# Talk2Data InsightGenius (remote · spss.insightgenius.io)

Survey data analysis: crosstabs with significance, ANOVA, correlation, Excel exports.

- Trust score: 65/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `spss.insightgenius.io`: 65/100 (this document), [markdown](https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss.md), [page](https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss)

## Channel facts

- Endpoint: `https://spss.insightgenius.io/mcp/sse?api_key={api_key}`
- Transports: `sse`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 40/100
  - Verified sse transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 4051 tokens (~270/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 99/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 96% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http quack2025-talk2data-insightgenius https://spss.insightgenius.io/mcp/sse?api_key={api_key}
```

### Codex

```toml
[mcp_servers.quack2025-talk2data-insightgenius]
url = "https://spss.insightgenius.io/mcp/sse?api_key={api_key}"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "quack2025-talk2data-insightgenius": {
      "type": "remote",
      "url": "https://spss.insightgenius.io/mcp/sse?api_key={api_key}",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add quack2025-talk2data-insightgenius --url https://spss.insightgenius.io/mcp/sse?api_key={api_key} --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  quack2025-talk2data-insightgenius:
    url: "https://spss.insightgenius.io/mcp/sse?api_key={api_key}"
```

### Other

```json
{
  "mcpServers": {
    "quack2025-talk2data-insightgenius": {
      "type": "http",
      "url": "https://spss.insightgenius.io/mcp/sse?api_key={api_key}"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 64, +5)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 59, −2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 61, +1)

- [functional] Server version: 3.4.4 → 3.4.5

### 2026-07-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 59, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 59)

First indexed and scored.

## MCP tools (15)

### `spss_get_started` (~108 tokens)

Get started with Talk2Data InsightGenius. Returns setup instructions, available analysis tools, and a quick-start guide.

Call this tool when:
\- The user asks to analyze a data file and you haven't used Talk2Data before in this conversation
\- You need to understand what analysis capabilities are available
\- The user asks "what can Talk2Data do?" or "how do I use this?"
\- You don't have the user's API key yet

This tool requires NO authentication.

### `spss_upload_file` (~248 tokens)

Get a file_id for analysis. Users upload files via the web UI, not through this tool.

IMPORTANT — How file upload works:
1\. Ask the user to go to https://spss.insightgenius.io/upload
2\. They drag & drop their file there and get a file_id (e.g., "abc123")
3\. They paste the file_id back in chat
4\. You use that file_id in all subsequent tool calls (spss_get_metadata, spss_analyze_frequencies, etc.)

DO NOT attempt to encode files as base64. DO NOT use file_base64. Always use the upload URL.
If the user already has a file_id, just pass it to validate the session.

Sessions last 30 minutes (sliding TTL — refreshed on each use).

Authentication: OAuth (Claude.ai) = no api_key needed. Claude Desktop = pass api_key.

Input parameters:

- `api_key` (string): API key (sk_test_... or sk_live_...). Optional if connected via OAuth.
- `file_id`: File ID from https://spss.insightgenius.io/upload. Ask user if you don't have one.

### `spss_get_metadata` (~209 tokens)

Get comprehensive metadata for an uploaded data file: variable names, types, labels, value labels, AI-detected banner variables, MRS groups, grid/battery variables, and suggested nets. Returns structured survey intelligence that goes far beyond what pandas.describe() provides.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content (fallback if no file_id).
- `file_id`: File session ID from spss_upload_file (preferred).
- `filename` (string): Original filename (default: upload.sav).
- `response_format` (string): 'json' or 'markdown'.

### `spss_get_server_info` (~63 tokens)

Get Talk2Data InsightGenius server status, version, available tools, and plan limits.

This is the only tool that does NOT require an api_key. Use it to verify connectivity
before other operations, or to check what analysis capabilities are available.

