Summary
A production-oriented MCP runtime that bridges Claude and Cursor with the Laviya AI orchestration platform. Exposes eight tools for task management and execution tracking: feed tasks, check work status, cancel jobs, add comments, retrieve your work queue, and report token usage. Operates on a global runtime with project-local config model using `.laviya/project.json` files in your repository. Ships with reusable prompt assets, Cursor rules, and Claude skills bundled in an npm package you can import directly. Useful when you need structured orchestration workflows with validation, retries, and idempotency guarantees built into your agent interactions. All responses come back as structured JSON envelopes with failure flags and message arrays.
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →
Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →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 toolinglaviya-mcp-server: stdio MCP runtime published frommcp/
What Is Included
core/: shared orchestration prompt assetsmcp/: TypeScript MCP runtime scaffold (laviya-mcp-server)cursor/: Cursor rule artifactsclaude/: Claude skill artifactsdocs/: 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.jsonor.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_helplaviya_feed_tasklaviya_get_local_work_statuslaviya_cancel_local_worklaviya_add_task_commentlaviya_get_my_worklaviya_start_executionlaviya_complete_executionlaviya_report_token_usagelaviya_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 matching completion executionEvidence and summary policyCompliance.
For full architecture details and file-level scaffolding, refer to mcp/README.md.
Featured
Keeps your Mac awake while Claude Code, Codex or Cursor works. Lets it sleep when they are done.
Try free for 7 days →Block distracting apps from your iPhone permanently without a 3rd party app. Free and open source.
Block now (100% free) →Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →Configuration
LAVIYA_API_KEY*secretLaviya API key used for MCP runtime authentication.
LAVIYA_BASE_URLOptional base URL override for the Laviya API endpoint.
LAVIYA_AGENT_UIDOptional agent UID override for execution orchestration.
LAVIYA_LOG_LEVELOptional log level override (debug|info|warn|error).
LAVIYA_GLOBAL_CONFIG_PATHOptional path override for global runtime config (useful in sandboxed environments where home directory is not readable).
Categories
Registryactive
Packagelaviya-mcp-server
TransportSTDIO
AuthRequired
UpdatedMay 6, 2026
