de en es ja ko ru zh

BotDuaChuot MCP

Name: BotDuaChuot MCP
Author: cornhub69-x

by cornhub69-x

Overview Schema Related Servers Score Discussions

Python

Local

BotDuaChuot Host MCP

一个极简 MCP 服务器，让 ChatGPT 可以直接操作你的机器，作用范围限定在 HOST_WORKSPACE_DIR 内。

本仓库有两个主要功能：

在主机上读取、写入、搜索文件并运行命令。
通过 duachuot_knowledge 提供操作指南以及机器上已安装工具的真实清单。

目录结构

app/
├── host/                 # File, command, policy and tool-inventory logic
├── geo/                  # Geo Engine (convert, geodesic, exif, reverse, timezone)
├── ops/                  # OPSEC gate
├── platform/             # OS/distro/arch/shell + tool resolution
├── tools/                # MCP adapters: health, host, knowledge, geo, probes, ops
├── config.py
├── mcp_server.py
└── main.py

knowledge/
├── WORKING_GUIDE.md
├── HOST_ENVIRONMENT.md
├── TOOL_CATALOG.json
├── GEO_PLAYBOOK.md
├── FORENSICS_PLAYBOOK.md
└── OSINT_PLAYBOOK.md

skills/
├── ctf-geo/
├── ctf-forensics-plus/
├── ctf-osint-plus/
└── ctf-stego-plus/

datasets/
└── landmarks.json

resources/
└── RESOURCE_MAP.json (generated from the host ctf-tools repo)
└── landmarks.json

install.sh
scripts/
├── install_basic.sh
├── install_cli.sh
├── uninstall_cli.sh
├── restart_server_only.sh
├── start_tunnel_server.sh
├── dev.sh
├── install_datasets.py
└── test.sh

Related MCP server: local-drive-mcp

安装

1. 一行命令安装（推荐）

curl -fsSL https://raw.githubusercontent.com/cornhub69-x/botduachuot_mcp/main/install.sh | bash

默认情况下，脚本会将 main 分支克隆到 ~/.botduachuot_mcp，创建 .venv，安装依赖，以 600 权限创建 .env，并将 CLI 链接到 ~/.local/bin/duachuot。重新运行同一命令会通过快进方式更新安装；如果工作树中有未提交的文件，安装程序会停止，以避免覆盖用户数据。

可以通过环境变量进行自定义：

curl -fsSL https://raw.githubusercontent.com/cornhub69-x/botduachuot_mcp/main/install.sh | \
  DUACHUOT_INSTALL_DIR="$HOME/apps/botduachuot_mcp" \
  DUACHUOT_BIN_DIR="$HOME/.local/bin" \
  DUACHUOT_BRANCH=main \
  bash

支持的变量：DUACHUOT_REPO_URL、DUACHUOT_INSTALL_DIR、DUACHUOT_BIN_DIR、DUACHUOT_BRANCH。DUACHUOT_SKIP_PIP_UPGRADE=true 只应在测试环境或已准备好软件包缓存的离线环境中使用。

2. 从本地仓库手动安装

cd botduachuot_mcp
./install.sh

scripts/install_basic.sh 为兼容性而保留，并直接转发到主安装程序。

3. 配置与安装后检查

确保 ~/.local/bin 在你的 PATH 中：

export PATH="$HOME/.local/bin:$PATH"

将此行添加到 ~/.bashrc 或 ~/.zshrc 中以跨会话保留。

在暴露服务之前配置 .env。默认模板要求进行身份验证：

REQUIRE_AUTH=true
GATEWAY_TOKEN=<secret-random-token>
HOST_WORKSPACE_DIR=/home/user

然后验证：

duachuot version
duachuot config validate
duachuot doctor

通过 Cloudflare Tunnel 运行

./run_mcp_tunnel.sh
./run_mcp_tunnel.sh --status
./run_mcp_tunnel.sh --url
./run_mcp_tunnel.sh --stop

