Schema | ai-runtime-guard

ai-runtime-guard

Describes the environment variables required to run the server.

Name	Required	Description
`AIRG_AGENT_ID`	Yes	Identifier for the agent, used to apply per-agent policy overrides (e.g., 'claude-desktop').
`AIRG_LOG_PATH`	Yes	The absolute path to the activity.log audit trail file.
`AIRG_WORKSPACE`	Yes	The absolute path to the project root where agent operations are performed.
`AIRG_POLICY_PATH`	Yes	The absolute path to the policy.json configuration file.
`AIRG_SERVER_COMMAND`	Yes	The absolute path to the airg-server executable.
`AIRG_REPORTS_DB_PATH`	Yes	The absolute path to the reports.db database file used for dashboard views.
`AIRG_APPROVAL_DB_PATH`	Yes	The absolute path to the approvals.db database file.
`AIRG_APPROVAL_HMAC_KEY_PATH`	Yes	The absolute path to the HMAC key file for database security.

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.

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`	{}

Functions exposed to the LLM to take actions

Name	Description
server_infoB	Return runtime identity details for this AIRG server instance. Includes build id, active workspace root, and resolved base directory.
restore_backupA	Restore files from a recorded AIRG backup manifest. Supports dry-run planning and token-gated apply mode when restore confirmation is required by policy.
execute_commandB	Execute a shell command after full AIRG policy and approval checks. The command is evaluated against network/workspace containment, command-tier policy, Script Sentinel continuity checks, and optional confirmation gates before execution.
read_fileC	Read a text file from the workspace after path-policy enforcement.
write_fileC	Write full file content with policy checks, logging, and backup support.
edit_fileC	Apply targeted text replacements in an existing file with backups.
delete_fileA	Delete a single file after policy checks and optional pre-delete backup.
list_directoryB	List directory entries with metadata, honoring path and depth policy.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

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

curl -X GET 'https://glama.ai/api/mcp/v1/servers/runtimeguard/runtime-guard'

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