How do I use system-monitor?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@system-monitor show me current CPU and memory usage" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

system-monitor

by 2428424081cn

Overview Schema Source Related Servers Score Discussions Admin

TypeScript

🛡️ System Status & Config MCP Server (Agentic AIOps)

License Node TypeScript Platform

The ultimate "eyes and ears" for your AI assistants. Give LLMs (like Claude, Cursor, or your autonomous agents) safe, read-only, and token-optimized access to your server's physical reality.

🌟 Why This Exists?

Large Language Models (LLMs) possess vast knowledge of system administration, architecture, and debugging. However, they suffer from a "reality gap" — they know how to fix an OOM error, but they don't know your server's RAM usage, your active configuration paths, or your current logs.

If you give an AI raw shell access (bash), it is extremely dangerous (e.g., accidental rm -rf or crashing the server by catting a 50GB log file).

This MCP (Model Context Protocol) Server solves this by acting as a Secure, Read-Only Abstraction Layer. It empowers AI to perform sub-second, cross-platform infrastructure audits and root-cause analysis without risking system integrity.

Related MCP server: GhostInTheShell MCP

🚀 Core Features

1. 📊 High-Concurrency System Probes (`get_system_status`)

Gathers real-time OS metrics across 17 distinct categories (CPU, Memory, Docker, Network, Processes, Windows WMI internals, etc.).

Smart Concurrency: Windows WMI/CIM queries are executed in parallel (Promise.all), reducing response times from seconds to ~200ms.
Cross-Platform: Normalizes complex metrics across Linux, macOS, and Windows into clean JSON.

2. 🔍 Intelligent Config Radar (`discover_configs`)

AI doesn't need to guess where your config files are.

Auto-locates 36+ well-known services (Nginx, Redis, SSH, WSL, VSCode, Git, etc.).
Directory Sniffing: Point it to a project directory (directory: "/path/to/project"), and it will automatically detect hidden . files and configuration extensions (.yaml, .ini, .env).

3. 🧠 Token-Optimized Config Reader (`read_config`)

Reads and parses structured configurations (JSON, YAML, INI, TOML, etc.).

keys-only Mode: Designed specifically for LLMs. If an AI needs to read a massive package-lock.json, this mode strips out heavy values and returns only the structural schema (e.g., replacing arrays with [Array of 8 items]), saving tens of thousands of tokens while preserving context.

4. 🛡️ Safe Log Tailing (`read_log`)

A purpose-built, high-performance log analyzer.

Reverse Chunk Reading: Directly reads 64KB chunks from the end of the file backwards. Never loads the entire file into memory (OOM-safe).
Native Grep: Search for keywords (e.g., grep: "ERROR") across massive log files.
Circuit Breakers: Hard-capped at 1000 lines and a 10MB backwards-search limit to protect the Node.js event loop during high CPU loads.

🛠️ Installation & Setup

Prerequisites

Node.js >= 18.x
TypeScript installed globally or locally

Build from source

# Clone the repository
git clone https://github.com/yourusername/system-status-mcp.git
cd system-status-mcp

# Install dependencies
npm install

# Build the project
npm run build

Usage with Claude Desktop

Add the following configuration to your Claude Desktop claude_desktop_config.json:

Windows (%APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "system-monitor": {
      "command": "node",
      "args": ["D:/Project/MCP/status/dist/index.js"]
    }
  }
}

macOS/Linux (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "system-monitor": {
      "command": "node",
      "args": ["/path/to/system-status-mcp/dist/index.js"]
    }
  }
}

🧰 Available MCP Tools

Tool Name	Description	Key Arguments
`get_system_status`	Retrieve system metrics.	`category` ("all", "performance", "docker", "windows", etc.)
`discover_configs`	Scan for known configs or project dotfiles.	`service` (filter by name), `directory` (scan a specific folder)
`read_config`	Parse a specific config file.	`path`, `service`, `compactMode` ("none", "keys-only")
`read_log`	Safely tail and grep massive log files.	`path`, `lines` (default 100), `grep` (optional filter)

🏗️ Architecture & Safety Highlights

Embedded Error Reporting: Instead of failing silently or returning 500 Internal Error, the server captures explicit filesystem errors (EACCES, ENOENT) and PowerShell timeouts, embedding them directly into the JSON response (e.g., { "_error": "Permission denied" }). This allows the AI to autonomously adjust its strategy (e.g., asking the user for sudo privileges).
Graceful Timeouts: All heavy subprocess executions (like Windows WMI) are strictly timed out at 15 seconds. If the CPU is pegged at 99%, the MCP server will gracefully report timeout failures rather than hanging the AI indefinitely.

