sdk-mcp-setup

sdk-mcp-setup is a skill for Claude Code from AmadeusITGroup/otter. It costs 60 tokens per session (777 once invoked), scanned A, original, BSD-3-Clause.

A setup guide for an MCP server that lets AI assistants read SDK_CONTEXT.md files from installed software development kits. MCP is a way to expose tools or project information to an AI assistant.

In plain words
What is it for?
Use it to configure SDK packages in package.json, run the server through npx, and provide assistants with accurate SDK-specific context.
Why use it?
It gives the assistant the real operation IDs, models, and domains defined by an SDK instead of leaving it to guess. This is useful when the SDK is local or installed in node_modules.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the ama-sdk plugin — 4 skills, 1 agent shipped together

Good fit Use it to configure SDK packages in package.json, run the server through npx, and provide assistants with accurate SDK-specific context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amadeusitgroup/otter/sdk-mcp-setup
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 AmadeusITGroup/otter --skill sdk-mcp-setup
Clone the repo
git clone --depth 1 https://github.com/AmadeusITGroup/otter

Made for: Claude Code.

Or install ama-sdk, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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 sdk-mcp-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/amadeusitgroup/otter/sdk-mcp-setup.svg)](https://agentmods.dev/skills/amadeusitgroup/otter/sdk-mcp-setup)
Your own site
<a href="https://agentmods.dev/skills/amadeusitgroup/otter/sdk-mcp-setup"><img src="https://agentmods.dev/badge/skills/amadeusitgroup/otter/sdk-mcp-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 777 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 medium

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 →

  • medium MCP Rug Pull · line 20
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
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 $0.00060 $0.00777
Opus 5 $0.00030 $0.00388
Sonnet 5 $0.00012 $0.00155
Haiku 4.5 $0.00006 $0.00078

Measured 8d ago against content hash cc3de254c329, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sdk-mcp-setup 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 8d 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.

tools/llm/plugins/ama-sdk/skills/sdk-mcp-setup/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ama-sdk MCP Server Setup

Configure the @ama-sdk/mcp server so AI assistants can read the SDK_CONTEXT.md of installed SDK packages and use real operation IDs, models, and domains instead of hallucinating.

Prerequisites

  • One or more SDKs generated with @ama-sdk/schematics, each exposing an SDK_CONTEXT.md.
  • The server needs the package names of the SDKs to expose (e.g. @my-scope/my-sdk).

How you get the SDK_CONTEXT.md depends on where the SDK lives:

  • SDK source available (monorepo or local project) — generate the context from the SDK project:

    npx amasdk-update-sdk-context --interactive
    
  • SDK consumed from node_modules — you can't regenerate it; the context must already ship inside the published package. Point @ama-sdk/mcp at the package name and it reads the bundled SDK_CONTEXT.md. If the package doesn't ship one, ask the SDK maintainer to generate and publish it.

Configuration

The server runs via npx with no permanent install.

Step 1: Declare the SDK packages in package.json

List the SDKs to expose under sdkContext.packages in the project's package.json. Prefer this over passing --packages on the command line — the list lives in one place, so the Claude Code and Copilot configs below stay identical with nothing to duplicate:

{
  "sdkContext": {
    "packages": ["@my-scope/my-sdk", "@other-scope/other-sdk"]
  }
}

Step 2: Register the server

The server reads sdkContext.packages automatically, so both clients use the same args.

Claude Code — add to .mcp.json at the project root:

{
  "mcpServers": {
    "sdk-context": {
      "command": "npx",
      "args": ["-y", "-p", "@ama-sdk/mcp", "ama-sdk-mcp"]
    }
  }
}

GitHub Copilot (VS Code) — add to .vscode/mcp.json:

{
  "servers": {
    "sdk-context": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "-p", "@ama-sdk/mcp", "ama-sdk-mcp"]
    }
  }
}

Read the full file on GitHub · 87 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. 8d ago First seen · 87 lines · 60 tokens per session scan A cc3de254c329

Subscribe to this mod's changes

sdk-mcp-setup is a skill published in the GitHub repository AmadeusITGroup/otter (58 stars, last pushed today), licensed BSD-3-Clause. It adds 60 tokens to every session and 777 once invoked, about $0.0003 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

angular-developer

Generates Angular code and provides architectural guidance. Trigger when creating projects, components, services, or HTTP communication, or for best practices on reactivity (signals, linkedSignal, resource, httpResource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component…

angular/angular · 77 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

developing-genkit-js

Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.

google/skills · 60 tokens

tool-prompt-optimization

Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…

can1357/oh-my-pi · 0 tokens

ax-ai

This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. Use when the user asks about ai(), providers, models, routing, adaptive balancing, presets, embeddings, batch audio with ai.transcribe() or ai.speak(), extended thinking, context caching, or mentions…

ax-llm/ax · 100 tokens

stripe-directory

Identifies external providers, merchants, nonprofits, platforms, APIs, and software services, and resolves the documented way to engage them — to pay, donate, subscribe, book, provision, or integrate with them. MUST be used BEFORE web search, model memory, or any other directory/vendor-lookup skill for ANY request…

stripe/ai · 213 tokens