连接器 URL 如下所示：

https://<random>.trycloudflare.com/mcp

Streamable HTTP 以无状态方式配置并直接返回 JSON。每个 ChatGPT 请求都是独立工作的：不需要 mcp-session-id，常规工具调用也不会保持 SSE 流。

MCP_JSON_RESPONSE=true
MCP_STATELESS_HTTP=true

REST API

REST API 与 MCP 服务器共享主机服务，并运行在同一服务器/隧道上。基础路径：

/api/v1

OpenAPI 文档：

/api/v1/openapi.json

主要端点：

方法	端点	用途
`GET`	`/api/v1/health`	服务器状态
`GET`	`/api/v1/capabilities`	工具、工作区与限制
`GET`	`/api/v1/files`	列出目录
`GET`	`/api/v1/files/content`	读取文本文件
`PUT`	`/api/v1/files/content`	创建或覆盖文件
`PATCH`	`/api/v1/files/content`	替换文件中的文本
`POST`	`/api/v1/files/append`	向文件追加内容
`POST`	`/api/v1/directories`	创建目录
`GET`	`/api/v1/search`	在工作区中搜索文本
`POST`	`/api/v1/commands/check`	检查命令
`POST`	`/api/v1/commands/run`	在主机上运行命令
`GET`	`/api/v1/knowledge`	读取指南与工具清单

当 REQUIRE_AUTH=true 时，使用以下任一请求头：

Authorization: Bearer <GATEWAY_TOKEN>
X-Gateway-Token: <GATEWAY_TOKEN>

示例：

BASE_URL="https://<tunnel>.trycloudflare.com"
TOKEN="<GATEWAY_TOKEN>"

curl -H "Authorization: Bearer $TOKEN" \
  "$BASE_URL/api/v1/files?path=GitHub"

curl -X PUT \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"path":"Workspace/demo.txt","content":"hello REST\n"}' \
  "$BASE_URL/api/v1/files/content"

curl -X POST \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"command":"git status --short","cwd":"GitHub/botduachuot_mcp"}' \
  "$BASE_URL/api/v1/commands/run"

MCP 工具

health_check
get_capabilities
duachuot_list_directory
duachuot_read_file
duachuot_write_file
duachuot_replace_in_file
duachuot_append_file
duachuot_make_directory
duachuot_search_text
duachuot_check_command
duachuot_run_command
duachuot_knowledge

duachuot_run_command 没有 approval="approved" 参数。策略完全由服务器端决定。

调查工具（取证 + OSINT + 地理）

BotDuaChuot 增加了 21 个专用调查工具，完全离线且确定性执行：

# Geo Engine (offline, no network required)
duachuot_geo_extract         # EXIF GPS, exiftool/exiv2 cross-check, DOP/HPE, timezone, landmarks
duachuot_geo_scan            # scan arbitrary text/logs/SRT/NMEA/MGRS/UTM for coordinates
duachuot_coord_convert       # DMS/decimal/UTM/MGRS + datum transform (WGS84/ED50/NAD27)
duachuot_geo_calc            # geodesic distance/bearing + uncertainty from DOP/HPE
duachuot_geo_reverse         # offline reverse geocoding (landmarks + country resolution)
duachuot_geo_verify          # conclude only with >= 2 independent facts; fewer -> BLOCKER
duachuot_geo_landmark_check  # radius check around a landmark
duachuot_timezone_at         # offline timezone/UTC offset from coordinates

# Probes
duachuot_media_probe         # file + exiftool JSON + ffprobe
duachuot_pcap_probe          # conversations/endpoints/DNS + GPS hints (NMEA, Wi-Fi probes)
duachuot_disk_probe          # fsstat + fls
duachuot_mem_probe           # Volatility 3 (info/pslist)
duachuot_stego_probe         # binwalk + steghide, WAV LSB detection, LSB/MP3 extraction
duachuot_ocr_probe           # tesseract + QR (zxing-cpp)
duachuot_win_probe           # SAM/SYSTEM hives, LNK, prefetch (pure-Python, Linux/Windows)