Built for the Agentic Era. Open-sourced under the ISC License.

Available Tools

4 tools

discover_configsA

Scan the system for known service configuration files (nginx, mysql, redis, docker, sshd, etc.), or scan a specific directory for project-level config files (like .env, .npmrc, *.json). Returns a list of detected config files with their paths, sizes, and last modified times.

ParametersJSON Schema

Name	Required	Description	Default
`service`	No	Optional. Filter by service name (e.g. 'nginx', 'mysql', 'redis', 'docker', 'sshd').
`directory`	No	Optional. Provide an absolute path to a directory (e.g. a project folder) to scan for local configs.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the behavioral burden. It tells the user what it returns (paths, sizes, last modified times) which is useful output transparency. However, it doesn't disclose scan depth, performance implications of scanning a large directory, permission requirements, or whether scanning could interfere with systems. For an apparently read-only discovery tool, this is reasonable but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the primary action and then covers secondary details. It's efficient with no wasted words, listing specific example services and file types that aid comprehension. Slightly long but each clause contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a discovery tool with no output schema and no annotations, the description adequately conveys the return value (list with paths, sizes, modified times). Given the tool's moderate complexity (two optional, mutually-exclusive parameters), the description covers the essential context: what it scans, what it returns, and the two operational modes. It could mention parameter exclusivity, but that's a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters ('service' and 'directory') already having descriptions in the schema. The description adds the complementary context that 'service' covers known system services like nginx/mysql/redis while 'directory' covers project-level configs like .env/.npmrc/*.json. This adds modest value beyond the schema but doesn't deeply extend parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Scan') with a clear resource ('system for known service configuration files') and distinguishes two scanning modes (system-wide services vs. directory for project-level configs). It clearly differentiates from siblings like read_config (which reads a config, not discovers them) and read_log (log reading). The purpose is unambiguous and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly explains the two use cases: scanning system-wide for known service configs, or scanning a specific directory for project-level configs. While it doesn't explicitly state when NOT to use it or name sibling alternatives, the distinction between system-level and project-level scanning provides clear context for choosing parameters. It lacks explicit exclusions but the intent is well conveyed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_system_statusA

Get comprehensive system status for production server monitoring. Covers performance metrics, hardware specs, software environment, storage & disk I/O, network traffic & connections, running processes, systemd services, Docker containers, CPU/GPU temperatures, logged-in users, security posture (open ports), displays, battery, and peripherals. Use 'overview' for a quick health snapshot, or specify a category for deep details.

ParametersJSON Schema

Name	Required	Description	Default
`category`	No	Category to query. 'all' returns everything (slow). 'overview' returns a lightweight server health snapshot (recommended for quick checks). 'windows' returns Windows-specific details (version, build, optional features, virtual memory, activation). Other options: performance, hardware, software, storage, network, processes, services, docker, temperature, users, security, displays, battery, peripherals, windows.

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It does disclose that 'all' returns everything but is slow (a performance/weight trait), and recommends 'overview' for lightweight checks. This gives the agent useful behavioral context about response weight and speed tradeoffs, though it doesn't disclose error conditions or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense, well-organized paragraph that front-loads the core purpose, lists covered areas efficiently, and closes with actionable usage guidance. No wasted words or redundancy with the schema. The coverage list is long but earns its place given the tool spans 17 categories.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite a complex tool covering 17 categories, the description adequately conveys the scope, distinguishes the overview shortcut, warns about the 'all' performance cost, and covers the Windows-specific case. With a 100% documented schema and 0 required params, the description is complete enough for an agent to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 17 enum options with descriptions. The description adds the practical recommendation hierarchy (overview > all for speed), which slightly exceeds the schema. Baseline 3 is appropriate since the schema already does the heavy lifting, and the description adds limited additional meaning beyond the performance note.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get comprehensive system status for production server monitoring' with a specific verb+resource. It lists 15+ specific content areas (performance metrics, hardware specs, networking, processes, etc.) which thoroughly distinguishes it from siblings like read_config and read_log. Very specific and comprehensive purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides usage guidance: 'Use 'overview' for a quick health snapshot, or specify a category for deep details.' It also flags 'all' as slow, telling the agent to prefer overview for quick checks. This is clear when-to-use guidance differentiated by category, and the sibling names (config/log tools) imply this is the operational-status tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_configA

Read and parse a specific service configuration file. Supports JSON, YAML, INI, TOML, env, nginx conf, sshd_config, sysctl, crontab, hosts, fstab, resolv.conf, and more. You can specify either a service name (e.g. 'nginx') to auto-locate the config, or provide a direct file path for custom configs.