### `spss_describe_variable` (~199 tokens)

Deep profile of specific variables: distribution, labels, missing values, statistics. Use this to understand a specific question/variable before running cross-tabulations.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `response_format` (string): 'json' or 'markdown'.
- `variable` (string): Single variable name.
- `variables`: List of variable names.

### `spss_analyze_frequencies` (~228 tokens)

Frequency tables with percentages, counts, mean, standard deviation, and median. Supports batch analysis of up to 50 variables in a single call. Returns professional market research output with content_blocks ready for presentations.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `response_format` (string): 'json' or 'markdown'.
- `variable` (string): Single variable name.
- `variables`: List of variable names (batch mode, up to 50).
- `weight`: Optional weight variable name.

### `spss_analyze_crosstab` (~289 tokens)

Cross-tabulation with column proportion z-test significance testing at 90/95/99% confidence. Returns letter notation (A/B/C) showing which columns are significantly different — the industry standard for market research reporting. Includes chi-square test, column percentages, and optional means.

This is a specialized statistical analysis that Python's pandas CANNOT replicate — it requires the exact significance testing methodology used in professional market research (column proportion z-test with Bonferroni correction and letter notation).

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `col`
- `col_variable` (string)
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `response_format` (string): 'json' or 'markdown'.
- `row` (string)
- `row_variable` (string)
- `significance_level` (number): Confidence threshold (0.90, 0.95, or 0.99).
- `weight`: Optional weight variable name.

### `spss_export_data` (~240 tokens)

Convert uploaded data file to xlsx, csv, dta, or parquet format. Supports applying value labels and including a metadata sheet.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `apply_labels` (boolean): Replace numeric codes with value labels (default True).
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `format` (string): Output format (alternative name). Same options.
- `include_metadata_sheet` (boolean): Add a variable-labels sheet to Excel output (default True).
- `target_format` (string): Output format. "xlsx", "csv", "dta", or "parquet".

### `spss_export_powerbi` (~324 tokens)

Export an uploaded file as a Power BI-ready ZIP with auto-generated DAX measures.

The ZIP contains:
\- `data/survey_data.csv` — wide-format data (one row per respondent)
\- `metadata/variables.csv` — variable names, labels, semantic types
\- `metadata/value_labels.csv` — code -> label dimension table
\- `dax/*.dax` — per-semantic-type measure files (binary, ordinal, interval, NPS)
\- `README.md` — Power BI Desktop import walkthrough + 5 Visual Recipes

DAX measures are generated based on each variable's semantic type (BINARY gets Pct_Yes,
ORDINAL gets Mean/Median/T2B/B2B, INTERVAL gets Mean/StdDev/Min/Max, 0-10 scales get NPS).

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using
Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content (alternative to file_id).
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `package_name` (string): Prefix used inside the ZIP and for the download filename.
- `table_name` (string): The Power BI table name every DAX measure will reference.

### `spss_create_tabulation` (~433 tokens)

Professional Excel tabulation with significance letters, nets, means, MRS groups, and Grid/Battery summaries. Publication-ready output matching the format used by market research agencies worldwide.

Generates a professional .xlsx workbook:
\- Summary sheet: column legend (letter -> label) + stub index
\- One sheet per stub variable with column percentages + significance letters (A/B/C)
\- Column bases (N), Top/Bottom 2 Box nets, means with T-test significance
\- Download URL (5-min TTL) for easy sharing

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `banner` (string): Single banner variable (v1 compat).
- `banners`: List of banner variables (v2, preferred).
- `custom_groups`: Custom break definitions.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `grid_groups`: Grid/battery summary definitions.
- `include_means` (boolean): Add means row with T-test significance.
- `include_total_column` (boolean): Include Total as first column.
- `mrs_groups`: MRS group definitions.
- `nets`: Net definitions per stub.
- `output_mode` (string): 'multi_sheet' or 'single_sheet'.
- `response_format` (string): 'json' or 'markdown'.
- `significance_level` (number): Confidence threshold (0.90, 0.95, 0.99).
- `stubs`: List of stub variable names, or null for all.
- `title` (string): Report title in the Summary sheet.
- `weight`: Optional weight variable name.

