Google PageRank for AI agents. 25,000+ tools indexed.

v3nividiv1ci/cit-mcp

Score: 54.2 Rank #35 MCP Server

Tree-structured context management for Claude Code via MCP server

Use v3nividiv1ci/cit-mcp in Claude Code Install AgentRank MCP — your AI finds the right tool automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

v3nividiv1ci/cit-mcp is a Python MCP server licensed under MIT. Tree-structured context management for Claude Code via MCP server

Ranked #35 out of 110 indexed tools.

Actively maintained with commits in the last week.

Ecosystem

Python MIT

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 2

2 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 MIT

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

Contributors medium impact

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

Dependents medium impact

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

Badge all embed codes →

AgentRank score for v3nividiv1ci/cit-mcp
[![AgentRank](https://agentrank-ai.com/api/badge/tool/v3nividiv1ci--cit-mcp)](https://agentrank-ai.com/tool/v3nividiv1ci--cit-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/v3nividiv1ci--cit-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/v3nividiv1ci--cit-mcp" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="v3nividiv1ci/cit-mcp"></script>

Matched Queries

"mcp server""mcp-server"

From the README

# cit — Context Information Tracker

Git-style conversation branching for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). [中文文档](docs/zh.md)

When you're deep in a conversation and hit an unfamiliar concept, open a branch to explore it. When you're done, squash it back — the parent branch gets a concise summary without the detour polluting its context.

```
main ●                         "Reading a PagedAttention paper"
└─ learn-mha ◈                 "How does Multi-Head Attention work?"
   └─ why-sqrt-dk ◈            "Why divide by √d_k?"
```

Each `squash` compresses an exploration into 1-3 sentences that bubble up to the parent. The parent sees only conclusions, not the journey.

## Setup

```bash
git clone https://github.com/v3nividiv1ci/cit-mcp.git && cd cit-mcp
./setup.sh
```

`setup.sh` handles everything:
- Creates Python venv and installs dependencies
- Registers the MCP server in `~/.claude.json`
- Registers session hooks in `~/.claude/settings.json`

Restart C
Read full README on GitHub →
Are you the maintainer of v3nividiv1ci/cit-mcp?

Claim this listing to add a tagline, mark deprecation status, and get a verified maintainer badge.

Claim this tool →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.