ellmos-servercommander-mcp
Alpha MCP server for server operations enabling deployment dry-runs, mail readiness diagnostics, access-log analysis, and HTTP health checks.
README
<p align="center"> <img src="https://raw.githubusercontent.com/ellmos-ai/.github/master/profile/logo-ellmos-servercommander.jpg" alt="ellmos ServerCommander MCP emblem" width="360"> </p>
ellmos-servercommander-mcp
Alpha MCP server for server operations: deployment dry-runs, mail status, access-log analysis, and HTTP health checks.
German README: README_de.md
Part of the ellmos-ai family.
Discoverability: Published on npm as ellmos-servercommander-mcp, described for MCP catalogs in server.json, and summarized for AI search/indexing in llms.txt.
Architecture Visualized
graph TD
Client[MCP Host: Claude / Cursor] <-->|stdio / JSON-RPC| NodeWrapper[Node.js Entrypoint]
NodeWrapper <-->|Spawn subprocess| PyServer[Python MCP Server]
subgraph Tools [ServerCommander Tools]
PyServer -->|sc_health_check| HTTP[HTTP/HTTPS Endpoint Check]
PyServer -->|sc_logs_analyze| Logs[Apache/Nginx Access Logs]
PyServer -->|sc_deploy / sc_deploy_status| Deploy[Dry-Run Manifest & SQLite History]
PyServer -->|sc_mail_*| Mail[IMAP/SMTP Safe Readiness Diagnostics]
end
subgraph Storage [Local Storage]
Deploy -->|Optional persist| SQLite[(SQLite Deploy History)]
Logs -->|Optional persist| JSONReports[(JSON Log Reports)]
end
Start Here
| Goal | Start with |
|---|---|
| Add ServerCommander to Claude Desktop, Claude Code, Cursor, or another MCP host | MCP Client Configuration |
| Check a public or internal HTTP endpoint before a deploy | sc_health_check |
| Inspect Apache/Nginx access logs for errors, bots, referrers, and suspicious paths | sc_logs_analyze |
| Build a dry-run deployment manifest before SFTP/SSH execution exists | sc_deploy and sc_deploy_status |
| Wire mail operations later without accidental sends today | sc_mail_list, sc_mail_read, sc_mail_send, sc_mail_search |
Status
- Transport: stdio via the Python MCP SDK
- Package status: public alpha package under
ellmos-ai - Current core: MCP tool listing, MCP tool dispatch, config loading, HTTP health checks, richer access-log analysis with optional persisted JSON reports, and optional local dry-run deployment history
- Safe alpha handlers:
sc_deploybuilds local SHA256 manifests, configuration diagnostics, and opt-in SQLite history records in dry-run mode;sc_mail_*reports protocol-specific IMAP/SMTP readiness without opening mail connections - i18n: localized MCP tool descriptions, input-schema field descriptions, and unknown-tool errors for
en,de,es,zh,ja,ruwith English fallback
Install
The npm package contains a Node wrapper that starts the Python server. You still need Python 3.10+ and the Python package mcp>=1.0.0.
Option 1: Install From npm
npm install -g ellmos-servercommander-mcp@alpha
ellmos-servercommander
Option 2: Install From Source
git clone https://github.com/ellmos-ai/ellmos-servercommander-mcp.git
cd ellmos-servercommander-mcp
$env:PYTHONIOENCODING = "utf-8"
python -m pip install -e ".[dev]"
python -m pytest -q
Avoid creating a .venv inside cloud-synced folders if your sync client locks files. If you need an isolated environment, create it outside that folder.
Start From Source
$env:PYTHONPATH = "src"
python -m servercommander.server
MCP Client Configuration
Global npm Install
{
"mcpServers": {
"servercommander": {
"command": "ellmos-servercommander"
}
}
}
Source Checkout
{
"mcpServers": {
"servercommander": {
"command": "python",
"args": ["-m", "servercommander.server"],
"env": {
"PYTHONPATH": "/absolute/path/to/ellmos-servercommander-mcp/src"
}
}
}
}
Replace /absolute/path/to/ellmos-servercommander-mcp with your local checkout path.
Server Configuration
Example: config/servercommander.example.toml
Default paths:
%USERPROFILE%\.servercommander\config.toml%USERPROFILE%\.config\servercommander\config.toml- override with
SERVERCOMMANDER_CONFIG
Language can be configured with [server].language, SERVERCOMMANDER_LANG, or SERVERCOMMANDER_LOCALE.