### `spss_auto_analyze` (~302 tokens)

Zero-config complete analysis: upload a file, get a full Excel workbook with AI-detected banners, MRS groups, grids, nets, and significance-tested cross-tabulations. No configuration needed — the engine detects the optimal analysis structure automatically.

Returns a download URL for the Excel file (valid 5 minutes) plus a structured summary with content_blocks for presentations.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `include_means` (boolean): Include means with T-test (default True).
- `max_banners` (integer): Maximum number of banner variables to use (default 3).
- `output_mode` (string): Output mode — "multi_sheet" or "single_sheet".
- `response_format` (string): 'json' or 'markdown'.
- `significance_level` (number): Confidence threshold (0.90, 0.95, 0.99).

### `spss_analyze_correlation` (~228 tokens)

Correlation matrix with Pearson, Spearman, or Kendall methods. Returns correlation coefficients with p-values and significance flags.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `method` (string): Correlation method — "pearson", "spearman", or "kendall".
- `response_format` (string): 'json' or 'markdown'.
- `variables` (array): List of numeric variable names to correlate (minimum 2, max 20).
- `weight`: Optional weight variable name.

### `spss_analyze_anova` (~235 tokens)

One-way ANOVA with Tukey HSD post-hoc pairwise comparisons. Identifies which groups differ significantly from each other.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `dependent` (string): Dependent (continuous) variable name.
- `factor` (string): Factor (grouping) variable name.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `post_hoc` (boolean): Run Tukey HSD post-hoc tests (default True).
- `response_format` (string): 'json' or 'markdown'.
- `weight`: Optional weight variable name.

### `spss_analyze_gap` (~225 tokens)

Importance-Performance gap analysis with quadrant classification (Concentrate Here, Keep Up, Low Priority, Possible Overkill). Standard framework for prioritizing improvements in customer experience research.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `importance_vars` (array): List of importance variable names.
- `performance_vars` (array): List of performance variable names (same order as importance).
- `response_format` (string): 'json' or 'markdown'.
- `weight`: Optional weight variable name.

### `spss_summarize_satisfaction` (~286 tokens)

Compact satisfaction summary: Top 2 Box (T2B), Bottom 2 Box (B2B), and Mean for scale variables. The standard KPI format used in market research reporting.

Authentication: If connected via OAuth (Claude.ai connector), no api_key needed. If using Claude Desktop or direct API, pass api_key (sk_test_... or sk_live_...).

Requires a file_id from a previous spss_upload_file call, or pass file_base64 directly.

Input parameters:

- `api_key` (string): Your API key (sk_test_... or sk_live_...). REQUIRED.
- `bottom_box`: Bottom Box values (e.g., [1, 2]).
- `file_base64`: Base64-encoded file content.
- `file_id`: File session ID from spss_upload_file.
- `filename` (string): Original filename (default: upload.sav).
- `response_format` (string): 'json' or 'markdown'.
- `scale`: Scale type — "5pt"/"1-5", "7pt"/"1-7", "10pt"/"1-10", or None for auto.
- `top_box`: Top Box values (e.g., [4, 5]).
- `variables` (array): List of satisfaction variable names.
- `weight`: Optional weight variable name.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss#diagnostics

## Score history

- 2026-08-03: 65
- 2026-08-02: 65
- 2026-08-01: 64
- 2026-07-31: 64
- 2026-07-30: 59
- 2026-07-29: 61
- 2026-07-28: 60
- 2026-07-27: 59
- 2026-07-26: 59

## Links

- Remote endpoint: https://spss.insightgenius.io/mcp/sse?api_key={api_key}
- Repository: https://github.com/quack2025/spss-insightgenius-api
- Changelog RSS feed: https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss/changelog.json
- HTML version of this page: https://verifymcp.io/servers/quack2025-talk2data-insightgenius/spss