open-jev
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JEV_HOME | No | Path to the Open-Jev installation. Default: ~/Projects/Open-Jev | |
| JEV_PORT | No | Port for the Open-Jev server. | |
| JEV_DEVICE | No | Device for running Open-Jev (e.g., 'cuda'). | |
| OPENJEV_URL | No | URL of the Open-Jev server. Default: http://127.0.0.1:8791/v1/systemone | |
| JEV_CHECKPOINT | No | Path to the Open-Jev model checkpoint. | |
| OPENJEV_DISABLE | No | Set to '1' to disable the pipeline entirely. | |
| OPENJEV_LLM_URL | No | URL of the local Ollama server. Default: http://127.0.0.1:11434 | |
| OPENJEV_FALLBACK | No | Fallback behavior when the planner fails. Allowed values: 'static' or 'none'. | |
| JEV_START_TIMEOUT | No | Timeout in seconds when waiting for the Open-Jev server to become ready. | |
| OPENJEV_LLM_MODEL | No | Ollama model used for planning. Default: qwen3.5:4b | |
| OPENJEV_MAX_CHARS | No | Maximum number of prompt characters processed. Default: 6000 | |
| OPENJEV_JEV_TIMEOUT | No | Timeout in seconds for the Open-Jev request. Default: 5 | |
| OPENJEV_PLAN_TIMEOUT | No | Timeout in seconds for the planner call. Default: 10 | |
| OPENJEV_MAX_QUESTIONS | No | Maximum number of questions generated. Default: 5 | |
| OPENJEV_MAX_CANDIDATES | No | Maximum number of answer candidates considered. Default: 24 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| jev_askC | Ask the local Open-Jev server typed questions about a state. questions maps question_id -> {"type": "noul"|"choice"|"score", "instructions": str, "criteria": ...}. choice criteria: {label: description, ...}; score criteria: ordered list of level descriptions (2-10, lowest first); noul: no criteria (or {"true": ..., "false": ...}). |
| jev_planA | Generate (but do not run) the Jev probe the local LLM planner would write for this prompt. |
| jev_analyzeB | Run the full pipeline (LLM planner -> local Jev) on any text; returns questions, answers and a summary. |
| jev_healthA | Report whether the local Open-Jev server and the Ollama planner model are available. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Most tools are clearly distinct: health checks availability, plan generates a probe, and analyze runs the full pipeline. The slight overlap is between ask and analyze, since both involve asking the Open-Jev server questions, but ask is a direct query about a state while analyze runs the complete planner-to-Jev flow.
All tool names follow the same jev_<verb> pattern with clear verbs: ask, plan, analyze, and health. This makes the toolset highly predictable and easy for an agent to navigate.
Four tools is well-scoped for this focused server. Each tool covers a meaningful operation without redundancy or unnecessary surface area.
The core workflows are covered: checking health, inspecting a generated plan, asking direct questions, and running the full analysis pipeline. A minor gap is that there is no explicit tool to run a previously generated probe exactly, though analyze effectively covers the end-to-end use case.