shellward

Describes the environment variables required to run the server.

Name	Required	Description	Default
`SHELLWARD_MODE`	No	Determines whether to block and log (enforce) or log only (audit).	enforce
`SHELLWARD_LOCALE`	No	The language locale for the server. Auto-detects from system LANG if set to auto.	auto
`SHELLWARD_THRESHOLD`	No	Risk score threshold for injection detection, ranging from 0 to 100.	60

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
check_commandA	Check if a shell command is safe to execute. Detects rm -rf, reverse shells, fork bombs, curl\|sh, etc.
check_injectionA	Detect prompt injection attempts in text. Supports 32+ rules for Chinese and English, with hidden character detection.
scan_dataA	Scan text for sensitive data: PII (Chinese ID cards, phone numbers, bank cards), API keys, passwords, private keys, JWT tokens, SSN, credit cards.
check_pathA	Check if a file path operation is safe. Protects .env, .ssh/, .aws/credentials, private keys, /etc/passwd, etc.
check_toolA	Check if a tool name is allowed. Blocks payment/transfer tools, flags exec/shell tools as sensitive.
check_responseA	Check an AI response for security issues: canary token leaks and sensitive data exposure.
security_statusA	Get current ShellWard security status: mode, active layers, detection capabilities.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

Latest Blog Posts

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jnMetaCode/shellward'

If you have feedback or need assistance with the MCP directory API, please join our Discord server