Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WITNESS_HOMENoOverride the witness data root directory. Defaults to ~/.local/share/witness/ (or ~/.local/share/claude-witness/ for pre-rename installs).
WITNESS_LOG_LEVELNoLog level for witness: debug, warn, error, or info. Anything unrecognized falls back to the default info level.info
WITNESS_MODEL_SHA256NoSHA256 checksum of the custom model binary. Must be provided together with WITNESS_MODEL_BASE_URL and WITNESS_TOKENIZER_SHA256.
WITNESS_MODEL_BASE_URLNoBase URL for a custom model mirror. Must be provided together with WITNESS_MODEL_SHA256 and WITNESS_TOKENIZER_SHA256.
WITNESS_TOKENIZER_SHA256NoSHA256 checksum of the custom model tokenizer. Must be provided together with WITNESS_MODEL_BASE_URL and WITNESS_MODEL_SHA256.

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

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/IngTian/witness'

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