activity_log
View the activity log showing what changed and when. Useful for understanding recent progress or reviewing what happened since the last session.
LABSCO SUMMARY
The plan an agent loses between sessions, kept in a file it can query.
The payoff is on day two: tracker_session_diff and tracker_dashboard let an agent open a session by asking what moved, rather than re-reading the repository and guessing. Dependencies are enforced rather than described — a task whose prerequisite is unfinished comes back blocked, and unblocks itself when that prerequisite is marked done.
What it is
A local task tracker exposed as 31 MCP tools. Projects, epics, tasks, subtasks, dependencies, comments and notes live in a single SQLite file in your project, and the agent writes to it as it works and reads it when it comes back.
What you get
- A real hierarchy — projects, epics, tasks, subtasks — instead of a TODO.md nobody updates
- Task dependencies that block and unblock themselves as prerequisites are marked done
- One dashboard call: stats, active epic, blocked and overdue tasks, recent activity, notes
- A session diff showing what changed since a timestamp, to open the next session with
- Comments kept in order on a task, so the reasoning survives the context window
- Notes typed as decision, context, meeting, technical, blocker, progress or release, and searchable by keyword
- Reusable task templates with {variable} placeholders, applied into any epic
- Epics and tasks scoped to a git branch, with branch="current" detecting the one you are on
- An activity log recording every change with its old and new value
- Batch calls: several subtasks created at once, several tasks updated at once
- Whole-project export and import as nested JSON, dependencies and comments included
Requirements
One environment variable, DB_PATH, holding an absolute path to the .tracker.db file — the file and its schema are created on first use. Runs over stdio through npx, on macOS, Windows or Linux. No account, no API key, no external service: the data stays in the SQLite file you named.
Setup effort
One command — npx -y saga-mcp
USE CASES
01
Picking up work you left three days ago
Ask what changed since the last session, then read the dashboard for the active epic and anything blocked or overdue.
02
Turning an agreed plan into tracked work
Create the epic, then the tasks with depends_on set, so the ones that must wait come back blocked instead of being started early.
03
Keeping the reasoning, not just the outcome
Leave a comment on the task as you go and save the decision as a note, both searchable later.
04
Running the same checklist on every feature
Save the steps once as a template with {variable} placeholders, then apply it into each new epic.
05
Working out where a half-finished feature stands
Pull one task with its subtasks, comments, notes and dependencies in a single call.
06
Moving a project to another machine
Export the whole tree as JSON and import it on the other side; dependencies and comments come with it.
31 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
comment_add
Add a comment to a task. Comments create a chronological discussion thread — useful for leaving breadcrumbs across sessions.
comment_list
List all comments on a task in chronological order.
epic_create
Create an epic within a project. Epics group related tasks into a feature or workstream. Pass branch to scope the epic to a git branch (use "current" to auto-detect).
epic_list
List epics for a project with task counts and completion stats. Optionally filter by status, priority, or branch. Pass branch="current" to auto-detect the active git branch; pass empty string to list only branch-agnostic epics.
epic_update
Update an epic. Pass only the fields you want to change. Set status to "cancelled" to soft-delete. Pass branch="current" to pin to the active branch, or empty string to clear.
note_delete
Delete a note by ID.
note_list
List notes with optional filters. Returns notes sorted by most recent first.
note_save
Create or update a note. Notes capture decisions, context, progress, meeting notes, blockers, technical details, or release info. If "id" is provided, updates the existing note; otherwise creates a new one.
note_search
Search across note titles and content by keyword.
project_create
Create a new project. Projects are the top-level container for all work.
project_list
List all projects with epic/task counts and completion percentages. Optionally filter by status.
project_update
Update a project. Pass only the fields you want to change. Set status to "archived" to soft-delete.
subtask_create
Create one or more subtasks (checklist items) for a task. Accepts a single title string or an array of title strings for batch creation.
subtask_delete
Delete one or more subtasks. Accepts a single ID or array of IDs.
subtask_update
Update a subtask title, status, or sort order.
task_batch_update
Update multiple tasks at once. Useful for changing status of several tasks (e.g., mark 3 tasks as done) or reassigning tasks.
task_create
Create a task within an epic. Tasks are the primary unit of work.
task_get
Get a single task with full details including all subtasks, related notes, comments, and dependencies.
task_list
List tasks with optional filters. If no epic_id given, lists across ALL epics. Includes subtask counts and dependency info. Pass branch="current" to restrict to tasks whose epic is scoped to the active git branch.
task_update
Update a task. Pass only fields to change. Status transitions are automatically logged in the activity log.
template_apply
Apply a template to create tasks in an epic. Replaces {variable} placeholders with provided values.
template_create
Create a reusable task template. Templates define a set of tasks that can be instantiated into any epic. Use {variable} placeholders for dynamic values.
template_delete
Delete a task template.
template_list
List all available task templates.
tracker_dashboard
Get a comprehensive project overview in a single call. Returns: project info, all epics with task counts, overall stats (total/done/blocked/in_progress), recent activity, and recent notes. This is the best first tool to call when starting work on a project. Pass branch="current" to scope the dashboard to the active git branch.
tracker_export
Export a full project as nested JSON. Includes all epics, tasks, subtasks, comments, dependencies, and related notes. Useful for backup, migration, or sharing.
tracker_import
Import a project from JSON (matching tracker_export format). Creates all entities with new IDs and remaps references. Uses a transaction for atomicity.
tracker_init
Initialize the tracker for a project. If the database is empty, creates a project with the given name. If a project already exists, returns its info.
tracker_search
Search across ALL entities (projects, epics, tasks, notes) by keyword. Returns categorized results. Pass branch="current" to restrict epic/task matches to the active git branch (projects and notes are not branch-scoped).
tracker_session_diff
Show what changed since a given timestamp. Returns aggregated summary with counts by action and entity type, plus highlights of key changes. Call this at the start of a session to understand what happened since the last one.
BEFORE YOU INSTALL
What to know first
Tools you get
31 tools when we connected.
Requires
- npx on PATH
- DB_PATH in your environment
Where it runs
Both documented clients run the server on your machine.
CONTEXT COST
Moderate Standing cost
Rated by the size of the 31 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y saga-mcpMCP Clients
Claude Code, Claude Desktop
JSON
{
"mcpServers": {
"saga": {
"command": "npx",
"args": [
"-y",
"saga-mcp"
],
"env": {
"DB_PATH": "<YOUR_PATH_TO_PROJECT>/.tracker.db"
}
}
}
}
