Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GF_BIND_HOSTNoThe host address the local proxy binds to. Loophack by default; set to 0.0.0.0 to allow remote access (non-loopback requests must present a bearer token).127.0.0.1
TROTH_STVC_BYPASSNoA documented escape hatch for local debugging that bypasses the STVC gate. troth doctor reports it when set.
telemetry_endpointNoAn optional endpoint to append telemetry counts to. No default endpoint ships; nothing is sent unless this is set in ~/.troth/config.json.
TROTH_NO_MODEL_FETCHNoSet to 1 to suppress all model/binary downloads (for CI, metered networks, or servers).
TROTH_LLAMA_SERVER_BINNoPath to a custom llama-server binary, overriding the pinned llama.cpp release download.

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

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/xgre1/troth'

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