BytesJev PlanningChecker
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| VIZ_URL | No | The URL the MCP server posts calls to for the live dashboard. Defaults to http://localhost:4310. Set this if the page is not on that URL. | |
| BYTESJEV_CACHE | No | Set to 1 to enable writing a cache to disk. Nothing is written to disk otherwise. | |
| BYTESJEV_DEBUG | No | Set to 1 to print one stderr line per call with the status, item count, and milliseconds. | |
| TYPESAFE_API_KEY | Yes | Your TypeSafe API key from https://typesafe.ai. Required for the Jev API. Read from TYPESAFE_API_KEY (or a .env file) and never logged or echoed. |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| PlanningCheckerA | Advisory check for overengineering. Call it once after you have a plan and before you edit any file. Send the user's ORIGINAL request verbatim (never reconstruct it), every meaningful proposed addition as its own plan item with your honest rationale, and the repository conventions or constraints that bear on those items. Do not send secrets, .env contents, or unrelated source: the payload is transmitted to the Jev API. Each item comes back with a necessity_score (Jev's support for the specific question "is this needed by the request, a stated constraint, or correctness/security"; not a verified probability), a recommendation (keep / simplify / review), a reason that cites your submitted text, and an uncertain flag. "simplify" is only given when the other plan items alone would satisfy the request. "review" means the evidence is mixed or missing: decide yourself and name the concrete need if you keep the item. On status "unavailable" proceed with your plan as normal. Limits: 25 items, 4000 chars of request, 8000 chars of context; truncation is reported in limitations. |
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 1 tool
With only one tool, there is no possibility of confusion or misselection between tools. The tool's purpose is clearly distinct by default.
A single tool named 'PlanningChecker' follows a consistent naming pattern by itself. There are no other tools to create inconsistency, so the naming is perfectly consistent within the set.
The server's purpose is a single advisory check, so one tool is appropriate and well-scoped. It is slightly below the typical 3-15 range, but the narrow focus justifies the minimal surface.
The tool covers the full stated purpose of checking a plan for overengineering, with no obvious missing operations for an advisory service. Minor gaps like history or batch processing are not required for its core function.