jev-answers
by AmooEbrahim
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEV_ANSWERS_HOME | No | Home directory for sessions and related data. | ~/.jev-answers |
| TYPESAFE_API_KEY | No | Fallback API key used when JEV_ANSWERS_API_KEY is not set and provider is typesafe. | |
| JEV_ANSWERS_DEBUG | No | Enable debug logging to stderr. | false |
| JEV_ANSWERS_MODEL | No | Model to use. Defaults to 'jev-latest' for TypeSafe or '~typesafe/jev-latest' for OpenRouter. | jev-latest |
| JEV_ANSWERS_CONFIG | No | Path to the config file. If unset, defaults to $XDG_CONFIG_HOME/jev-answers/config.json or ~/.config/jev-answers/config.json. | |
| OPENROUTER_API_KEY | No | Fallback API key used when JEV_ANSWERS_API_KEY is not set and provider is openrouter. | |
| JEV_ANSWERS_API_KEY | No | API key for the chosen provider. Falls back to TYPESAFE_API_KEY or OPENROUTER_API_KEY. | |
| JEV_ANSWERS_BASE_URL | No | Full endpoint URL for the provider. Defaults per provider: TypeSafe uses https://api.typesafe.ai/v1/systemone; OpenRouter uses https://openrouter.ai/api/alpha/decisions. | |
| JEV_ANSWERS_PROVIDER | No | Provider to use. One of 'typesafe' or 'openrouter'. | typesafe |
| JEV_ANSWERS_MAX_FILES | No | Maximum number of files to collect per call. | 200 |
| JEV_ANSWERS_TIMEOUT_MS | No | Timeout in milliseconds per request attempt. | 60000 |
| JEV_ANSWERS_MAX_RETRIES | No | Maximum number of retries for retryable errors. | 2 |
| JEV_ANSWERS_MAX_FILE_BYTES | No | Maximum size in bytes per individual file. | 1048576 |
| JEV_ANSWERS_RETENTION_DAYS | No | Number of days to retain session folders. 0 means keep forever. | 0 |
| JEV_ANSWERS_MAX_INPUT_TOKENS | No | Maximum estimated input tokens for the state plus the longest question. | 28000 |
| JEV_ANSWERS_MAX_TOTAL_TOKENS | No | Maximum estimated total tokens for a request. | 56000 |
| JEV_ANSWERS_ALLOW_SECRET_FILES | No | Allow explicitly named secret-looking files to be included. | false |
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
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues