Skip to content
Agentmart
Submit a tool

Laviya Agent Skills

Laviya AI Orchestration MCP runtime for IDE and agent integrations.

Connector by kartegagithub · GitHub account verified by the MCP Registry

IndexedLicense unknownLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/kartegagithub-laviya-agent-skills

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Laviya AI Orchestration MCP runtime for IDE and agent integrations.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
5 read · 12 write · 1 delete
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Node.js package

Tools by what they do 18

Read from the source code; the running server may list different tools.

Read 5 · Look things up without changing anything.

  • laviya_diagnostics
  • laviya_get_local_work_status
  • laviya_get_my_work
  • laviya_help
  • laviya_list_projects

Write 12 · Create, change, send or run things.

  • laviya_add_task_comment
  • laviya_assign_task
  • laviya_complete_execution
  • laviya_complete_task_work
  • laviya_create_tasks
  • laviya_feed_task
  • laviya_report_token_usage
  • laviya_start_delivery_run
  • laviya_start_execution
  • laviya_start_task_work
  • laviya_update_task_description
  • laviya_upload_task_file

Delete 1 · Delete, drop, revoke or wipe things.

  • laviya_cancel_local_work

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • LAVIYA_API_KEY

Other settings (environment variables or headers).

  • LAVIYA_AGENT_UID
  • LAVIYA_BASE_URL
  • LAVIYA_GLOBAL_CONFIG_PATH
  • LAVIYA_LOG_LEVEL

Tools (18)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • laviya_add_task_commentAdd Task Comment

    Append self-managed agent work output to a task as a comment. Images in filePaths/fileIDs are shown inline in the comment, other files as links (files are also added to the task attachments).

  • laviya_assign_taskAssign Task

    Assign a Laviya task. Without assigneeEmails the task is assigned to you. Only users with PM permission (PM, Director or Admin) can assign other people; for others the call is rejected.

  • laviya_cancel_local_workCancel Local Workcan change or delete data

    Cancel an active local-direct run and its active execution leases.

  • laviya_complete_executionComplete Execution

    Submit one final output containing a canonical LAVIYA_RESULT. Laviya validates, evaluates, and routes the result server-side.

  • laviya_complete_task_workComplete Task Work

    Outside orchestration, finish the work started with laviya_start_task_work: Laviya records the measured time as AI effort, moves the task to Ready for deploy (or targetStatus) and adds the completion comment. Safe to retry for the same sessionID: steps already done are not repeated.

  • laviya_create_tasksCreate Approved Tasks

    Create Laviya tasks from a work list the user has explicitly approved and return taskID/customTaskID per referenceID. Only call after the user approved the exact list and the target project (projectID, chosen with laviya_list_projects); never call it from an orchestrated execution. All items are created together or none; resending the same list (same requestKey) returns the already created tasks instead of duplicating them.

  • laviya_diagnosticsLaviya Diagnosticsread-only

    Read secret-free runtime configuration and active lease diagnostics.

  • laviya_feed_taskFeed Task

    Feed a task into local-direct AI execution mode by TaskID. Backend creates or reuses a hidden single-step flow run for the task.

  • laviya_get_local_work_statusGet Local Work Statusread-only

    Read runtime status, last execution, and artifact counters for a local-direct run.

  • laviya_get_my_workGet My Workread-only

    Get the next eligible Laviya orchestration work item. Supports lite payload controls, run pinning, project defaults, and minified/filtered output shaping.

  • laviya_helpLaviya Helpread-only

    List Laviya MCP tools, explain what they do, and return valid example calls. Optionally filter by toolName.

  • laviya_list_projectsList Projectsread-only

    List the Laviya projects the api key owner can access (id, name, taskPrefix, spaceName), optionally filtered by name or task prefix. Use it to let the user choose by name which project laviya_create_tasks should create tasks in.

  • laviya_report_token_usageReport Token Usage

    Report measured token usage for the current execution. Runtime blocks empty reports and generates deterministic idempotency key.

  • laviya_start_delivery_runStart Delivery Run

    Outside orchestration, group existing Laviya tasks into a delivery run before working on them. Reuses your active run that already contains any of the tasks (adding the missing ones), otherwise creates a run. Pass the returned id as deliveryRunID to laviya_start_task_work.

  • laviya_start_executionStart Execution

    Start an execution lease in Laviya for the active work item. Also starts local lease refresh management.

Show 3 more tools
  • laviya_start_task_workStart Task Work

    Outside orchestration, start the server-measured AI working time on a Laviya task right before implementing it. Moves the task to the project's Processing status and adds it to a delivery run (deliveryRunID, else the task's active run, else a new one). Calling it again returns the open session and keeps the first start time. A new session uses one Agent Orchestration credit.

  • laviya_update_task_descriptionUpdate Task Description

    Add plain text and files to a Laviya task's description (mode append, default) or replace it (mode replace). Local filePaths are uploaded to the task attachments first; images are shown inline, other files as links.

  • laviya_upload_task_fileUpload Task File

    Upload a local file (screenshot, document, log, ...) to a Laviya task's attachments. Returns fileID, url and embedHtml; pass fileID to laviya_update_task_description or laviya_add_task_comment to show it there (images inline).

Signals

Stars
0
Forks
1
Open issues
0
Last commit
Oct 23, 2026 (6 days ago)
Last release
Oct 26, 2026 (4 days ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.kartegagithub/laviya-agent-skills
Version
0.1.29
Auth
API key
Packages
npm laviya-mcp-server
License
License unknown
Repository
github.com/kartegagithub/laviya-agent-skills
First seen
Oct 24, 2026
Last checked
Oct 26, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Laviya Agent Skills MCP server. Agent Mart. https://agentmart.dev/connectors/kartegagithub-laviya-agent-skills (last updated 2026-10-26)