Server awheeler262/qgis_mcp Enables interaction with QGIS (Quantum GIS) through an MCP plugin and server, allowing natural language commands to control QGIS. | |
| flow-agent-mcp awictor/flow-agent-mcp An MCP server that exposes Estuary Flow pipeline operations as typed tools, enabling agents to inspect pipeline health, publish captures and materializations, edit/restart tasks, and read landed documents via tool calls. | |
| SharedBrain awictor/shared-brain Local-first, multi-user shared memory for AI agents with semantic search, offline support, and team synchronization. | |
| floci-mcp awilliv/floci-mcp Enables AI agents to deploy and manage simulated AWS resources (like EC2, S3, DynamoDB) on a local Floci instance through natural language. | |
| SQLite MCP Server awiseking/sqlite_mcp_server Enables AI assistants to interact with SQLite databases by executing read and write queries, listing tables, and inspecting schemas. It provides a secure, local interface for database management and data retrieval through the Model Context | |
| d3p MCP Server awkie1/d3p-mcp-server MCP server for the digital3 agent protocol (d3p) — exposes all d3p services as MCP tools that any MCP client can call. | |
| mcp-netsuite-practice awnt9/mcp-netsuite-practice MCP server that exposes read-only NetSuite tools for querying warehouse stock levels and order status, using mock data locally and a pluggable client interface. | |
| Gitingest-MCP awroblewski13/gitingest-mcp Enables MCP clients to quickly extract information about GitHub repositories, including repository summaries, project directory structures, and file contents. | |
| threejs-devtools-mcp awroblewski66208/threejs-devtools-mcp Enables AI agents to inspect and live-edit 3D browser scenes — objects, materials, shaders, lights, textures, animation, performance and memory — and to turn previewed tweaks into ready-to-paste React Three Fiber or vanilla code. It also ad | |
| tmux-bridge-mcp awroblewski98/tmux-bridge-mcp Enables AI agents running in separate tmux panes to read each other's terminal output, send messages and keystrokes, and coordinate multi-agent workflows through standard MCP tool calls. | |
| clawclaw-soul awrshift/clawclaw-soul Provides real-time temporal drift to SOUL.md agent identities, enabling agents to check their current behavioral state through tools like get_daily_drift. | |
| Powertools MCP Search Server aws-powertools/powertools-mcp Enables LLMs to search through AWS Lambda Powertools documentation across multiple runtimes (Python, TypeScript, Java, .NET) using a Model Context Protocol server. | |
| Nova Act MCP Server aws-samples/sample-agents-with-nova-act-and-mcp Exposes Amazon Nova Act web automation capabilities through the Model Context Protocol, enabling AI agents to perform browser tasks like navigation, data extraction, and form interaction. | |
| simple-websearch-mcp aws-samples/sample-api-for-websearch-on-agentcore This MCP server enables any MCP client to perform web searches over HTTP using just an endpoint URL and API key, abstracting away AWS SigV4 signing and Bedrock AgentCore protocol translation entirely server-side. | |
| CFM Tips - Cost Optimization MCP Server aws-samples/sample-cfm-tips-mcp A comprehensive Model Context Protocol server that analyzes AWS costs and provides optimization recommendations by integrating with services like Cost Explorer, Cost Optimization Hub, and Trusted Advisor. | |
| AWS Cost Explorer MCP Server aws-samples/sample-cloud-spend-mcp-server Enables analyzing AWS cloud spending and Bedrock usage through natural language queries using Claude. | |
| AWS Deep Learning Containers MCP Server aws-samples/sample-dlc-mcp-server Provides tools for discovering, building, deploying, and troubleshooting AWS Deep Learning Containers (DLC) images. Supports multiple frameworks and instance recommendations. | |
| AWS DR Cost Estimator MCP Server aws-samples/sample-dr-cost-estimator-mcp Plan AWS disaster recovery budgets conversationally, comparing backup/restore, pilot light, warm standby, and active/active strategies using live Cost Explorer data. | |
| @aws/ftr-eval-mcp aws-samples/sample-ftr-self-assessment-mcp Automates the AWS Foundational Technical Review (FTR) partner self-assessment by evaluating SOC 2 and WAFR reports against defined controls, returning structured PASS/FAIL decisions with reasoning. | |
| Governed Agentic Companion aws-samples/sample-governed-agentic-companion Enables MCP clients to interact with a safe, orchestrator-driven multi-agent builder that enforces governance constraints such as no deployment, no secret leakage, and grounded, non-hallucinated answers through an always-on governance gate. | |
