← Back to Skills Marketplace
edwardirby

Integrate Claude Agent SDK with You.com MCP server

by Edward Irby · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
1842
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install ydc-claude-agent-sdk-integration
Description
Integrate Claude Agent SDK with You.com HTTP MCP server for Python and TypeScript. Use when developer mentions Claude Agent SDK, Anthropic Agent SDK, or integrating Claude with MCP tools.
Usage Guidance
This skill appears to do what it says (set up Claude + You.com MCP) and legitimately needs two API keys, but exercise caution because the registry metadata omitted those required env vars and there is no source or homepage listed. Before installing or running templates: 1) verify the package names and that they come from official registries (PyPI/NPM) and official maintainers; 2) prefer setting keys as environment variables rather than embedding them in code; 3) confirm the YDC and Anthropic key scopes and rotate keys used for testing; 4) review any downloaded packages' source code (or use a disposable/dev environment) before trusting in production; 5) ask the skill author for a source repository or homepage and an explicit list of required env vars/permissions — providing that would raise confidence and could change this assessment to benign.
Capability Analysis
Type: OpenClaw Skill Name: ydc-claude-agent-sdk-integration Version: 1.0.0 The skill bundle is designed to integrate the Claude Agent SDK with You.com's HTTP MCP server. It provides clear instructions and code templates for Python and TypeScript, guiding the user to install legitimate packages (`claude-agent-sdk`, `@anthropic-ai/claude-agent-sdk`) and configure API keys (`YDC_API_KEY`, `ANTHROPIC_API_KEY`) from environment variables. The `YDC_API_KEY` is used to authenticate with the intended service endpoint `https://api.you.com/mcp`. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution patterns, persistence mechanisms, obfuscation, or prompt injection attempts against the agent in the `SKILL.md` file. All actions are aligned with the stated purpose of SDK integration.
Capability Assessment
Purpose & Capability
The skill's templates and instructions (install claude-agent-sdk, configure an HTTP MCP server pointing at api.you.com, and use both YDC_API_KEY and ANTHROPIC_API_KEY) are coherent with the stated purpose of integrating Claude Agent SDK with You.com's MCP. However, the package/source provenance is missing (no homepage/source repo), which reduces trustworthiness.
Instruction Scope
SKILL.md stays within the integration scope: it instructs installing the SDK, creating/updating files, reading two environment variables (YDC_API_KEY and ANTHROPIC_API_KEY), and calling official endpoints (you.com and Anthropic). It doesn't instruct scraping unrelated files or exfiltrating arbitrary data.
Install Mechanism
This is an instruction-only skill (no install spec). The instructions reference normal package installs via pip/npm, which is expected for SDK integration. No downloads from arbitrary URLs or archive extraction are present.
Credentials
The runtime instructions require YDC_API_KEY and ANTHROPIC_API_KEY — which are reasonable for this integration — but the skill's registry metadata declares no required environment variables or primary credential. That metadata/instruction mismatch is a red flag because tools should declare the credentials they need. Also there is no explicit primaryEnv or explanation of minimal required scopes for the keys.
Persistence & Privilege
The skill does not request permanent presence (always:false), doesn't modify other skills' configs, and is instruction-only. It does not request elevated system privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ydc-claude-agent-sdk-integration
  3. After installation, invoke the skill by name or use /ydc-claude-agent-sdk-integration
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
ydc-claude-agent-sdk-integration 1.0.0 – Initial Release - Introduces an interactive workflow for integrating Claude Agent SDK with the You.com HTTP MCP server. - Supports both Python (3.10+) and TypeScript (v1: generator, v2: send/receive, TypeScript 5.2+). - Guides users to set up API keys, environment variables, and file structure for new or existing projects. - Provides ready-to-run template code for Python and TypeScript (v1/v2), including MCP server configuration. - Includes step-by-step prompts to ensure correct setup of Claude Agent SDK with You.com tool access. - MIT licensed and compatible with Node.js 18+ and modern Python/TypeScript versions.
Metadata
Slug ydc-claude-agent-sdk-integration
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Integrate Claude Agent SDK with You.com MCP server?

Integrate Claude Agent SDK with You.com HTTP MCP server for Python and TypeScript. Use when developer mentions Claude Agent SDK, Anthropic Agent SDK, or integrating Claude with MCP tools. It is an AI Agent Skill for Claude Code / OpenClaw, with 1842 downloads so far.

How do I install Integrate Claude Agent SDK with You.com MCP server?

Run "/install ydc-claude-agent-sdk-integration" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Integrate Claude Agent SDK with You.com MCP server free?

Yes, Integrate Claude Agent SDK with You.com MCP server is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Integrate Claude Agent SDK with You.com MCP server support?

Integrate Claude Agent SDK with You.com MCP server is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Integrate Claude Agent SDK with You.com MCP server?

It is built and maintained by Edward Irby (@edwardirby); the current version is v1.0.0.

💬 Comments