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 |
|---|---|
| huawei-cloud-ascend-command Huawei Ascend NPU natural language management skill, supporting both local direct connection and SSH remote modes. Provides comprehensive npu-smi command capabilities including device queries, configuration management, firmware upgrade, vNP | |
| huawei-cloud-ascend-models-deploy Huawei Cloud Ascend model deployment and testing skill for large language models on Ascend DevServer (910B series). Supports single-machine and dual-machine deployment for LLM, VL (vision-language), Embedding, and Rerank models. Provides mo | |
| huawei-cloud-ascend-op-mfu-calculator Calculate MFU (Machine FLOP Utilization) for operators like matmul/GEMM/FlashAttention on Ascend NPU, providing clear formulas and derivation process Use this skill when the user wants to: (1) calculate MFU for matrix operations, (2) analyz | |
| huawei-cloud-ascend-profiler-db-explorer Convert natural language questions into safe executable SQL to query Ascend PyTorch Profiler / msprof database for operator time consumption, communication, dispatch, and other performance data. Supports table schema extraction from officia | |
| huawei-cloud-ascend-remote-connect Provides temporary SSH remote connection for Huawei Cloud Ascend devices with dynamic host/port/user/password input (in-memory only), disk management, NPU monitoring, container management, security auditing and log analysis; sensitive opera | |
| huawei-cloud-ascend-small-model-migrate Migrate vision/detection/segmentation small models to Ascend NPU, covering the full workflow: model structure analysis, migration verification, performance profiling, and optimization. Based on torch_npu and msprof Use this skill when the u | |
| huawei-cloud-ascendc-operator-performance-optim Develop and optimize custom operators using AscendC programming language. Analyze operator performance bottlenecks and conduct optimization validation. Based on AscendC and CANN toolkit Use this skill when the user wants to: (1) optimize pe | |
| huawei-cloud-billing-scout Huawei Cloud BSS billing (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page brief | |
| huawei-cloud-business-tf-support Queries Huawei Cloud billing and fee details only when Terraform needs a billing or pricing inquiry. Covers balances, bills, coupons, cash coupons, stored-value cards, orders, refunds, costs, free resources, resource usage, enterprise accou | |
| huawei-cloud-cc-central-network-query Queries Huawei Cloud Cloud Connect (CC) Central Network resources via hcloud CLI. Covers central network instances (single + list), central network attachments (single + list, including ER route table and GDGW attachment types), and central | |
| huawei-cloud-cc-gcb-query Queries Huawei Cloud Cloud Connect (CC) Global Connection Bandwidth (GCB) resources via hcloud CLI. Covers single GCB detail query (including bound instance info), GCB list query with filters, GCB tenant configuration query (size ranges, qu | |
| huawei-cloud-cc-instance-query Queries Huawei Cloud Cloud Connect (CC) resources via hcloud CLI. Covers cloud connection instances (single + list), bandwidth packages (single + list), inter-region bandwidths (single + list), network instances (single + list), cloud conne | |
| huawei-cloud-cce-alarm-correlation-engine Huawei Cloud AOM alarm correlation and alarm-rule management skill for CCE operations. Use this skill when the user wants to: (1) query AOM active and historical alarms, (2) analyze alarm deduplication, alarm storms, severity grouping, burs | |
| huawei-cloud-cce-chaos-experiment Huawei Cloud CCE AZ power outage chaos experiment — end-to-end fault drill: discover clusters and node AZ distribution, validate cross-AZ capacity, shut down all CCE nodes in one AZ to simulate a power failure, observe Pod eviction and resc | |
| huawei-cloud-cce-cluster-management Huawei Cloud CCE (Cloud Container Engine) cluster lifecycle management skill using hcloud CLI (KooCLI) for Huawei Cloud API calls and kubectl cce plugin for Kubernetes node operations (cordon/uncordon/drain/status). Use this skill when the | |
| huawei-cloud-cce-cluster-migrator End-to-end Kubernetes cluster migration assistant for migrating self-hosted, on-premise, or third-party cloud Kubernetes workloads to Huawei Cloud Cloud Container Engine (CCE). Covers source cluster assessment, CCE cluster sizing, container | |
| huawei-cloud-cce-env-assessment A skill for huawei cloud container(CCE) assessment. It automatically collects metrics and configurations from containerized application environments on Huawei Cloud to generate a comprehensive assessment report. Use this when users want to | |
| huawei-cloud-cce-kubernetes-event-analyzer Query and analyze Kubernetes Events in Huawei Cloud CCE clusters. Trigger when users ask about CCE events, Kubernetes warning events, FailedScheduling, FailedMount, ImagePullBackOff, event patterns, historical events in LTS, or event-based | |
| huawei-cloud-cce-log-analyzer Query and analyze Huawei Cloud CCE workload, audit, and control-plane logs. Use when investigating CCE logs, Kubernetes logs, Pod logs, application logs, audit logs, LTS logs, kube-apiserver logs, kube-scheduler logs, log analysis, log coll | |
| huawei-cloud-cce-metric-analyzer Huawei Cloud CCE Metric analysis skill using the Python dispatcher with hcloud-backed cloud service queries. Use this skill when the user wants to: (1) query Pod/Node/CoreDNS/nginx-ingress/autoscaler/control-plane CPU, memory, disk, QPS, la | |
| huawei-cloud-cci-instance-management Huawei Cloud CCI (Cloud Container Instance) full lifecycle management using hcloud CLI. Covers Namespace, Network, Deployment, StatefulSet, Pod creation/update/delete/status, EIPPool for public IP, logs and metrics. Two-step confirmation fo | |
| huawei-cloud-cdn-abnormal-status-code-analysis Diagnose CDN business abnormal HTTP status codes (4xx/5xx) using hcloud CLI. Discover and quantify 4xx/5xx volume, localize the exact status code and time window, fork edge-generated vs origin-generated via back-to-source status statistics, | |
| huawei-cloud-cdn-certificate-diagnosis Triggers include: "certificate diagnosis", "certificate expiry", "HTTPS certificate", "certificate configuration", "SSL certificate", "cert expiry check". Diagnose CDN HTTPS certificate configuration and expiration status using hcloud CLI. | |
| huawei-cloud-cdn-dns-resolution-diagnosis Diagnose CDN domain DNS resolution issues using hcloud CLI and Python DNS probes. Query the CDN domain detail to obtain the expected CNAME, probe the actual DNS resolution of the domain via scripts/dns_resolve.py (dnspython) to collect reso | |
| huawei-cloud-cdn-domain-ownership-verification Diagnose CDN domain ownership verification failures using hcloud CLI. Query the ownership verification method (DNS TXT or file verification) configured by CDN, probe the actual verification record or file, and compare against the expected v | |
| huawei-cloud-cdn-origin-diagnosis Diagnose CDN origin server reachability and back-to-source failures using hcloud CLI. Query the origin configuration (origin_addr, origin_type, http_port, https_port, origin_protocol) of a CDN domain via ShowDomainFullConfig/v2, then probe | |
| huawei-cloud-cdn-traffic-anomaly-analysis Analyze CDN domain traffic anomalies using hcloud CLI. Query billing mode and traffic/bandwidth metrics for specified domains, compare against 3-month baseline and absolute thresholds to identify traffic theft or abuse. Use this skill when | |
| huawei-cloud-cdn-universal-query Comprehensive CDN query reference skill using hcloud CLI. Covers all 44 GET read-only CDN APIs organized by category: domain management, statistics & analytics, refresh/log/export, template/rule/tag/account. Provides command templates, para | |
| huawei-cloud-ces-aom-capacity-assessment Huawei Cloud capacity assessment. Assesses capacity for instances across 21 services (NAT/RDS/ECS/ELB/EIP/CSS/DDS/DWS/DCS/DMS/TaurusDB/GeminiDB/DC/ER/EVS/EFS Turbo/APIG/DRS/VPCEP/Bandwidth/CCE) by comparing peak/valley fluctuations of monit | |
| huawei-cloud-ces-drill-inspection Fault drill steady-state inspection tool. Collects instance status and CES monitoring metrics across Huawei Cloud multi-region ECS/RDS/DCS(Redis) and 19 cloud services via hcloud CLI, compares against expected steady-state baseline, and gen | |
| huawei-cloud-ces-ecs-monitoring Huawei Cloud ECS monitoring skill using Cloud Eye Service (CES). Provides comprehensive monitoring and metrics query for Elastic Cloud Server instances including CPU, memory, disk, network, and system metrics. Supports real-time monitoring, | |
| huawei-cloud-ces-elb-monitoring Huawei Cloud ELB monitoring skill using Cloud Eye Service (CES). Provides comprehensive monitoring and metrics query for Elastic Load Balance instances including connection metrics, traffic metrics, HTTP status codes, and performance indica | |
| huawei-cloud-cli-guidance Provides guidance for Huawei Cloud KooCLI command-line tool operations. Covers KooCLI installation, IAM authentication configuration, access credential configuration, command construction, common error troubleshooting. Use this skill when u | |