[server]
name = "ellmos-servercommander"
language = "en" # en, de, es, zh, ja, ru
[deploy]
persist_history = false
history_db = "~/.servercommander/deploy_history.db"
[logs]
default_format = "apache" # apache | nginx
persist_reports = false
reports_dir = "~/.servercommander/log_reports"
Secrets should be referenced through environment variables, for example $MAIL_PASSWORD or $SFTP_PASSWORD.
Tools
sc_health_check: checks HTTP endpoints and reports status code plus latency; malformed endpoint URLs are returned as failed checks, so one bad input does not abort a batchsc_logs_analyze: analyzes Apache/Nginx access logs from inline text or a local file, including status classes, bytes, referers, error paths, suspicious request markers, and optional JSON report persistence viapersist_reportsc_deploy: creates a deployment plan with a local SHA256 manifest and profile diagnostics, but does not upload yet; readiness checks required fields, manifestable local paths, and supported protocols before optionalrecord_history=true; nested symlinks are reported but excluded so a manifest cannot silently traverse beyond the selected release directorysc_deploy_status: shows configured deploy profiles, selected-profile diagnostics, and recent dry-run history from the local SQLite history databasesc_mail_list,sc_mail_read,sc_mail_send,sc_mail_search: safe alpha status responses with action-specific IMAP/SMTP readiness diagnostics and no mail connections by default. With[mail].execution_enabled = true,sc_mail_listruns a live, read-only IMAP reachability probe (connect + list folders) by reusing the canonicalmail-connectormodule — it does not reimplement an IMAP client; message-level read/search staymail-connector's domain, and SMTP send stays non-executing
Search And Disambiguation
ServerCommander is the ellmos operations MCP server for local-first server administration workflows. Use this repo when searching for:
- MCP server operations tools
- MCP deploy dry-run server
- MCP access log analyzer
- MCP HTTP health check tool
- local-first server management MCP
- Claude Code server operations MCP
- safe SFTP deployment planning MCP
It is not the GitHub MCP server, not a generic shell-command MCP server, not a hosting provider control panel, and not a production SFTP/IMAP executor yet. The current alpha surface is intentionally diagnostic and dry-run first.
ellmos-ai Ecosystem
This MCP server is part of the ellmos-ai ecosystem — AI infrastructure, MCP servers, and intelligent tools.
MCP Server Family
| Server | Tools | Focus | npm |
|---|---|---|---|
| FileCommander | 46 | Filesystem, process management, interactive sessions, cloud-lock-safe operations | ellmos-filecommander-mcp |
| CodeCommander | 22 | Code analysis, JSON repair, imports, diffs, regex | ellmos-codecommander-mcp |
| Clatcher | 12 | File repair, format conversion, batch operations | ellmos-clatcher-mcp |
| n8n Manager | 18 | n8n workflow management via AI assistants | n8n-manager-mcp |
| ControlCenter | 20 | MCP stack discovery, profile management, control plane | ellmos-controlcenter-mcp |
| Homebase | 45 | Local-first LLM memory, knowledge, state, routing, swarm orchestration | ellmos-homebase-mcp (alpha) |
| ServerCommander | 8 | Server operations: health checks, log analysis, deploy dry-runs, mail diagnostics | ellmos-servercommander-mcp (alpha) |
| Blender Use | 3 | Headless Blender asset QA and FBX reimport verification | ellmos-blender-use-mcp (alpha) |
| Open Compute | 10 | Model-agnostic computer use: capture, safety-gated actions, Windows UIA | open-compute-mcp (alpha) |
AI Infrastructure
| Project | Description |
|---|---|
| BACH | Local-first text-based OS for LLM agents — 113+ handlers, 550+ tools, SQLite memory |
| open-compute | Model-agnostic computer-use core powering Open Compute MCP |
| clutch | Provider-neutral LLM orchestration with auto-routing and budget tracking |
| rinnsal | Lightweight agent memory, connectors, and automation infrastructure |
| ellmos-stack | Self-hosted AI research stack (Ollama + n8n + Rinnsal + KnowledgeDigest) |
| MarbleRun | Autonomous agent chain framework for Claude Code |
| gardener | Minimalist database-driven LLM OS prototype (4 functions, 1 table) |
| ellmos-tests | Testing framework for LLM operating systems (7 dimensions) |
Desktop Software
Our partner organization open-bricks bundles AI-native desktop applications — a modern, open-source software suite built for the age of AI. Categories include file management, document tools, developer utilities, and more.
Development
$env:PYTHONIOENCODING = "utf-8"
$env:PYTHONDONTWRITEBYTECODE = "1"
python -m pytest -q
npm run smoke
npm pack --dry-run
Next useful step: add explicitly configured execution adapters for SFTP and IMAP/SMTP while keeping dry-run/status-only defaults.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。