Brain Execution Server
Click on "Install 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., "@Brain Execution ServerQueue a command to check system info"
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.
Brain Execution Server
A queue-based execution server that monitors and processes jobs from the Brain MCP command queue.
Features
Monitors
/Users/bard/mcp/memory_files/command_queue/pendingfor jobsExecutes shell commands and Python scripts
Supports both JSON and text file job formats
Moves completed jobs to
completed/orfailed/directories5-minute timeout for safety
Logs all operations to
daemon.log
Job Formats
JSON Format
{
"command": "which",
"args": ["node"],
"description": "Check if node is in PATH"
}Or:
{
"task_id": "unique_id",
"command": "python3 /path/to/script.py",
"purpose": "Description of the job",
"result_file": "optional_output.txt"
}Text Format
Plain text files (.txt or .sh) containing shell commands:
cd /path/to/dir && python script.pyInstallation & Usage
Start the server:
cd /Users/bard/Code/mcp-execution-server python3 server.pyMonitor the queue:
python3 /Users/bard/mcp/memory_files/command_queue/queue_viewer.pyAdd a job to the queue:
# JSON job echo '{"command": "echo", "args": ["Hello from queue!"]}' > /Users/bard/mcp/memory_files/command_queue/pending/test_job.json # Text job echo 'ls -la /Users/bard/Code' > /Users/bard/mcp/memory_files/command_queue/pending/list_code.txt
Running in Background with LaunchControl
Create a launch agent to run the server automatically:
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>com.brain.execution-server</string>
<key>ProgramArguments</key>
<array>
<string>/usr/bin/python3</string>
<string>/Users/bard/Code/mcp-execution-server/server.py</string>
</array>
<key>WorkingDirectory</key>
<string>/Users/bard/Code/mcp-execution-server</string>
<key>RunAtLoad</key>
<true/>
<key>KeepAlive</key>
<true/>
<key>StandardOutPath</key>
<string>/Users/bard/mcp/memory_files/command_queue/server.log</string>
<key>StandardErrorPath</key>
<string>/Users/bard/mcp/memory_files/command_queue/server.error.log</string>
</dict>
</plist>Queue Directories
Pending:
/Users/bard/mcp/memory_files/command_queue/pending/- Jobs waiting to be processedCompleted:
/Users/bard/mcp/memory_files/command_queue/completed/- Successfully executed jobsFailed:
/Users/bard/mcp/memory_files/command_queue/failed/- Jobs that failed or timed outLogs:
/Users/bard/mcp/memory_files/command_queue/daemon.log- Server activity log
Security Note
This server executes arbitrary code from the queue. Ensure proper permissions on the queue directories.
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
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/MikeyBeez/mcp-execution-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server