jev-bridge
by lhviet
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TYPESAFE_DB | No | The database path. | $JEV_BRIDGE_HOME/jev.db |
| TYPESAFE_MODEL | No | Alternative to TYPESAFE_DEFAULT_MODEL for specifying the default model. | jev-latest |
| JEV_BRIDGE_HOME | No | Where the key file and database live. | ~/.jev-bridge |
| TYPESAFE_API_KEY | No | The TypeSafe API key. The key is looked up in this order: TYPESAFE_API_KEY, TYPESAFE_API_KEY_FILE, ~/.jev-bridge/.env, then a .env at the repository root. If set as an environment variable, the key sits in the MCP client config file in plain text. | |
| TYPESAFE_API_URL | No | Full API base including /v1. Wins over TYPESAFE_BASE_URL when both are set. | |
| TYPESAFE_HISTORY | No | How much of each call to keep for review. 'full' stores state and question text, 'meta' stores only answers, timings, tokens, cost)Skip hashes, 'off' keeps nothing. | full |
| TYPESAFE_BASE_URL | No | API root, the SDKs' name for it; /v1 is added. Must be https://, or http:// to this machine, or the key is not sent. | https://api.typesafe.ai |
| TYPESAFE_CACHE_MAX | No | Cache entries kept before eviction. | 20000 |
| TYPESAFE_TIMEOUT_MS | No | Timeout per attempt, as in the SDKs. There is no total budget. | 10000 |
| TYPESAFE_HISTORY_MAX | No | Unreviewed calls kept before the oldest go. | 10000 |
| TYPESAFE_MAX_RETRIES | No | Retries after the first attempt, for 408, 429, 5xx, timeouts and dropped connections. 0 turns retrying off. | 2 |
| TYPESAFE_API_KEY_FILE | No | Read the key from this file instead of using TYPESAFE_API_KEY. | |
| TYPESAFE_HISTORY_DAYS | No | How long an unreviewed call is kept. | 30 |
| TYPESAFE_USD_PER_MTOK | No | Price used to compute cost. | 0.042 |
| TYPESAFE_DEFAULT_MODEL | No | Default model, the SDKs' name for it. Pin a version such as jev-1.13.0 if you tune thresholds against it. TYPESAFE_MODEL also works. | jev-latest |
| TYPESAFE_CACHE_TTL_DAYS | No | How long an answer stays fresh. | 7 |
| TYPESAFE_BACKOFF_INITIAL_MS | No | First backoff, doubling to 5 s with 25% jitter. A Retry-After or retry-after-ms up to 60 s is used instead. | 500 |
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