mcp-core-best-practices

mcp-core-best-practices is a skill for Claude Code from aliyun/alibabacloud-agent-toolkit. It costs 78 tokens per session (5,196 once invoked), scanned A, original, Apache-2.0.

A reference guide for using Alibaba Cloud’s general-purpose API server through an MCP connection. It explains how to find APIs, inspect their definitions, generate commands, run them, and handle longer tasks.

In plain words
What is it for?
Finding Alibaba Cloud APIs and documentation, generating or running CLI commands, checking API parameters and errors, polling asynchronous tasks, and preparing infrastructure-as-code operations.
Why use it?
It helps when Alibaba Cloud’s many APIs are difficult to discover or use correctly. It also documents workflows for regions, multiple accounts, infrastructure-as-code, and safety settings.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the alibabacloud-core plugin — 10 skills, 6 hooks, 1 MCP server shipped together

Good fit Finding Alibaba Cloud APIs and documentation, generating or running CLI commands, checking API parameters and errors, polling asynchronous tasks, and preparing infrastructure-as-code operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add aliyun/alibabacloud-agent-toolkit --skill mcp-core-best-practices
Clone the repo
git clone --depth 1 https://github.com/aliyun/alibabacloud-agent-toolkit

Made for: Claude Code.

Or install alibabacloud-core, the plugin that ships this one along with the rest of its 10 skills, 6 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-core-best-practices

README.md
[![agentmods](https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices/github.svg)](https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices)
Your own site
<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-core-best-practices

Your own site · 80×15
<a href="https://agentmods.dev/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices"><img src="https://agentmods.dev/badge/skills/aliyun/alibabacloud-agent-toolkit/mcp-core-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Output Handling · line 91
    Model output is used without validation or sanitization. Unvalidated output injected into downstream contexts (SQL, shell, HTML) enables injection attacks and arbitrary code execution.
    Fix: Validate and sanitize all model output before using it in downstream contexts. Use parameterized queries for SQL, shell quoting for commands, and HTML encoding for web output.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.05196
Opus 5 $0.00039 $0.02598
Sonnet 5 $0.00016 $0.01039
Haiku 4.5 $0.00008 $0.00520

Measured 11d ago against content hash 758e238ed51c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcp-core-best-practices scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/alibabacloud-core/skills/mcp-core-best-practices/SKILL.md · 425 lines

How it starts

The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Alibaba Cloud MCP Core Best Practices

This skill documents the canonical patterns for using the alibabacloud-core MCP server — the generalized OpenAPI MCP Server Core that covers all Alibaba Cloud APIs without requiring pre-selection of specific operations.

Available Tools

Tool Purpose
AlibabaCloud___SearchApis Natural language search for APIs matching a requirement
AlibabaCloud___CallCLI Execute a single CLI command remotely
AlibabaCloud___GetApiDefinition Get full API definition (params, response, errors) by product/version/name
AlibabaCloud___ListApis List all APIs for a product, optionally filtered
AlibabaCloud___ListProductRegions List regions where a product is available
AlibabaCloud___GenerateCLICommand Generate a CLI command from API definition + parameters
AlibabaCloud___ListProducts List all Alibaba Cloud products
AlibabaCloud___SearchDocuments Search Alibaba Cloud official documentation by keyword, with optional product/language/site filters
AlibabaCloud___GetDocument Get full Markdown content of a document by doc_id (preferred) or URL
AlibabaCloud___GetDocumentTree Browse a product's document directory tree to discover available docs
AlibabaCloud___GrepDocuments Search within a specific product's documents by keyword pattern
AlibabaCloud___RunScript Start a restricted Python task with structured Alibaba Cloud OpenAPI access
AlibabaCloud___GetTask Long-poll a RunScript task until approval, execution, or failure reaches a terminal state
AlibabaCloud___RunIaC Run Terraform / IaC (action=plan/apply/destroy) to provision or tear down a multi-resource stack; plan-before-apply, sync or async, HITL approval
AlibabaCloud___GetPresignedUrl Get a time-limited OSS presigned URL (default upload) + presignToken to feed RunIaC; no credentials exposed

Standard Workflow

1. API Discovery

When the target API is unknown, use AlibabaCloud___SearchApis with a natural language description of the requirement. Each query should be granular enough to map to a single API call.

Read the full file on GitHub · 425 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 425 lines · 78 tokens per session scan A 758e238ed51c

Subscribe to this mod's changes

mcp-core-best-practices is a skill published in the GitHub repository aliyun/alibabacloud-agent-toolkit (21 stars, last pushed today), licensed Apache-2.0. It adds 78 tokens to every session and 5,196 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

alibabacloud-ecs-windows-os-troubleshooting

Troubleshoot and repair Alibaba Cloud ECS Windows instances from inside the GuestOS or remotely via Cloud Assistant. Use whenever the user reports any Windows symptom or asks for a health check on an ECS Windows instance, even vague ones like "check this machine": boot failures (BSOD, black screen, boot loop, stuck at…

aliyun/alibabacloud-ecs-troubleshoot-skills · 215 tokens

alibabacloud-ecs-linux-os-troubleshooting

Troubleshoot an Alibaba Cloud ECS Linux OS. Use when a user needs to diagnose a specified ECS Linux instance, such as instance stuck in Starting, boot stuck, SSH/VNC/Workbench login failure, network issues, disk/FS issues, performance anomalies, suspected mining or hidden processes, crash/hang, clock drift, or…

aliyun/alibabacloud-ecs-troubleshoot-skills · 84 tokens

microsoft365-expert

Expert in Microsoft 365 ecosystem, Power Platform, SharePoint Online, Microsoft Teams, Graph API, and Microsoft 365 administration. Use when the user mentions Microsoft platforms, Office 365, productivity, cloud, the Power Platform, or SharePoint, or when the task involves Microsoft 365 Services, Power Platform, Graph…

personamanagmentlayer/pcl · 78 tokens

pipedream-workflows

Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.

oyi77/1ai-skills · 38 tokens

notebooklm-management

NotebookLM MCP server management - query notebooks, add from share links, handle auth, reset sessions. Use when working with Google NotebookLM notebooks for conversational research tasks.

PracticalSwan/agent-skills · 38 tokens

webrtc-livekit

Deploy LiveKit WebRTC SFU (docs.livekit.io — Apache-2.0 Go binary): livekit-server (SFU binary, YAML + env config), livekit-cli (admin + load-testing — create-token, load-test, room list, room join), livekit-egress (record/stream-out to HLS/MP4/RTMP), livekit-ingress (RTMP/WHIP/SRT/URL ingest), livekit-agents…

damionrashford/media-os · 243 tokens