ParametersJSON Schema

Name	Required	Description
`path`	No	Direct absolute path to a config file. Use this for custom configs not in the known list. If both 'service' and 'path' are provided, 'path' takes priority.
`format`	No	Optional format hint. If omitted, the format is auto-detected from the file extension. Use 'raw' to get unprocessed file content.
`service`	No	Service name to read config for (e.g. 'nginx', 'mysql', 'redis', 'sshd', 'docker', 'hosts', 'fstab'). The tool will auto-locate the config file. Available services: nginx, apache, caddy, traefik, haproxy, mysql, postgresql, redis, mongodb, elasticsearch, rabbitmq, memcached, docker, docker-compose, containerd, kubernetes-kubelet, sshd, ssh-client, fail2ban, ufw, sysctl, fstab, hosts, resolv, crontab, logrotate, limits, supervisord, pm2, php-fpm, gunicorn, prometheus, grafana, rsyslog, bind, wsl, windows-terminal, vscode, npm, ssh-user, bash-profile
`maxSizeKB`	No	Maximum file size to read in KB. Default: 512. Increase for large configs.
`compactMode`	No	Optional token-saving mode. Use 'keys-only' for huge JSON/YAML files to only return the schema/structure without all the values. Great for AI context saving.

TDQS

A4.1/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses the parsing capability and the priority rule (path over service), and mentions file size limits via parameters. However, it doesn't disclose what happens on parse failure, permissions errors, or how auto-location resolves ambiguous service matches. It also doesn't mention that this is a read-only operation explicitly, though it's implied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single tight paragraph, front-loaded with the core action. It's concise but dense with useful info. It could mention sibling distinctions explicitly, but it's not bloated. The service list is quite long (leaning on schema) but that's in the schema already.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is moderately complex with 5 params and many format/service options, but schema coverage is 100% and the description adds the parsing formats, dual usage modes, and priority rule. No output schema exists, but for a read/parse tool the return value can be reasonably inferred. Auto-detection behavior from file extension is mentioned in the format param schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with rich descriptions for each parameter. The description adds complementary context by naming example service names and format scenarios beyond the schema. The compactMode parameter ('keys-only') is contextualized as 'AI context saving' which adds useful intent. The description adds the priority ordering between service and path which isn't in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads and parses config files, lists many supported formats, and distinguishes between service-name auto-location vs direct file path. It clearly differentiates from sibling tools like read_log and discover_configs by specifying it's about config files with parsing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains two usage modes (service name auto-locate vs direct path) and notes path takes priority when both are given. It gives concrete examples like 'nginx'. However, it doesn't explicitly state when NOT to use this for alternatives, though siblings are clearly different (read_log, discover_configs, get_system_status).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_logA

Safely read the end of a log file (tail), optionally filtering by a keyword (grep). Extremely efficient for huge log files as it reads backwards from the end without loading the whole file into memory. Use this instead of read_config for files like /var/log/syslog, nginx access logs, or any file that could be massive.

ParametersJSON Schema

Name	Required	Description
`grep`	No	Optional keyword to filter lines. Only lines containing this keyword (case-insensitive) will be returned.
`path`	Yes	Absolute path to the log file (e.g. '/var/log/syslog', 'C:\logs\error.log').
`lines`	No	Number of lines to read from the end. Default is 100. Max is 1000.

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden, and it does well: discloses the efficiency trait ('reads backwards from the end without loading the whole file into memory'), the case-insensitive grep behavior is implied, and it flags the tool as safe ('Safely'). It doesn't disclose much about return format or error behavior, but the described caching/efficiency benefit is genuinely useful behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: the first states function, the second explains efficiency/behavior, the third gives concrete use guidance. Well front-loaded with the primary purpose in the first clause and no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-param read tool with 100% schema coverage and clear sibling differentiation, the description is complete. It covers purpose, use cases, alternatives, and performance characteristics. No output schema exists, but the tool's return (filtered tail lines) is self-evident from the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for all 3 parameters (path, lines, grep), so the baseline is 3. The description adds context about the grep being case-insensitive (echoed in schema) and the tail-backwards behavior, but doesn't add substantial new parameter meaning beyond what the schema already documents. No major compensation needed since coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool does tail+grep on log files, with specific verb ('read the end'), resource ('log file'), and mode ('tail', optionally 'grep'). It also explicitly distinguishes from siblings by naming read_config and explaining when NOT to use it, which differentiates it from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('Use this instead of read_config for files like /var/log/syslog, nginx access logs') and names the alternative tool (read_config), establishing clear boundary conditions. The guidance about 'any file that could be massive' provides practical selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

