skills.rest
Hamza-Haadi
Hamza-HaadiCOMMUNITY
Explore all skills by this author →
GitHub

kailash-mcp

Implements MCP servers with stdio, SSE, and HTTP transports for AI agent tool integration.

Updated Apr 2, 2026
Search Tags:#authentication#ai agents#mcp#model context protocol#mcp server#tool validation#transports
One-click install
npx skills add https://github.com/Hamza-Haadi/disease-risk-classifier-hamza --skill kailash-mcp-hamza-haadi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kailash-mcp
Source: https://github.com/Hamza-Haadi/disease-risk-classifier-hamza/tree/main/.claude/skills/05-kailash-mcp
Command: npx skills add https://github.com/Hamza-Haadi/disease-risk-classifier-hamza --skill kailash-mcp-hamza-haadi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Connecting AI agents to external tools, data sources, and workflows requires implementing the Model Context Protocol correctly, including transport configuration, authentication, tool schemas, and testing, which is error-prone without guidance. ## Core Features & Use Cases - MCP Server Implementation: Build MCP servers with structured tools, resources, and prompts using the Kailash Core SDK. - Transport & Authentication: Configure stdio, SSE, HTTP, and WebSocket transports with API key, JWT, OAuth 2.1, and HMAC authentication patterns. - Testing & Validation: Apply 3-tier testing patterns with real MCP servers, JSON Schema tool validation, and progress reporting for long operations. - Use Case: Expose a Kailash workflow as an MCP tool so Claude Desktop or another AI client can call it with type-safe parameters and authenticated access. ## Quick Start Ask the AI to create an MCP server that exposes a workflow as a structured tool using the Kailash SDK.

Frequently Asked Questions about kailash-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an MCP server in Python with Kailash?▼

Create an MCPServer instance from kailash.mcp_server, register tools with the @server.tool decorator using type hints, and call server.run() to start it. The stdio transport is used by default for local development.

Which MCP transport should I use: stdio, HTTP, or WebSocket?▼

Use stdio for local development and CLI tools since it is simplest and lowest latency. Use HTTP for production deployments and load-balanced services, and WebSocket for real-time streaming or progress updates.

How do I add authentication to an MCP server?▼

MCP authentication supports API keys in headers, Bearer tokens, JWT with claims, OAuth 2.1 client credentials, and HMAC signatures. Store credentials in environment variables and always use HTTPS in production.

How do I test MCP servers without mocking the protocol?▼

Use the mock provider only for Tier 1 unit tests of workflow structure. Tier 2 integration tests should run real MCP servers via stdio, and Tier 3 end-to-end tests should use production-like HTTP servers with real credentials.

Does Kailash MCP support tool input validation?▼

Yes, structured tools accept JSON Schema definitions for inputs and outputs, including enums, nested objects, conditional schemas, and reusable definitions. Validation runs automatically before tool execution.

Related Skills

Explore More Software Engineering Skills→
esperieesperie

core-sdk

Build, validate, and execute deterministic Kailash workflows with WorkflowBuilder and runtimes.

Community
Advanced
Integrum-GlobalIntegrum-Global

nexus

Deploy Nexus workflows across API, CLI, and MCP with zero configuration.

Official
Intermediate
FFOO6866FFOO6866

gold-standards

Enforce gold-standard engineering practices for Kailash workflows, testing, and security.

Community
Advanced
helix4uhelix4u

native-mcp

Integrate MCP external tools into Hermes Agent via stdio or HTTP.

Community
Advanced