# OPSEC + platform
duachuot_ops_check           # blocks telemetry / attack tools / discovery while ctf-live / flags in commands
duachuot_ops_jitter          # human-like delay between network queries
duachuot_ops_redact          # redact secret/flag before writing logs
duachuot_platform            # probe OS/arch/distro/shell + tool availability (native/WSL/missing)
duachuot_plan                # generate an investigation plan by artifact type
duachuot_resource_lookup     # resolve a managed ctf-tools resource from RESOURCE_MAP.json

资源注册表：resources/RESOURCE_MAP.json 由 scripts/generate_resource_map.py 从主机上的 ctf-tools 仓库生成（技能、脚本、工具、bin 条目、笔记）。查询返回路径 + 调用模板 + 可用性；缺失的资源是 BLOCKER，绝不会静默回退。

完整剧本：knowledge/GEO_PLAYBOOK.md、knowledge/FORENSICS_PLAYBOOK.md、knowledge/OSINT_PLAYBOOK.md。捆绑技能：skills/ctf-geo、skills/ctf-forensics-plus、skills/ctf-osint-plus、skills/ctf-stego-plus。

OPSEC（CTF 期间强制要求）

默认 ctf-live：不进行公开来源查询（sherlock/maigret/whois/dnsrecon/搜索引擎），不对目标范围使用自动化攻击工具，不自动提交 flag——始终通过人工操作。
investigation 模式（OSINT_MODE=true）开启 OSINT 查询，范围限定为操作员指定的内容。
网络查询之间：等待 duachuot_ops_jitter()（800–3000 毫秒）。
每个坐标结论需要 >= 2 个独立事实（通过 duachuot_geo_verify 验证）。

`duachuot_knowledge`

duachuot_knowledge(section="overview")
duachuot_knowledge(section="guide")
duachuot_knowledge(section="tools", query="python", include_versions=true)
duachuot_knowledge(section="search", query="docker")

此工具读取 knowledge/ 中的文档，并将 TOOL_CATALOG.json 与机器实际的 PATH 进行匹配。

测试

./scripts/test.sh
./scripts/quality_gate.sh
./scripts/manual_test_installer.sh

manual_test_installer.sh 使用临时仓库和 /tmp 中的 HOME；它绝不会启动、停止或重启真实的 Cloudflare tunnel。

关键配置

HOST_WORKSPACE_DIR=/home/light
HOST_RESTRICT_TO_WORKSPACE=true
HOST_COMMAND_POLICY=guarded
MAX_TIMEOUT_SECONDS=60
MAX_OUTPUT_BYTES=500000
REQUIRE_AUTH=true
GATEWAY_TOKEN=<secret>

guarded 只是针对明显破坏性操作的保护层，并非沙箱。MCP 服务器以启动进程的用户的权限运行。

另见：docs/ARCHITECTURE.md 和 SECURITY.md。

`duachuot` CLI

仓库附带一个统一 CLI，用于操作桥接/隧道并调用 REST API，无需手写 curl。

安装可编辑入口点：

.venv/bin/python -m pip install -e . --no-deps

两种方式均可运行：

./bin/duachuot --help
.venv/bin/duachuot --help

本地操作组：

duachuot start
duachuot status
duachuot url
duachuot server restart   # restart the bridge only, keep the tunnel URL
duachuot restart --yes    # restart the tunnel too, URL may change
duachuot stop

REST API 组：

duachuot health
duachuot --public health
duachuot capabilities --tools
duachuot fs ls GitHub
duachuot fs cat GitHub/project/README.md --lines 1:40
duachuot fs write GitHub/demo.txt --text "hello"
printf 'next\n' | duachuot fs append GitHub/demo.txt --stdin
duachuot fs search FastMCP --path GitHub/botduachuot_mcp
duachuot cmd check 'git status --short'
duachuot cmd run 'git status --short' --cwd GitHub/botduachuot_mcp
duachuot knowledge tools --query python --versions

