Saga — Project Tracker for AI Agents

A Jira-like project tracker MCP server for AI agents. SQLite-backed, per-project scoped, with full hierarchy and activity logging — so LLMs never lose track.

Category: Pending
Primary Subcategory: Project & Task Management Platforms

View in the Claude registry

Integration details

Description

Saga gives your AI assistant a structured SQLite database to track projects, epics, tasks, subtasks, notes, and decisions across sessions. No more scattered markdown files — one `tracker_dashboard` call gives full project context to resume work. **Key features:** - Full hierarchy: Projects > Epics > Tasks > Subtasks - Task dependencies: Express sequencing with auto-block/unblock - Comments: Threaded discussions on tasks for decision trails - 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 - Activity log: Every mutation is automatically tracked - Notes system: Decisions, context, meeting notes, blockers - Batch operations: Create multiple subtasks or update multiple tasks in one call - 31 focused tools with safety annotations - Import/export: Full project backup and migration as JSON

Integration type: Connector
Verification status: Verified connector
Platform: Claude
Category: Pending
Primary Subcategory: Project & Task Management Platforms
Secondary Subcategories: None listed
Brand: Unknown
Access: Unknown
First tracked: 2026-06-17
Tool count: 31
Geography: US

Claude Discoverability Score

Saga — Project Tracker for AI Agents isn’t discoverable through Claude’s Connector picker

It runs as a local Claude Desktop Extension, so Claude cannot surface or score it there today.

No spam. Unsubscribe any time.

What the current score measures

Claude showing a list of relevant Connectors in a conversation

Remote Connectors Claude can surface from the Connector picker.

How this score is measured

Primary Subcategory

Project & Task Management Platforms

View Category

Adobe Workfront5/100

AerionPending VerificationGet notified

AIOProductOSPending VerificationGet notified

Asana95/100

Astravue App15/100

—Saga — Project Tracker for AI AgentsLocal Extension · Not scored

Tools

31 tools agents can invoke

View change history with filters
Add a comment to a task (threaded discussion)
List comments on a task (soft-deleted ones hidden by default)
Create an epic within a project
List epics with task counts
Update an epic
Delete a note
List notes with filters
Create or update a note (upsert)
Full-text search across notes
Create a new project
List projects with completion stats
Update project (archive to soft-delete)
Create subtask(s) — supports batch
Delete subtask(s) — supports batch
Update a subtask; set depends_on or blocks for ordering
Update multiple tasks at once
Create a task with optional dependencies
Get task with subtasks, notes, comments, and dependencies
List/filter tasks with dependency info
Update task (auto-logs, auto-blocks/unblocks)
Apply template to create tasks with variable substitution
Create a reusable task template
Delete a template
List available templates
Full project overview with natural language summary
Export full project as nested JSON
Import project from JSON
Initialize tracker and create first project
Cross-entity search (projects, epics, tasks, notes)
Show what changed since a given timestamp

Saga — Project Tracker for AI Agents FAQ

How do I improve a Verified connector's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.