mcp-memory-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-memory-server List top 5 memory consuming processes"
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.
MCP Memory Server
MCP server for memory management with process inspection and cleanup tools.
Tools
Tool | Description |
| System memory summary (like |
| Top N memory consumers with details |
| Find sleeping/idle processes by age, state, name pattern |
| Kill PIDs with safety checks |
Related MCP server: mem0_mcp_server
Installation
Claude Code
Add to ~/.config/claude-code/mcp.json:
{
"mcpServers": {
"mcp-memory": {
"command": "nix",
"args": ["run", "github:paolino/mcp-memory-server", "--refresh"]
}
}
}The --refresh flag ensures you always get the latest version. Remove it to use the cached version for faster startup.
From source
git clone https://github.com/paolino/mcp-memory-server
cd mcp-memory-server
nix develop
just install
just runUsage Examples
Show memory usage
Ask Claude: "Show me current memory usage"
Find stale GHC processes
Ask Claude: "Find old GHC or cabal processes using more than 100MB"
This calls find_stale_processes with:
name_pattern:"ghc|cabal"min_memory_mb:100
Kill processes
Ask Claude: "Kill these PIDs: 1234, 5678"
Safety checks:
Refuses PID 0/1
Refuses root-owned processes (unless running as root)
Optional name confirmation to prevent killing wrong process
Default SIGTERM, SIGKILL only when explicit
Development
nix develop
just test # Run tests
just run # Start server
just format # Format code
just lint # Lint codeLicense
MIT
Available Tools
5 toolsfind_stale_processesB
Find potentially stale processes based on various criteria.
Useful for finding long-running background processes that may be consuming resources unnecessarily.
Inputs: states, name_pattern, min_age_hours, min_memory_mb. Returns: result
kill_processesA
Kill processes by PID with safety checks.
Safety mechanisms:
Refuses to kill PID 0 or 1
Refuses root-owned processes unless running as root
Optional name confirmation to prevent killing wrong process
Uses SIGTERM by default, SIGKILL only when explicit
Inputs: pids (required), signal_name, confirm_names. Returns: Summary of kill operation results.
list_memory_usageA
Get system memory usage summary.
Returns total, available, used memory and swap statistics,
similar to the free -h command.
Inputs: no named parameters. Returns: System memory information.
list_process_groupsA
List processes grouped by name with aggregated stats.
Useful for seeing total resource usage by process type (e.g., "3 claude processes using 1.6GB total").
Inputs: n, min_count. Returns: result
list_top_processesC
List top N memory-consuming processes.
Inputs: n, sort_by. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct purpose: memory usage overview, top processes, process grouping, stale process detection, and process termination. Even the two listing tools are clearly differentiated by their focus on top consumers versus name-based aggregation, with descriptions reinforcing this.
All tool names follow a consistent verb_noun pattern in snake_case (list_*, find_*, kill_*). There are no mixed conventions or vague verbs, making the API predictable and easy to navigate.
With 5 tools, the server is well-scoped for its purpose. It provides a comprehensive set for memory monitoring and process management without unnecessary bloat, and each tool earns its place.
The tool surface covers the core lifecycle: memory overview, process listing, grouping, stale detection, and killing. A minor gap is the lack of a tool to retrieve detailed information about a single process by PID, but this does not critically impede the server's primary functionality.
Maintenance
Related MCP Connectors
An MCP memory server. One memory your agents share — across models, devices and apps.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Autopilot MCP server for GEO analyses, reports, content, audits, memories and agents.
Related MCP Servers
- AlicenseAqualityDmaintenanceMCP server for system monitoring, enabling users to ask about CPU, memory, disk, network, and processes on their system.93MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides memory management tools for AI agents, enabling adding, searching, updating, and deleting memories via the Mem0 API.18 npmMIT
- FlicenseNot gradedqualityDmaintenanceMCP server providing agent memory management with layered awakening, per-agent SQLite storage, and a dashboard for monitoring and administration.-
- AlicenseNot gradedqualityDmaintenanceAn MCP server for Windows process memory inspection/editing and crash dump analysis, enabling live memory scanning, patching, pointer resolution, disassembly, and offline dump examination via structured tool calls.MIT