Claude Cursor GitHub Copilot Skill

preset-mcp-data

Use Superset MCP data-returning tools for chart data, chart previews, rendered chart SQL, and dataset query results. Use only for MCP tool workflows; do not use for direct API work.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download preset-io-agent-skills-plugins_preset-mcp-skills_skills_preset-mcp-data-73d2674.zip · 1 KB

preset-io/agent-skills 12 1 forks Apache-2.0 Updated 14d ago

Part of preset-io/agent-skills — 28 skills

Install

skills CLI npx skills add https://github.com/preset-io/agent-skills/tree/master/plugins/preset-mcp-skills/skills/preset-mcp-data

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install preset-io-agent-skills@llmmart

Git git clone https://github.com/preset-io/agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole preset-io/agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

preset-mcp-data

Use when the user needs data returned through MCP tools.

Always

Use MCP tools only; do not switch to REST chart-data, SQL Lab, or dataset endpoints.
Treat returned rows, rendered SQL, chart previews, and dataset query results as potentially sensitive.
Keep row limits, selected columns, metrics, filters, and formats narrow.
Use discovery tools first when identifiers, metrics, columns, or chart IDs are unknown.
Do not use data tools as a workaround after data-model permission denial.

Decision Rules

Use get_chart_data for existing chart result data.
Use get_chart_preview for renderable existing chart previews.
Use get_chart_sql to inspect rendered chart SQL without executing it.
Use query_dataset for semantic-layer metrics, dimensions, filters, and time ranges (saved metrics only; route ad-hoc aggregates to preset-mcp-sqllab).
Route chart creation to preset-mcp-visualization.

Workflow Order

Classify which output the request needs: result data, preview content, SQL text, or semantic-layer output. Do not ask the user to re-confirm an explicit data request.
Resolve the object and schema through discovery if needed.
Choose get_chart_data, get_chart_sql, get_chart_preview, or query_dataset according to the requested output.
Request a small result with narrow fields, row limits, and the least revealing format.
Summarize data carefully; do not paste large raw payloads.

Retrieve

Data tool routing: references/data-tools.md

Files (agent-skills)

references

data-tools.md 1.6 KB

# Data Tools

| Goal | MCP Tool | Notes |
|---|---|---|
| Existing chart result rows | `get_chart_data` | Can return customer data in formats such as JSON/CSV/Excel depending on schema. |
| Existing chart preview | `get_chart_preview` | Returns preview URL or formatted content such as ASCII/table/Vega-Lite. |
| Rendered chart SQL | `get_chart_sql` | SQL text can expose business logic and schema. It does not execute the chart query. |
| Semantic-layer result table | `query_dataset` | Use saved metrics and column names from `get_dataset_info`. |

Prefer `query_dataset` when the user asks for metrics by dimensions on a known dataset. Prefer `get_chart_data` when the chart already exists and the user wants its result.

## Safe Data Workflow

1. Resolve the chart or dataset through discovery if the ID, metric, column, or filter is unknown.
2. Choose the narrowest MCP data tool:
   - `get_chart_data` for existing chart result rows.
   - `get_chart_sql` for rendered chart SQL inspection without execution.
   - `get_chart_preview` for existing chart preview output.
   - `query_dataset` for semantic-layer metrics, dimensions, filters, and time ranges.
3. Apply small row limits, narrow selected columns/metrics, narrow time ranges, and compact formats.
4. Summarize the result and avoid pasting large raw payloads.
5. Stop before changing surfaces.

Do not use the REST chart-data endpoint, SQL Lab, dataset REST endpoints, direct API calls, or database access from an MCP data workflow. If the MCP data tool cannot satisfy the request, explain the missing MCP capability and ask before changing surfaces.

SKILL.md 1.7 KB

---
name: preset-mcp-data
description: Use Superset MCP data-returning tools for chart data, chart previews, rendered chart SQL, and dataset query results. Use only for MCP tool workflows; do not use for direct API work.
---

# preset-mcp-data

Use when the user needs data returned through MCP tools.

## Always

- Use MCP tools only; do not switch to REST chart-data, SQL Lab, or dataset endpoints.
- Treat returned rows, rendered SQL, chart previews, and dataset query results as potentially sensitive.
- Keep row limits, selected columns, metrics, filters, and formats narrow.
- Use discovery tools first when identifiers, metrics, columns, or chart IDs are unknown.
- Do not use data tools as a workaround after data-model permission denial.

## Decision Rules

- Use `get_chart_data` for existing chart result data.
- Use `get_chart_preview` for renderable existing chart previews.
- Use `get_chart_sql` to inspect rendered chart SQL without executing it.
- Use `query_dataset` for semantic-layer metrics, dimensions, filters, and time ranges (saved metrics only; route ad-hoc aggregates to `preset-mcp-sqllab`).
- Route chart creation to `preset-mcp-visualization`.

## Workflow Order

1. Classify which output the request needs: result data, preview content, SQL text, or semantic-layer output. Do not ask the user to re-confirm an explicit data request.
2. Resolve the object and schema through discovery if needed.
3. Choose `get_chart_data`, `get_chart_sql`, `get_chart_preview`, or `query_dataset` according to the requested output.
4. Request a small result with narrow fields, row limits, and the least revealing format.
5. Summarize data carefully; do not paste large raw payloads.

## Retrieve

- Data tool routing: [references/data-tools.md](references/data-tools.md)