@barivia/barsom-mcp 0.2.5 → 0.2.7
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -6
- package/dist/index.d.ts +1 -1
- package/dist/index.js +418 -246
- package/dist/index.js.map +1 -1
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# @barivia/barsom-mcp
|
|
2
2
|
|
|
3
|
-
MCP proxy for the Barivia Analytics Engine -- connects any stdio MCP client (Cursor, Claude Desktop, etc.) to the barSOM cloud API.
|
|
3
|
+
MCP proxy for the Barivia Analytics Engine -- connects any stdio MCP client (Cursor, Claude Desktop, etc.) to the barSOM cloud API. 13 tools covering the full data analysis lifecycle: upload, preview, train, analyze, compare, and export.
|
|
4
4
|
|
|
5
5
|
## Installation
|
|
6
6
|
|
|
@@ -32,16 +32,14 @@ This is the standard pattern for MCP servers distributed as npm packages (same a
|
|
|
32
32
|
|
|
33
33
|
Legacy `BARSOM_API_KEY` / `BARSOM_API_URL` are also accepted as fallbacks.
|
|
34
34
|
|
|
35
|
-
## Tools (
|
|
35
|
+
## Tools (13)
|
|
36
36
|
|
|
37
37
|
### Data Management
|
|
38
38
|
|
|
39
39
|
| Tool | Description |
|
|
40
40
|
|---|---|
|
|
41
|
-
| `
|
|
41
|
+
| `datasets` | upload: add CSV; preview: inspect columns/stats/samples before train_som; subset: create subset by row_range or filter; delete: remove dataset |
|
|
42
42
|
| `list` | List datasets (type=datasets) or jobs (type=jobs; optional dataset_id filter) |
|
|
43
|
-
| `preview_dataset` | Inspect columns, statistics, sample rows, detect datetime columns, suggest temporal features |
|
|
44
|
-
| `delete_dataset` | Delete dataset and S3 artifacts |
|
|
45
43
|
|
|
46
44
|
### Training Lifecycle
|
|
47
45
|
|
|
@@ -55,7 +53,7 @@ Legacy `BARSOM_API_KEY` / `BARSOM_API_URL` are also accepted as fallbacks.
|
|
|
55
53
|
|
|
56
54
|
| Tool | Description |
|
|
57
55
|
|---|---|
|
|
58
|
-
| `get_results` | Download results with inline images and quality metrics |
|
|
56
|
+
| `get_results` | Download results with inline images and quality metrics; use figures to request specific plots (e.g. figures: ["umatrix"] or figures: "all") |
|
|
59
57
|
| `get_job_export` | Export training_log (learning curves), weights (weight matrix + node_coords), or nodes (per-node statistics) |
|
|
60
58
|
|
|
61
59
|
### Analysis (10 types via `analyze`)
|
|
@@ -96,6 +94,10 @@ When adding or refining tools, follow [MCP best practices](https://modelcontextp
|
|
|
96
94
|
- **Explicit parameter descriptions** — Each parameter should describe format, constraints, and when to use it
|
|
97
95
|
- **Bounded capability** — Focused tools with specific contracts; prefer narrow, testable actions over broad ones
|
|
98
96
|
|
|
97
|
+
## Data preparation
|
|
98
|
+
|
|
99
|
+
To train on a subset of your data (e.g. first 2000 rows, or rows where region=Europe) without re-uploading: use **datasets(action=subset)** with `row_range` and/or `filter` to create a new dataset, then **train_som** on the new dataset_id; or pass **row_range** in **train_som** params for a one-off training slice.
|
|
100
|
+
|
|
99
101
|
## How It Works
|
|
100
102
|
|
|
101
103
|
The proxy implements the MCP stdio transport locally and translates tool calls into REST API requests to the Barivia backend. Results are returned as rich MCP content with text summaries, inline base64 images, and resource links.
|