Survey Insight MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | LLM model to use (e.g., 'claude-3-5-sonnet-20241022' for Anthropic or 'gemini-2.0-flash-exp' for Google) | |
| LLM_API_KEY | No | API key for the selected LLM provider (Anthropic Claude or Google Gemini) | |
| LLM_PROVIDER | No | LLM provider to use for AI analysis ('anthropic' or 'google') | |
| USE_CLAUDE_CODE_SUBSCRIPTION | No | Set to 'true' to use Claude Code Subscription for AI analysis |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_surveyC | アンケートCSVファイルを分析し、形態素解析、WordCloud、グラフを含む洗練されたHTMLレポートを生成します |
| update_ai_analysisA | 既存のHTMLレポートにClaude Codeが分析した課題と解決策を追加します。 |
| generate_wordcloudC | テキストデータからWordCloudを生成 |
| extract_keywordsC | 形態素解析でキーワードを抽出 |
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 4 tools
The four tools have distinct primary purposes: analyze_survey creates comprehensive HTML reports, extract_keywords focuses on keyword extraction, generate_wordcloud creates visual word clouds, and update_ai_analysis enhances existing reports with AI insights. However, there is some functional overlap as analyze_survey already includes keyword extraction and word cloud generation, which could cause confusion about when to use the specialized tools versus the comprehensive analyzer.
All tool names follow a consistent verb_noun pattern with snake_case formatting: analyze_survey, extract_keywords, generate_wordcloud, and update_ai_analysis. The naming is predictable and follows the same grammatical structure throughout, making it easy for agents to understand the action-object relationship.
Four tools is a reasonable number for a survey analysis server, providing focused functionality without being overwhelming. However, the set feels slightly thin for comprehensive survey analysis workflows, as it lacks tools for basic survey operations like loading/parsing survey data, filtering responses, or generating different types of visualizations beyond word clouds.
The toolset covers advanced analysis and reporting well but has notable gaps in foundational survey operations. There are no tools for importing/validating survey data, basic statistical analysis, filtering responses by demographics, or creating different visualization types. The workflow assumes users already have processed survey data ready for analysis, creating potential dead ends for agents needing to perform complete survey analysis from raw data.