How do I install the saga mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

It reads `DB_PATH` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

Saga MCP Server

A Jira-like project tracker MCP server for AI agents. SQLite-backed, per-project scoped, with full hierarchy (Projects > Epics > Tasks > Subtasks)

Local serverstdio

What is the Saga MCP Server?

A Jira-like project tracker MCP server for AI agents. SQLite-backed, per-project scoped, with full hierarchy (Projects > Epics > Tasks > Subtasks), activity

The short version

Full hierarchy — Projects > Epics > Tasks > Subtasks
Task dependencies — Express sequencing with auto-block/unblock when deps are met
Comments — Threaded discussions on tasks — leave breadcrumbs across sessions
Templates — Reusable task sets with {variable} substitution
Dashboard — One tool call gives full overview with natural language summary
SQLite — Self-contained .tracker.db file per project — zero setup, no external database

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
tracker_init	Initialize tracker and create first project
tracker_next	What to work on next, with the reason and what is blocked
tracker_dashboard	Full project overview with natural language summary
project_create	Create a new project
project_list	List projects with completion stats
project_update	Update project (archive to soft-delete)
epic_create	Create an epic within a project
epic_list	List epics with task counts
epic_update	Update an epic
epic_archive	Archive/unarchive an epic, hiding it and its tasks from listings
task_create	Create a task with optional dependencies
task_list	List/filter tasks; follows a manual arrangement when one exists
task_get	Get task with subtasks, notes, comments, and dependencies
task_update	Update task (auto-logs, auto-blocks/unblocks)
task_batch_update	Update multiple tasks at once
task_reorder	Set the order of an epic's tasks
task_lock_description	Lock/unlock a description so agents can't rewrite it
task_delete	Remove a todo task (soft delete, restorable)
task_restore	Restore a removed task
subtask_create	Create subtask(s) — supports batch
subtask_update	Update title/status/position; depends_on and blocks set ordering
subtask_reorder	Set the order of a task's subtasks in one call
subtask_delete	Delete subtask(s) — supports batch
comment_add	Add a comment to a task (threaded discussion)
comment_list	List comments on a task (removed ones hidden unless include_deleted)
comment_delete	Remove a comment — soft delete, row kept for audit
comment_restore	Restore a removed comment
template_create	Create a reusable task template with {variable} placeholders
template_list	List templates; include_tasks shows what each one creates
template_update	Edit a template in place — name, description or tasks
template_apply	Apply template to create tasks with variable substitution
template_delete	Delete a template
note_save	Create or update a note (upsert)
note_list	List notes with filters
note_search	Full-text search across notes
note_delete	Delete a note
tracker_search	Cross-entity search (projects, epics, tasks, notes)
activity_log	View change history with filters
tracker_session_diff	What changed since a timestamp — call at session start
tracker_export	Export full project as nested JSON (includes dependencies and comments)
tracker_import	Import project from JSON (matching export format)

How to install the Saga MCP Server

{
  "mcpServers": {
    "saga": {
      "command": "npx",
      "args": [
        "-y",
        "saga-mcp"
      ],
      "env": {
        "DB_PATH": "/absolute/path/to/your/project/.tracker.db"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

Variable	Description	Required
DB_PATH	Declared in the maintainer’s client configuration.	Yes

Example prompts to try

“Use Saga MCP to Projects.”
“Use Saga MCP to Epics.”
“Use Saga MCP to Tasks.”

Frequently asked questions

A Jira-like project tracker MCP server for AI agents. SQLite-backed, per-project scoped, with full hierarchy (Projects > Epics > Tasks > Subtasks), activity Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.