Skip to main content
Glama
FinloAI
by FinloAI

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHATWORK_ROOTSYesControls file modification, command working directory, and long task working directory. Configure access roots before starting.
CHATWORK_TOKENNoToken required when non-loopback listening is allowed.
CHATWORK_STATE_DIRNoPersistent task, screenshot, and audit state directory; stable runner defaults to Application Support.
CHATWORK_READ_ROOTSNoControls dedicated read-only tool scope; if omitted, inherits write roots.
CHATWORK_ALLOW_REMOTENoSet to 1 to allow non-loopback HTTP listening.
CHATWORK_MAX_OUTPUT_BYTESNoUpper limit for command return output.
CHATWORK_MAX_SCAN_ENTRIESNoMaximum directory entries to check per recursive discovery/search.
CHATWORK_MAX_JOB_LOG_BYTESNoUpper limit for long-running job log size.
CHATWORK_MAX_COMMAND_SECONDSNoUpper limit for synchronous commands (max 90 seconds).
CHATWORK_MAX_CONCURRENT_JOBSNoMaximum concurrent parallel long-running jobs.
CHATWORK_REQUIRE_PROCESS_SANDBOXNoWhen set to 1, refuse to run commands if macOS process sandbox is unavailable; otherwise degrade.
CHATWORK_ALLOW_SENSITIVE_COMMAND_READSNoSet to 1 to allow commands to read sensitive paths (not recommended for trusted work).

Instructions

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.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources