Is the lean-agents MCP server actively maintained?

The lean-agents MCP server was last committed today and has 1 contributor. Issue health: 50% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

lean-agents MCP Server

Name: moxer-mmh/lean-agents
Rating: 3.0 (1 reviews)
Author: moxer-mmh

moxer-mmh/lean-agents

Score: 49.6 Rank #108 MCP Server

Are you the maintainer of moxer-mmh/lean-agents? Claim this listing →

Lightweight subagent replacements for Claude Code users with many MCP servers. Fixes 'prompt too long' errors.

Add AgentRank to Claude Code Discover and compare tools like moxer-mmh/lean-agents — your AI finds the right one automatically

Get API Access →

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

Overview

moxer-mmh/lean-agents is a MCP server. Lightweight subagent replacements for Claude Code users with many MCP servers. Fixes 'prompt too long' errors.

Ranked #108 out of 129 indexed tools.

Actively maintained with commits in the last week.

Ecosystem

No license

Score Breakdown

Stars 15% 1

1 stars → early stage

Freshness 25% today

Last commit today → actively maintained

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 0

Description Good

License None

Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

License low impact

Add an MIT or Apache-2.0 license to signal trust and enable adoption

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/badge/tool/moxer-mmh--lean-agents)](https://agentrank-ai.com/tool/moxer-mmh--lean-agents/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

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

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="moxer-mmh/lean-agents"></script>

Details

Stars: 1
Forks: 0
Open Issues: 0
Closed Issues: 0
Contributors: 1
Dependents: —
Language: —
License: —
Last Commit: today

Matched Queries

"mcp server""mcp-server"

From the README

# Lean Agents

Lightweight subagent replacements for Claude Code users with many MCP servers configured.

## Problem

When you have 10+ MCP servers configured (Supabase, PostHog, Playwright, GitHub, Slack, etc.), built-in subagents (Explore, Plan, general-purpose) fail with **"prompt is too long"** because they inherit all MCP tool schemas from the parent session. With 300+ tools, the schemas alone can exceed Sonnet's 200k context limit before the agent even starts.

See: [#37793](https://github.com/anthropics/claude-code/issues/37793), [#31623](https://github.com/anthropics/claude-code/issues/31623)

## Solution

This plugin provides lightweight agent replacements that use explicit `tools:` allowlists to try to reduce or avoid inheriting MCP tool schemas. This is a runtime-dependent workaround rather than a guaranteed fix (see [Limitations](#limitations)):

| Agent | Model | Tools | Use Instead Of |
|-------|-------|-------|----------------|
| `lean-explore` | Sonnet | Glob, Grep, Rea

Read full README on GitHub →