openEuler MCP Toolkit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENEULER_MCP_ALLOWED_ROOTS | No | Colon-separated list of directories allowed for file analysis. Defaults to the server's startup directory. Use system path separator to configure multiple allowed directories. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_memory_infoA | READ-ONLY memory snapshot. Use only for current system RAM, swap, and /proc/meminfo. Takes no arguments. Never deletes files or stops processes. |
| get_process_memoryA | READ-ONLY memory inspection for one PID. Returns RSS, VMS, and largest mappings. This cannot stop, kill, or modify the process; refuse such requests. |
| sample_memory_trendA | READ-ONLY time-series sampling of system memory. Use for trends over a requested duration, not for a single snapshot, files, page algorithms, or processes. |
| simulate_page_replacementA | PURE PAGE-REPLACEMENT SIMULATION using FIFO/LRU/CLOCK/OPT. Use only for a page reference string. Not for disk block allocation, filesystem scans, or live memory. Required JSON keys: reference_string and algorithm. |
| get_filesystem_infoA | READ-ONLY mounted-filesystem snapshot. Returns space and inode usage. Takes no arguments and never scans, changes, or deletes files. |
| analyze_file_distributionA | READ-ONLY DIRECTORY SCAN for counts, extensions, sizes, and largest paths. Use max_files to cap scanning. Not a disk-allocation simulation and cannot delete files. |
| monitor_file_metadataA | READ-ONLY polling of one FILE's size and timestamps. Requires the exact file path. This is not a directory scan, access tracing, or a delete/modify operation. |
| simulate_disk_allocationA | PURE DISK-BLOCK ALLOCATION SIMULATION using flat arguments. Arguments are files, strategy, total_blocks, and block_size_bytes. Not for page-reference algorithms, directory scans, or real disk changes. |
| get_process_treeB | READ-ONLY PROCESS TREE starting at root_pid. The result is bounded by depth and node count. This cannot stop, kill, reprioritize, or otherwise modify any process. |
| monitor_context_switchesA | READ-ONLY CONTEXT-SWITCH sampling for the system or one PID. This observes counters only and cannot stop or modify processes. It is not a CPU scheduling simulation. |
| simulate_cpu_schedulingA | CALL THIS EXACT TOOL for RR, SJF, FCFS, or PRIORITY job scheduling. This is a pure simulation. Include every requested job, the explicit algorithm, and RR time slice. The tool name must remain simulate_cpu_scheduling. This does not inspect, stop, or modify real processes. |
| sample_cpu_time_ratiosA | READ-ONLY sampling of live CPU user/system/idle percentages. Never use for job lists, algorithms, RR, SJF, Priority, or time slices. This is not context-switch monitoring, process control, or CPU scheduling simulation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose, and descriptions explicitly contrast siblings (e.g., snapshot vs. trend, directory scan vs. single-file polling, page replacement vs. disk allocation). No two tools appear to overlap in function.
All tool names use snake_case and follow a consistent verb_noun pattern (get_, simulate_, sample_, monitor_, analyze_). The verbs are varied but appropriate, and no mixed conventions appear.
With 12 tools, the set is well-scoped for a system monitoring and OS simulation toolkit. Each tool covers a distinct resource or operation, and the count stays within the ideal 3–15 range.
The surface covers memory, CPU, filesystem, process, and key simulations, but has minor gaps: no system-wide info (uptime, load, kernel version), no per-process CPU usage, and no flat process listing. These gaps are workaroundable but limit the toolkit's coverage.