Is the ai-toolkit MCP server actively maintained?

The ai-toolkit MCP server was last committed 1mo ago and has 3 contributors. Issue health: 50% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

ai-toolkit MCP Server

Name: softspark/ai-toolkit
Rating: 3.7 (1 reviews)
Author: softspark

softspark/ai-toolkit

Score: 68.0 Rank #4492 Agent Framework

[![AgentRank](https://agentrank-ai.com/api/v1/badge/softspark--ai-toolkit)](https://agentrank-ai.com/tool/softspark--ai-toolkit/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

Are you the maintainer of softspark/ai-toolkit? Claim this listing →

Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode).

Add AgentRank to Claude Code Discover and compare tools like softspark/ai-toolkit — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

softspark/ai-toolkit is a Python tool licensed under Apache-2.0. Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI, opencode). Topics: ai-agents, ai-skills, anthropic, claude, claude-code, cline, codex, copilot, cursor, gemini, mcp, opencode, toolkit, windsurf.

Ranked #4492 out of 24846 indexed tools.

Ecosystem

Python Apache-2.0 30 pypi/wk

ai-agentsai-skillsanthropicclaudeclaude-codeclinecodexcopilotcursorgeminimcpopencodetoolkitwindsurf

Score Breakdown

Stars 15% 180

180 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 50%

1/2 issues closed → decent issue management

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads 13% 30/wk

30 weekly installs → early adoption

Forks 21

Description Detailed

License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 32 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/v1/badge/softspark--ai-toolkit)](https://agentrank-ai.com/tool/softspark--ai-toolkit/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/softspark--ai-toolkit/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/softspark--ai-toolkit" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="softspark/ai-toolkit"></script>

Details

Stars: 180
Forks: 21
Open Issues: 1
Closed Issues: 1
Contributors: 3
Dependents: —
Language: Python
License: Apache-2.0
Last Commit: 1mo ago

Matched Queries

topic:mcp

From the README

# ai-toolkit

> AI coding toolkit with machine-enforced safety, 116 skills, 44 agents, lifecycle hooks, persona presets, opt-in plugin packs, and benchmark tooling.

## What's New in v5.3.5

- **No orphaned `## Project Constitution` heading.** It now leaves `CLAUDE.md`
  together with its import; `update` removes one an older release left, and
  `adopt-agents-md` no longer keeps it.
- **`update` names projects with instructions only in `CLAUDE.md` (v5.3.4).** Agents
  other than Claude Code do not read that file; the list ends the update with
  the `ai-toolkit adopt-agents-md` fix. An untouched older template is now
  recognized and moved to `AGENTS.md`.
- **Current models (v5.3.4).** Skills and defaults reference Claude Haiku 5.5 and
  Sonnet 5.5, and the Codex reference adds GPT-6.1 Sol.
- **The npm package no longer ships an `AGENTS.md` (v5.3.3).** It was the toolkit's
  generated core, which nothing in the package read; `ai-toolkit agents-md`
  still prints it. This repository now

Read full README on GitHub →