# GetQueryly — AI Data Analyst

> Upload spreadsheets, get plain-English analysis with real computed charts and quality scores.

- name: io.github.thesinbin12-jpg/getqueryly
- version: 1.0.0
- connection class: R1 (autonomous)
- trust: 97/100
- quality: 81/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.thesinbin12-jpg%2Fgetqueryly
- tools: https://api.protogrid.dev/v1/servers/io.github.thesinbin12-jpg%2Fgetqueryly/tools

**An agent can connect on its own if it already holds `X_API_KEY`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "getqueryly": {
      "type": "http",
      "url": "https://getqueryly.com/mcp/mcp",
      "headers": {
        "X-API-Key": "${X_API_KEY}"
      }
    }
  }
}
```

Placeholders to fill: `${X_API_KEY}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-8d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (good)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: ds_swarm (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ds_report (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ds_health_check (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,168 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 22, about 2,168 tokens to load them all
- tool set hash: 49955b9a71bfaf498938333ed3b90f30
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.thesinbin12-jpg/getqueryly.svg)](https://protogrid.dev/servers/io.github.thesinbin12-jpg/getqueryly)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://getqueryly.com/mcp/mcp (streamable-http, auth api_key ${X_API_KEY}, reachable true, uptime30d 1)

## Packages

_none_

## Tools (22)

- `ai_chat`: Chat with getqueryly AI. Ask questions, generate content, search the web. Costs 1 Make.
- `analyze_file`: ONE-CALL deep analysis (v2): upload a file and get quality score, top
    insights, a summary and the headline chart — no session juggling.
    Without a question: full analysis (2 Makes). With a question: answers
    just that question (1 Make). Returns structured JSON.
- `chart`: Generate a chart from data. Ask for any chart type: bar, line, scatter, heatmap, box plot, treemap, etc. Costs 2 Makes.
- `create_comparison`: Create a side-by-side comparison infographic. Costs 1 Make.
- `create_infographic`: Create a professional infographic. stats_json/bars_json/progress_json: JSON arrays. Themes: corporate, vibrant, clean, nature, sunset. Costs 1 Make.
- `ds_dashboard`: Auto-generate a Power BI-grade executive dashboard (KPIs, charts, pricing
    elasticity, impact/effort matrix, takeaways) from the uploaded dataset. Costs 2 Makes.
- `ds_elasticity`: Pricing sensitivity: if the dataset has discount + margin columns, compute per-segment
    margin sensitivity to discount (slope, R-squared, confidence, recommendation). Costs 1 Make.
- `ds_graph`: Build or query a knowledge graph for an uploaded dataset (GraphRAG).
    action='build' turns the data into a graph and returns a summary.
    action='query' answers a question over the graph (e.g. 'which products share the most suppliers?').
    Costs 1 Make.
- `ds_health_check`: Run a data health check. Detects missing values, outliers, type issues, duplicates. Costs 2 Makes.
- `ds_insights`: Get automatic insights from data: patterns, anomalies, trends, correlations. Costs 3 Makes.
- `ds_query`: Ask a question about uploaded data. AI writes and runs Python code. Returns analysis with charts. Costs 1 Make.
- `ds_report`: Generate a PDF report from data analysis. Includes charts, stats, insights. Costs 3 Makes.
- `ds_swarm`: Run analyst swarm: multiple AI personas analyze your data independently, then synthesize consensus. Depth: quick (5 Makes) or full (8 Makes).
- `ds_upload`: Upload a data file for AI analysis. Supports CSV, Excel, JSON, PDF, images, SPSS, Parquet. Returns session_id. Free.
- `generate_diagram`: Generate a diagram from description. Types: flowchart, org_chart, process, mindmap, tree. Palettes: blue, green, purple, dark, warm. Costs 1 Make.
- `generate_org_chart`: Generate an org chart. names_json: JSON array of [name, role, parent_name_or_null]. Example: [["CEO John", "CEO", null], ["VP Sarah", "VP Engineering", "CEO John"]]. Costs 2 Makes.
- `get_costs`: Get the Makes cost table for all operations. Free.
- `get_usage`: Check your getqueryly Makes balance and usage. Free.
- `kaggle_analyze`: Search Kaggle, download dataset, and analyze it in one step. Costs 2 Makes for the query.
- `kaggle_load`: Download a Kaggle dataset and create an analysis session. Returns session_id for queries. Free.
- `kaggle_search`: Search 200K+ Kaggle datasets by keyword. Returns dataset refs, titles, license info, download counts. Free.
- `smart_test`: AI picks the right statistical test for your data and runs it. Costs 1 Make.