jev-mcp
by drmedia
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port of the Streamable HTTP server. Default 8098. | 8098 |
| JEV_MODEL | No | Model to use. Default `jev-latest`. | jev-latest |
| JEV_PROVIDER | No | Provider to use: `typesafe`, `openrouter`, or `local`. Default `typesafe`. | |
| JEV_HTTP_HOST | No | Host for the Streamable HTTP server. Default `127.0.0.1`; `0.0.0.0` only inside a container. | 127.0.0.1 |
| JEV_LOG_LEVEL | No | Log level: `error`, `warn`, `info`, `debug`. Default `warn`. | warn |
| JEV_PROVIDERS | No | Comma-separated list of providers clients may select per request. Default unset: only `JEV_PROVIDER` is used. | |
| JEV_HTTP_TOKEN | No | Token for Streamable HTTP server (at least 32 characters). Required for `npm run start:http`. | |
| JEV_IMAGE_DIRS | No | Absolute directories for image `path`, separated by `;` on Windows and `:` elsewhere. Default unset: image `path` disabled. | |
| JEV_TIMEOUT_MS | No | Milliseconds per provider request attempt. Default 30000 (1000 to 600000). | 30000 |
| JEV_MAX_RETRIES | No | Maximum retries (0 to 10; 0 disables). Default 2. | 2 |
| TYPESAFE_API_KEY | No | Your TypeSafe API key. Required when JEV_PROVIDER=typesafe. | |
| JEV_LOCAL_API_KEY | No | API key for local provider. Default unset: no Authorization header. | |
| TYPESAFE_BASE_URL | No | Base URL for TypeSafe API. Default `https://api.typesafe.ai`. | https://api.typesafe.ai |
| JEV_LOCAL_BASE_URL | No | Server root for local provider, without `/v1`. Default `http://127.0.0.1:8097`. | http://127.0.0.1:8097 |
| OPENROUTER_API_KEY | No | Your OpenRouter API key. Required when JEV_PROVIDER=openrouter. | |
| JEV_MAX_CONCURRENCY | No | Provider requests at a time in `jev.evaluate_batch`. Default 4 (1 to 16). | 4 |
| JEV_MAX_INPUT_CHARS | No | Characters of `state` plus `questions` per request; `0` disables. Default 256000. | 256000 |
| OPENROUTER_BASE_URL | No | API root for OpenRouter, without `/v1`. Default `https://openrouter.ai/api`. | https://openrouter.ai/api |
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