| huawei-cloud-cloudrobo-asset Manage the full lifecycle of CloudRobo assets — query repositories and catalogs, create/list/show/update/delete assets and versions, batch-delete, tag management, predefined tag discovery, Action CRUD, permission checks, marketplace search, | |
| huawei-cloud-cloudrobo-dataset Manage CloudRobo data processing (proc-tasks) and data evaluation (eval-tasks) — query algorithms, create/list/show/update/delete/restart tasks; poll task status until terminal; retrieve system and job logs; download logs; preview output da | |
| huawei-cloud-cloudrobo-dispatch Manage CloudRobo embodied-agent task dispatch (robo-dispatcher) — create embodied tasks that drive a robot via an exec/model and constraints, list/show tasks in a session, cancel tasks, and retrieve task results. Dispatch orchestrates robot | |
| huawei-cloud-cloudrobo-infer Manage CloudRobo inference services — deploy a model into a managed inference service, list/query deployed services and their logs, start/stop a running service, update or delete a service, and orchestrate the 'wait-deploy' convenience flow | |
| huawei-cloud-cloudrobo-inference-adapter Guides adapting a VLA model's inference server interface to the CloudRobo standard interface/protocol. Use this skill when the user wants to create a compatible inference interface protocol for a model, or make a model compatible with the C | |
| huawei-cloud-cloudrobo-model-workflow Model development orchestration Skill covering asset query, model training, inference deployment, and real-robot evaluation in any combination. Supports full end-to-end pipeline or partial stages (e.g., train+deploy only, deploy+eval only). | |
| huawei-cloud-cloudrobo-r2c Run the R2C (Robot-to-Cloud) data-plane client — start the robot-side edge client (Zenoh pub/sub with mTLS credential bundle, hardware adapter, translator, control loop). The credential bundle is produced by the robot skill's export-certifi | |
| huawei-cloud-cloudrobo-resource Query CloudRobo resource quotas and resource pools — list workspace-level and Domain-level quotas with CCE/ModelArts isolation (CCE: cpu/memory/gpu, ModelArts: npu), list resource pools with multi-condition filtering (type/sub-type/pool-typ | |
| huawei-cloud-cloudrobo-robot Manage CloudRobo robot instances — register robots, query robot lists and details, update robot metadata, delete offline robots, export robot certificates for secure access, and fetch the latest robot-side SDK package information. Robots ar | |
| huawei-cloud-cloudrobo-train Manage CloudRobo model training tasks and simulation reinforcement learning (SimRL) tasks — create pretrain (TRAIN_FROM_SCRATCH) and finetune (MODEL_TUNING) tasks with FFT/SFT/LORA/QLORA/DEEPSPEED methods; manage the full task lifecycle (cr | |
| huawei-cloud-cloudrobo-train-metrics Integrate the ocms (Octopus Metrics Summary) library into any PyTorch training script to report training metrics (loss, learning rate, timing, eval scores, grad norm, etc.) to the Huawei Octopus platform for visualization. Use this skill wh | |
| huawei-cloud-cloudrobo-weight-layout Standard directory layout and naming conventions for saving model weights (checkpoints). Use this skill when the user needs to implement checkpoint saving in a training script, restructure an existing checkpoint/output directory layout, dec | |
| huawei-cloud-cloudrobo-workspace Manage CloudRobo workspaces — create, list, show, update, delete workspaces; manage workspace members (add, list, update role, delete); view workspace overview statistics (capacity, used, available, member count); switch active workspace co | |
| huawei-cloud-codearts-code-gen CRITICAL — Do NOT write code yourself. Route ALL code generation through this Skill. This is the MANDATORY entry point. When a user asks for any code, file, project, or feature (生成代码/write code, 写函数/write a function, 创建模块/create a module, 开 | |
| huawei-cloud-codearts-pipeline-diagnose Huawei Cloud CodeArts Pipeline (流水线) and CodeArts Build (编译构建/构建任务) management, monitoring and failure diagnosis using the KooCLI hcloud command-line client. Covers pipeline and build-task listing/detail, build log retrieval, build failure | |
| huawei-cloud-computing-query Queries Huawei Cloud computing resources (ECS/BMS/IMS/AS), Covers ECS instances, flavors, keypairs, quotas, server groups, block devices, NICs, VNC console, BMS bare metal servers/flavors/quotas, IMS images/OS versions/members/quotas, and A | |
| huawei-cloud-config-helper Queries Huawei Cloud Config service for global resource inventory, resource configurations, resource schemas, advanced SQL queries, and built-in compliance rules. Read-only. Use this skill when the user needs to query cloud resources, audit |
36,901–36,950 of 108,824
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.