feellab-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FEELLAB_OUT | No | The only folder Feel Lab writes to (its reports); defaults to ~/.feellab. | ~/.feellab |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_checklistC | The checklist: every interaction, what the player should get, and how it is checked (measured or by a person). |
| list_scenesD | The standard scenes a probe plays, one timeline each, and what each asks it to do. |
| list_metricsB | Every metric: its scene, unit, which way is better, its rule and the rule's source (estimate or evidence). |
| check_timelineC | A timeline file against the contract (feellab-timeline/1): every problem, or none. |
| judge_folderB | Each subject's scenes judged against the checklist: every measured item's values, rules and verdict, a summary, and a Markdown report written beside them. |
| gate_rowsC | The metrics as rows for a gate (Weapon Lab's row format): subject, scene, metric, value. |
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 6 tools
The three list_* tools clearly target distinct resources (checklist, scenes, metrics), and check_timeline vs judge_folder differ in scope (single file validation vs folder-level judging). Minor overlap between check_timeline and judge_folder since both involve evaluation, but descriptions separate them adequately.
Five of six tools follow a clean verb_noun pattern (list_checklist, list_scenes, list_metrics, check_timeline, judge_folder). gate_rows deviates in form, but it's a single minor exception rather than a systematic inconsistency.
Six tools is well-scoped for an evaluation/QA framework: three listing tools plus three analysis tools. Each tool earns its place with no redundancy or padding.
The surface covers the inspection lifecycle: enumerating resources (checklist, scenes, metrics), validating timelines, judging folders, and emitting gate rows. The toolset is read/analysis-oriented, so authoring or updating checklists/metrics/scenes is absent, but that appears intentional for this domain.