Cuba-Exec
by LeandroPG19
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CUBA_EXEC_TTL | No | Idle process TTL in seconds (default: 3600) | |
| CUBA_EXEC_AUDIT | No | Enable audit logging (set to 1 to enable). | |
| CUBA_EXEC_MAX_PROCS | No | Maximum concurrent processes (default: 20) | |
| CUBA_EXEC_BUFFER_SIZE | No | Output buffer size in bytes (default: 64KB) | |
| CUBA_EXEC_ALLOWED_DIRS | No | Comma-separated list of allowed working directories. | |
| CUBA_EXEC_ALLOWED_COMMANDS | No | Comma-separated list of allowed commands. If set, only these commands can execute. | |
| CUBA_EXEC_BLOCKED_COMMANDS | No | Comma-separated list of blocked commands. Overrides default blocklist. | |
| CUBA_EXEC_SHUTDOWN_TIMEOUT | No | Graceful shutdown timeout in seconds (default: 5) |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/LeandroPG19/cuba-exec'
If you have feedback or need assistance with the MCP directory API, please join our Discord server