Is the Charles-mcp MCP server actively maintained?

The Charles-mcp MCP server was last committed 4mo ago and has 1 contributor. Issue health: 60% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

Charles-mcp MCP Server

Name: heizaheiza/Charles-mcp
Rating: 3.1 (1 reviews)
Author: heizaheiza

heizaheiza/Charles-mcp

Score: 52.3 ↑ 4.6% Rank #15230 MCP Server

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

Are you the maintainer of heizaheiza/Charles-mcp? Claim this listing →

Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts

Add AgentRank to Claude Code Discover and compare tools like heizaheiza/Charles-mcp — your AI finds the right one automatically

Get API Access →

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

Overview

heizaheiza/Charles-mcp is a Python MCP server licensed under MIT. Charles Proxy MCP server for AI agents with live capture, structured traffic analysis, and agent-friendly tool contracts Topics: ai-agent, charles-proxy, codex, developer-tools, mcp, openai, mcp-server, network-debugging.

Ranked #15230 out of 24846 indexed tools.

Ecosystem

Python MIT

ai-agentcharles-proxycodexdeveloper-toolsmcpopenaimcp-servernetwork-debugging

Score Breakdown

Stars 15% 320

320 stars → growing community

Freshness 25% 4mo ago

Last commit 4mo ago → stale

Issue Health 25% 60%

3/5 issues closed → decent issue management

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 35

Description Good

License MIT

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

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 128 days ago — a recent commit would boost your freshness score

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/v1/badge/heizaheiza--Charles-mcp)](https://agentrank-ai.com/tool/heizaheiza--Charles-mcp/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

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

Embed Widget docs →

HTML

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

Details

Stars: 320
Forks: 35
Open Issues: 2
Closed Issues: 3
Contributors: 1
Dependents: —
Language: Python
License: MIT
Last Commit: 4mo ago

Matched Queries

"mcp server""mcp-server"topic:mcptopic:mcp-server

From the README

# Charles MCP Server

[Docs](docs/README.md) | [Tool Contract](docs/contracts/tools.md) | [AGENTS](AGENTS.md) | [Agent Workflow Guide](docs/agent-workflows.md) | [English README](README.en.md)

> **仓库维护公告（2026-04-21）**  
> 本仓库的公开 Git 历史已于 2026-04-21 重新整理。如果你在该日期之前克隆过本仓库，请在继续贡献前重新克隆。不要从旧的本地克隆直接合并或推送，否则可能会把过期历史重新引入仓库。

Charles MCP Server 用于把 Charles Proxy 接入 MCP 客户端，让 agent 可以稳定地读取实时流量、分析历史录包，并在需要时再展开单条请求细节。

它解决的核心问题只有三个：

- 录制还在进行时，agent 也能持续读取当前 session 的增量流量
- live 与 history 统一走结构化分析，不再让 agent 直接消费原始抓包字典
- 默认使用 summary-first 输出，先看热点与摘要，再 drill-down 到单条 detail

## 本次更新方向（v3.0）

`v3.0` 的更新方向是：`charles-mcp` 的能力开始从“流量查看/筛选”向“逆向工程工作流”延伸。

- 在保留原有 live/history 分析能力的基础上，新增 reverse-analysis 工具链（导入、查询、解码、回放、签名候选分析、live 逆向会话）。
- 目标是让 agent 不只看到流量，还能围绕认证、签名、参数变异与可重放性，形成更完整的逆向分析闭环。

## 快速开始

### 1. 开启 Charles Web Interface

在 Charles 中依次进入：`Proxy -> Web Interface Settings`

请确认：

- 勾选 `Enable web interface`
- 用户名为 `admin`
- 密码为 `123456`

菜单位置示意：

设置窗口示意：

### 2. 安装并配置到 MCP 客户端

无需 clone 仓库，无需手动创

Read full README on GitHub →