embodied-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| detect_datasetA | Identify the on-disk format of an embodied-AI dataset (LeRobot, HDF5/robomimic, MCAP, rosbag1/2, RLDS, canonical JSONL) with confidence and evidence. |
| summarize_datasetA | Summarise a dataset: format, version, fps, robot type, features (key/dtype/shape/kind), episode count, frames, duration, tasks and notes. Use before any analysis to learn the schema. |
| validate_datasetB | Run structural validation: required metadata, feature vocabulary (state/action), episode indices and lengths, fps consistency, format-specific layout rules. Returns issues with severity, stable code, hint and a 0-100 score. |
| quality_reportB | Compute per-feature statistics (range, mean, std, percentiles, NaN ratio) and detect anomalous windows (jumps, stalls, non-finite spans) with robust z-scoring. |
| segment_episodesC | Split episodes into moving/idle segments using feature-speed percentiles. Useful for phase labelling and for trimming dead time. |
| labeling_tasksC | Generate an annotation manifest: each task names an episode, a frame range, cues and a concrete question, ready for a human reviewer or a vision-language model. |
| convert_datasetB | Convert a dataset to another layout: 'jsonl' (canonical, dependency-free) or 'lerobot' (v2.1 parquet, needs pyarrow). Numeric features only; camera streams are reported, not re-encoded. |
| scaffold_projectC | Write a project skeleton: 'platform' (HTTP API + quality gate + catalog + data contract), 'adapter' (new format adapter with tests) or 'pipeline' (ingest -> validate -> index). |
| catalog_indexB | Scan a directory tree, load every dataset found and upsert its metadata into a SQLite catalog. Incremental: unchanged datasets are skipped. |
| catalog_searchC | Query the dataset catalog by free text, format, robot type, episode count, duration or minimum health score. |
| catalog_statsB | Totals for the catalog: datasets per format, episodes, frames, duration, robot types and last index time. |
| list_formatsA | List supported dataset formats, how each is detected, which optional dependency it needs, and the available validation checks. |
| plan_windowsC | Plan fixed-length training windows over the episodes of a dataset (window, stride, episode/start/end). |
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 13 tools
Most tools target clearly different dataset lifecycle stages: detection, summarisation, validation, quality analysis, segmentation, labelling, conversion, cataloging, and planning. Minor possible confusion exists between detect_dataset and list_formats, and between summarize_dataset/validate_dataset/quality_report, but the descriptions clarify specific versus aggregate and structural versus statistical roles.
Most names use a readable snake_case convention, with verb_noun patterns like detect_dataset, validate_dataset, convert_dataset, segment_episodes, and plan_windows. The catalog_index/search/stats group is internally consistent, though quality_report and labeling_tasks deviate from the dominant verb_noun style.
Thirteen tools is well within the appropriate range and each appears to cover a distinct useful operation in an embodied-AI dataset workflow. The set is broad without feeling bloated, spanning inspection, validation, conversion, cataloging, and project scaffolding.
The surface covers a wide lifecycle: format detection, schema summary, validation, quality reporting, segmentation, annotation planning, conversion, scaffolding, cataloging, format listing, and training-window planning. Minor gaps remain, such as no explicit catalog deletion/pruning and no tool to materialise planned windows into actual training samples.