English Français العربية

io.github.kartegagithub/laviya-agent-skills

Official registry Developer tools

Laviya AI Orchestration MCP runtime for IDE and agent integrations.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package laviya-mcp-server
Claude Code 
claude mcp add laviya-agent-skills -e 'LAVIYA_API_KEY=<your laviya_api_key>' -e 'LAVIYA_BASE_URL=<LAVIYA_BASE_URL>' -e 'LAVIYA_AGENT_UID=<LAVIYA_AGENT_UID>' -e 'LAVIYA_LOG_LEVEL=<LAVIYA_LOG_LEVEL>' -e 'LAVIYA_GLOBAL_CONFIG_PATH=<LAVIYA_GLOBAL_CONFIG_PATH>' -- npx -y laviya-mcp-server@0.1.30
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "laviya-agent-skills": {
            "command": "npx",
            "args": [
                "-y",
                "laviya-mcp-server@0.1.30"
            ],
            "env": {
                "LAVIYA_API_KEY": "<your laviya_api_key>",
                "LAVIYA_BASE_URL": "<LAVIYA_BASE_URL>",
                "LAVIYA_AGENT_UID": "<LAVIYA_AGENT_UID>",
                "LAVIYA_LOG_LEVEL": "<LAVIYA_LOG_LEVEL>",
                "LAVIYA_GLOBAL_CONFIG_PATH": "<LAVIYA_GLOBAL_CONFIG_PATH>"
            }
        }
    }
}

Environment variables

  • LAVIYA_API_KEY required secret Laviya API key used for MCP runtime authentication.
  • LAVIYA_BASE_URL Optional base URL override for the Laviya API endpoint.
  • LAVIYA_AGENT_UID Optional agent UID override for execution orchestration.
  • LAVIYA_LOG_LEVEL Optional log level override (debug|info|warn|error).
  • LAVIYA_GLOBAL_CONFIG_PATH Optional path override for global runtime config (useful in sandboxed environments where home directory is not readable).

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Laviya Agent Skills
  2. Packages
  3. What Is Included
  4. Repository Structure
  5. Quick Start
  6. Installable Asset Package
  7. Documentation Index
  8. Runtime Overview

Laviya Agent Skills

Laviya Agent Skills is a repository of reusable orchestration assets for IDE and agent integrations. It provides a production-oriented MCP runtime, shared orchestration prompt assets, and client-specific artifacts for tools such as Cursor and Claude.

Packages

  • laviya-agent-skills: reusable prompt, rule, and skill asset bundle for Node-based tooling
  • laviya-mcp-server: stdio MCP runtime published from mcp/

What Is Included

  • core/: shared orchestration prompt assets
  • mcp/: TypeScript MCP runtime scaffold (laviya-mcp-server)
  • cursor/: Cursor rule artifacts
  • claude/: Claude skill artifacts (SKILL.md for orchestration, laviya-delivery-cycle/SKILL.md for the user-driven delivery cycle)
  • docs/: setup, npm publishing, and end-user onboarding guides

Repository Structure

laviya-agent-skills/
  core/
  mcp/
    src/
    examples/
    README.md
  cursor/
  claude/
  docs/
    Setup.md
    MCPServerPublish.md
    InstallationAndUsage.md

Quick Start

cd mcp
npm install
npm run typecheck
npm run build
npm run dev

Required environment variable:

  • LAVIYA_API_KEY

Installable Asset Package

Install the reusable asset bundle:

npm install laviya-agent-skills

Example usage:

import { assets, resolveAssetPath } from "laviya-agent-skills";
import { readFileSync } from "node:fs";

const cursorRule = readFileSync(assets.cursorRule, "utf8");
const orchestratorPrompt = readFileSync(resolveAssetPath("orchestratorSystemPrompt"), "utf8");

Documentation Index

  • Runtime architecture and implementation: mcp/README.md
  • Developer setup guide: docs/Setup.md
  • NPM publishing guide: docs/MCPServerPublish.md
  • End-user installation and usage: docs/InstallationAndUsage.md
  • Client-specific MCP setup (Codex, VS Code, Antigravity, Claude): docs/InstallationAndUsage.md

Runtime Overview

The MCP runtime follows a global-runtime plus project-local-config model:

  • machine-level runtime installation
  • repository-level project configuration (.laviya/project.json or .laviya.json)
  • runtime-enforced lifecycle mechanics (validation, retries, idempotency, and structured logging)

Current MCP tool set includes both orchestration and local-direct task feed flows:

  • laviya_help
  • laviya_feed_task
  • laviya_get_local_work_status
  • laviya_cancel_local_work
  • laviya_add_task_comment
  • laviya_list_projects
  • laviya_create_tasks
  • laviya_start_delivery_run
  • laviya_upload_task_file
  • laviya_update_task_description
  • laviya_assign_task
  • laviya_start_task_work
  • laviya_complete_task_work
  • laviya_get_my_work
  • laviya_start_execution
  • laviya_complete_execution
  • laviya_report_token_usage
  • laviya_diagnostics

All tools return API envelope JSON text in the shape: { HasFailed, Messages, Data }.

Work items may include a backend-defined ExecutionPolicy. Analysis and review policies are read-only: agents must not implement changes, and enforced policies require a truthful completion executionEvidence.

For full architecture details and file-level scaffolding, refer to mcp/README.md.

Frequently asked questions

What is io.github.kartegagithub/laviya-agent-skills?

Laviya AI Orchestration MCP runtime for IDE and agent integrations.

How do I install io.github.kartegagithub/laviya-agent-skills?

It runs on your machine. In Claude Code: claude mcp add laviya-agent-skills -e 'LAVIYA_API_KEY=<your laviya_api_key>' -e 'LAVIYA_BASE_URL=<LAVIYA_BASE_URL>' -e 'LAVIYA_AGENT_UID=<LAVIYA_AGENT_UID>' -e 'LAVIYA_LOG_LEVEL=<LAVIYA_LOG_LEVEL>' -e 'LAVIYA_GLOBAL_CONFIG_PATH=<LAVIYA_GLOBAL_CONFIG_PATH>' -- npx -y laviya-mcp-server@0.1.30. For other clients, paste the JSON configuration from this page into their MCP settings.

Does io.github.kartegagithub/laviya-agent-skills need an API key?

Yes. It expects LAVIYA_API_KEY, which you set in its configuration.

Is io.github.kartegagithub/laviya-agent-skills open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains io.github.kartegagithub/laviya-agent-skills?

It is published by kartegagithub. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.