io.github.renezander030/agentic-task-system

@reneza/ats-cli

MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads

9 204/wk 1 tool GitHub npm

No known CVEs

No license

Actively maintained

Last commit 7d ago

Works with most clients

Transport: stdio, sse, http

1 tool · ~52 tok

Grade A · 0.0% of 200K ctx

MCPpedia last refreshed this data 1d ago

Edit this pageView history

AI / ML

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "io-github-renezander030-agentic-task-system": {
      "args": [
        "-y",
        "@reneza/ats-cli"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-renezander030-agentic-task-system)](https://mcppedia.org/s/io-github-renezander030-agentic-task-system)

Read me

What io.github.renezander030/agentic-task-system does

ats is an MCP server and CLI that gives your AI agent memory and execution context from the task system you already use — TickTick, Taskmaster, Beads, or an Obsidian vault. It combines adapter-aware retrieval fused by Reciprocal Rank Fusion (RRF) with portable intent, exploration-to-execution promotion, goal hierarchy, typed task relationships, lifecycle validity, scoped access decisions, context assembly, an action ledger, and bounded task-state events. TickTick can add dense search through loc

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y '@reneza/ats-cli' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

88/100across 5 weighted dimensions

How we score →

0255075100

−12

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked @reneza/ats-cli against OSV.dev.

Inventory

Tools (1)

Click any tool to inspect its schema.

~52 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.renezander030/agentic-task-system safe to use?: io.github.renezander030/agentic-task-system has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.
How do I install io.github.renezander030/agentic-task-system?: io.github.renezander030/agentic-task-system supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.renezander030/agentic-task-system do?: io.github.renezander030/agentic-task-system provides 1 tool: Conventions. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.renezander030/agentic-task-system?: io.github.renezander030/agentic-task-system is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.renezander030/agentic-task-system actively maintained?: io.github.renezander030/agentic-task-system is actively maintained — last commit was 7 days ago. It has 9 GitHub stars.

Similar servers

Others in ai-ml

View all →

Sequential Thinking MCP Server96

Dynamic problem-solving through sequential thought chains

88.9k 1

Memory MCP Server96

Persistent memory using a knowledge graph

88.9k 5

Antigravity Workspace Template96

Workspace template + MCP server for Claude Code, Codex CLI, Cursor & Windsurf. Multi-agent knowledge engine (ag-refresh / ag-ask) that turns any codebase into a queryable AI assistant.

1.3k 2

LycheeMem96

Compact, efficient, and extensible long-term memory for LLM agents.

1.2k 3

MCP Security Weekly

Get CVE alerts and security updates for io.github.renezander030/agentic-task-system and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

What's new

v0.10.0 — partial-retrieval transparency (find returns degraded + warnings when a source or branch drops out, instead of silently serving a subset), optional reranking over the RRF pool (ats find --rerank), usage observability (ats usage: per-tool volume, latency, empty/degraded rates), near-duplicate and contradiction detection (ats dedup), and reactive OAuth token refresh (retry once on a 401).

v0.9.0 — reversible writes (ats undo / undo_write from a ledger before-image), forward/dangling links that back-resolve on target creation (add_task_link --allow-missing, resolve_task_links), Obsidian path-traversal hardening, and verified stdio config for Cursor, Windsurf, and OpenCode.

How it compares

Approach	Where memory lives	Upkeep	Retrieval
`CLAUDE.md` / memory files	markdown you re-edit by hand	manual, drifts	none — whole file injected every session
Vector-DB memory (mem0-style)	a new store only the agent sees	rots unless you keep feeding it	dense-only
Plain TickTick / Obsidian MCP	your task app	none	keyword or the app's native search
ATS	your task app	none — you curate it daily	hybrid retrieval + typed context, validity, provenance, audit

Approach

Where memory lives

Upkeep

Retrieval

CLAUDE.md / memory files

markdown you re-edit by hand

manual, drifts

none — whole file injected every session

Vector-DB memory (mem0-style)

a new store only the agent sees

rots unless you keep feeding it

dense-only

Plain TickTick / Obsidian MCP

your task app

none

keyword or the app's native search

ATS

your task app

none — you curate it daily

hybrid retrieval + typed context, validity, provenance, audit

Andrej Karpathy's LLM Wiki idea is right about the destination, wrong about the starting line: almost nobody's knowledge lives in clean markdown — it lives in the task app they've used for years. ATS closes that gap with pluggable storage adapters.

Frequently Asked Questions

Is io.github.renezander030/agentic-task-system safe to use?

io.github.renezander030/agentic-task-system has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.renezander030/agentic-task-system?

io.github.renezander030/agentic-task-system supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.renezander030/agentic-task-system do?

io.github.renezander030/agentic-task-system provides 1 tool: Conventions. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.renezander030/agentic-task-system?

io.github.renezander030/agentic-task-system is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.renezander030/agentic-task-system actively maintained?

io.github.renezander030/agentic-task-system is actively maintained — last commit was 7 days ago. It has 9 GitHub stars.

What's new

How it compares

Approach	Where memory lives	Upkeep	Retrieval
`CLAUDE.md` / memory files	markdown you re-edit by hand	manual, drifts	none — whole file injected every session
Vector-DB memory (mem0-style)	a new store only the agent sees	rots unless you keep feeding it	dense-only
Plain TickTick / Obsidian MCP	your task app	none	keyword or the app's native search
ATS	your task app	none — you curate it daily	hybrid retrieval + typed context, validity, provenance, audit

Approach

Where memory lives

Upkeep

Retrieval

CLAUDE.md / memory files

markdown you re-edit by hand

manual, drifts

none — whole file injected every session

Vector-DB memory (mem0-style)

a new store only the agent sees

rots unless you keep feeding it

dense-only

Plain TickTick / Obsidian MCP

your task app

none

keyword or the app's native search

ATS

your task app

none — you curate it daily

hybrid retrieval + typed context, validity, provenance, audit

io.github.renezander030/agentic-task-system

Install in your client