| AWS Health MCP Server aws-samples/sample-health-mcp-server MCP server that exposes AWS Health API as tools for checking service health, events, and scheduled maintenance at account or organization level. | |
| Allotrope MCP Server aws-samples/sample-laboratory-data-transformation-mcp Provides tools for validating, listing, describing, and fetching Allotrope Simple Model (ASM) data formats for laboratory instruments. | |
| Lark AgentCore Gateway Interceptor MCP Server aws-samples/sample-lark-identity-on-agentcore-interceptor Enables Bedrock agents to act as a Lark user, performing document operations (list, create, edit, delete) and identity verification via Lark's REST API, with per-user credential injection through a Gateway Interceptor. | |
| lark-mcp-on-agentcore aws-samples/sample-lark-mcp-on-agentcore A hosted remote MCP service enabling AI clients to call Feishu's 2500+ APIs via 200+ tools, with smart orchestration for multi-step operations. | |
| mcp-identity-proxy-for-aws aws-samples/sample-mcp-identity-proxy-for-aws A client-side MCP proxy that injects OAuth 2.0 bearer tokens or API keys into MCP requests, enabling MCP clients to connect to OAuth/API-key-protected MCP servers like Amazon Bedrock AgentCore Gateway. It automatically fetches and refreshes | |
| MCP Security Scanner aws-samples/sample-mcp-security-scanner Integrates Checkov, Semgrep, Bandit, and ASH to provide comprehensive code security analysis for AI coding assistants. | |
| Sample S3 MCP Server aws-samples/sample-mcp-server-s3 Enables interaction with AWS S3 buckets to list buckets and objects, retrieve files, and expose PDF documents as resources that can be loaded into the LLM's context. | |
| Quick Space Migrator aws-samples/sample-quick-migrator-mcp MCP server that migrates Amazon Quick Suite resources (Spaces, Chat Agents, Action Connectors, and S3 Knowledge Bases) between AWS accounts, preserving permissions and linkages, with idempotency and preview dry-run support. | |
| SPICE Capacity Optimiser aws-samples/sample-quicksight-spice-capacity-optimiser Enables users to identify unused columns in Amazon QuickSight SPICE datasets, remove them after confirmation, list and manage snapshots, and roll back changes to reduce storage costs and speed up refreshes. | |
| ABAP Accelerator MCP Server aws-solutions-library-samples/guidance-for-deploying-sap-abap-accelerator-for-amazon-q-developer Enterprise-grade MCP server for SAP ABAP development, enabling AI-powered coding assistance through Amazon Q Developer and Kiro with 15 SAP development tools. | |
| Sessionize MCP Server aws-user-group-toolkit/otto-mcp-sessionize Enables AI agents to search for speakers and talks by date using the Sessionize API. | |
| Zotero MCP Server awsl5714/zotero-mcp-server Enables LLM-powered tools to interact with Zotero academic libraries, including searching papers, adding arXiv papers, updating metadata, and generating literature reviews. | |
| amazon-datazone-mcp-server awslabs/amazon-datazone-mcp-server A high-performance Model Context Protocol (MCP) server that provides seamless integration with Amazon DataZone services. This server enables AI assistants and applications to interact with Amazon DataZone APIs through a standardized interfa | |
| IAM Policy Autopilot awslabs/iam-policy-autopilot Analyzes application code locally to automatically generate baseline AWS IAM identity-based policies by detecting AWS SDK calls in Python, Go, and TypeScript applications. Helps AI coding assistants quickly create IAM permissions that can b | |
| Log Analyzer with MCP awslabs/log-analyzer-with-mcp A Model Context Protocol server that provides AI assistants access to AWS CloudWatch Logs, enabling browsing, searching, summarizing, and correlating logs across multiple AWS services. | |
| AWS SRA Verify MCP Server awslabs/sra-verify-mcp Enables AI agents to assess AWS environments against the AWS Security Reference Architecture (SRA) by providing tools to discover, describe, and run security checks across AWS services and accounts. | |
| Threat Modeling MCP Server awslabs/threat-modeling-mcp-server A comprehensive MCP server for structured threat modeling using STRIDE methodology, with automatic code validation and report generation. | |
| claude-code-orchestrator awslew/codex-job-orchestrator This MCP server enables asynchronous, event-driven orchestration of long-running AI coding agents, allowing a leader session to dispatch jobs that execute in the background, survive disconnects, and provide queryable status and resumability |
32,051–32,100 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.