4 tool updatesv1.0.0Aug 4, 2026
- First observeddiscover_configs
- First observedget_system_status
- First observedread_config
- First observedread_log

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Scored 2026-08-04 01:40 across 4 tools

Disambiguation4/5

The four tools are mostly distinct: status monitoring, config discovery, config reading, and log reading. However, read_config and read_log could cause confusion (both deal with reading files), and discover_configs could be seen as overlapping with read_config since both touch config files. The descriptions clarify boundaries well, but the similar purposes create minor ambiguity.

Naming Consistency4/5

Tools follow a mostly consistent verb_noun pattern (get_system_status, discover_configs, read_config, read_log). All use snake_case with imperative verbs. The inconsistency is that get_system_status uses a 3-word name while others use 2-word names, and 'discover' vs 'read' vs 'get' are slightly different verb styles for similar actions.

Tool Count4/5

Four tools is on the lower end but reasonable for a focused system-monitoring server. It covers status, config discovery, config reading, and log reading - a coherent but slightly thin set. One or two more tools (e.g., executing commands, managing services) could round out the surface.

Completeness3/5

The server covers monitoring (status), config exploration (discover/read configs), and log inspection (read_log). However, it lacks write-capabilities entirely - there's no way to modify configs, restart services, or send commands, which feels like a notable gap for a system-monitor. Additionally, there's no tool for managing processes or services beyond reading, only observing them.

Maintenance

ActivitySlowing

ResponsivenessNo issues

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 Connectors

turva-mcp A
dev.turva
Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.
Autonomous Agents Developer Tools Security
52
ambiscribe
io.ambiscribe
Read-only MCP access to a documented IT fleet: state, changes, posture. 15 tools.
Monitoring Observability Security
2
secureflows-mcp A
io.github.michal-lefler
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
Code Analysis Developer Tools Security
181
MCP FortressOAuth
io.github.mcp-fortress
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Security Testing & QA Tools Penetration Testing
2

Related MCP Servers

aegis
Security Code Analysis Penetration Testing
cognis-digital
F
license
Not graded
quality
C
maintenance
MCP server for auditing AI agent permissions and access by scanning for the trifecta of credentials, injection, and reach without heavy infrastructure.
Updated 13 days ago (2026-08-29 10:45 UTC)
-
GhostInTheShell MCP
Monitoring Observability Shell Access
pronzzz
A
license
Not graded
quality
D
maintenance
A sandboxed, read-only MCP server that safely exposes system metrics, container diagnostics, and logs to AI agents with intelligent context compression and strict security measures.
Updated 7 months ago (2026-02-20 20:24 UTC)
MIT
mcp-infra-readonly
Observability Monitoring Networking & Infrastructure
senseicoder
F
license
Not graded
quality
B
maintenance
A read-only MCP server that gives Claude Code secure, non-invasive access to infrastructure logs, service status, metrics, Ansible facts, and Docker state via SSH, with a strict command allowlist and no write operations.
Updated 2 months ago (2026-07-05 07:29 UTC)
-
srv-explore
Shell Access Command Line Databases
redmadrobot-rnd
F
license
Not graded
quality
B
maintenance
Enables AI agents to safely explore and diagnose remote servers by providing a read-only sandbox with controlled access to files, logs, Docker, and databases. It exposes MCP tools that allow natural-language investigation and direct command execution without write permissions.
Updated a month ago (2026-08-12 17:30 UTC)
3
-

🛡️ System Status & Config MCP Server (Agentic AIOps)

🌟 Why This Exists?

🚀 Core Features

1. 📊 High-Concurrency System Probes (get_system_status)

2. 🔍 Intelligent Config Radar (discover_configs)

3. 🧠 Token-Optimized Config Reader (read_config)

4. 🛡️ Safe Log Tailing (read_log)

🛠️ Installation & Setup

Prerequisites

Build from source

Usage with Claude Desktop

🧰 Available MCP Tools

🏗️ Architecture & Safety Highlights

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

1. 📊 High-Concurrency System Probes (`get_system_status`)

2. 🔍 Intelligent Config Radar (`discover_configs`)

3. 🧠 Token-Optimized Config Reader (`read_config`)

4. 🛡️ Safe Log Tailing (`read_log`)