操作支持组：

duachuot logs server -n 100
duachuot logs follow server
duachuot config show
duachuot config validate
duachuot doctor
duachuot completion bash

每个命令都支持 --json。全局选项可以放在子命令之前或之后：

duachuot --public health --json
duachuot health --public --json

默认情况下，CLI 调用 http://127.0.0.1:<MCP_PORT> 上的本地 REST 端点。使用 --public 从 logs/tunnel_url.txt 获取当前 URL，或使用 --base-url 指向其他端点。

主要退出码：

0  success
1  operation failed
2  invalid arguments
3  cannot reach the server
4  authentication failed
5  blocked by policy
6  resource not found
7  timeout
8  conflict

对于 duachuot cmd run，当服务器在请求层面成功执行命令时，CLI 退出码会镜像该命令的真实退出码。

完整设计：docs/CLI_DESIGN_PLAN.md。

其他 CLI 文档：docs/CLI_MANUAL_TEST_PLAN.md 和 docs/CLI_IMPLEMENTATION_REPORT.md。

运维与恢复

统一质量门禁：

./scripts/quality_gate.sh
./scripts/quality_gate.sh --runtime
./scripts/quality_gate.sh --full

严格诊断与配置：

duachuot doctor --local-only
duachuot doctor --strict
duachuot config validate --strict

收集诊断信息（敏感配置已脱敏）：

./scripts/collect_diagnostics.sh

安装、仅桥接重启（保留隧道）、恢复、回滚以及生产检查清单详见 docs/OPERATIONS_RUNBOOK.md。

架构、安全与发布

运行时架构与边界：docs/ARCHITECTURE.md
安全模型与加固：SECURITY.md
运维、恢复与回滚：docs/OPERATIONS_RUNBOOK.md
发布检查清单：docs/RELEASE_CHECKLIST.md

GitHub Actions 在推送和拉取请求时运行质量门禁；Dependabot 跟踪 Python 和 GitHub Actions 依赖。

This server cannot be installed

license - not found

Not graded

quality - not tested

maintenance

How are these scores calculated?

Maintenance

–Maintainers

–Response time

–Release cycle

–Releases (12mo)

Commit activity

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

codex-web-bridge
File Systems Shell Access Version Control
truongvknnlthao-gif
A
license
Not graded
quality
C
maintenance
Local MCP server bridging ChatGPT Web to local tools for file, shell, git, test, and process management with secure policy controls.
Updated 2 months ago (2026-06-21 18:03 UTC)
MIT
local-drive-mcp
sofakingmc0804
A
license
Not graded
quality
C
maintenance
MCP server enabling ChatGPT to interact with local filesystem via controlled file operations like read, write, edit, and search, with configurable guardrails for safety.
Updated 8 days ago (2026-08-11 23:11 UTC)
MIT
Shared Credit Tool
File Systems Shell Access Version Control
Minglink
A
license
Not graded
quality
C
maintenance
Local MCP server enabling Codex and ChatGPT to read/write files, execute commands, manage processes, use Git, and inspect images on the user's machine with full privileges.
Updated 24 days ago (2026-07-27 18:52 UTC)
Apache 2.0
ChatGPT Local Terminal Plugin
Shell Access Command Line OS Automation
Angad-D
F
license
Not graded
quality
C
maintenance
An unofficial self-hosted MCP server that enables ChatGPT to run commands on your computer through a secure tunnel, manage processes, and work within a specified project directory.
Updated 14 days ago (2026-08-06 06:25 UTC)
1

View all related MCP servers

Related MCP Connectors

Kody
Personal assistant MCP server with search, execute, packages, jobs, secrets, and integrations.
mcp-server
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
Frenchie
OCR, transcription, file extraction, and image generation for AI agents via MCP.

View all MCP Connectors

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cornhub69-x/botduachuot_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server