NoCodeCSV
Ask questions about a CSV in plain English and get answers, charts and cleaned data back.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"nocodecsv": {
"url": "https://nocodecsv.com/api/mcp"
}
}
}Remote endpoints
https://nocodecsv.com/api/mcpstreamable-httpWhat it can do
Tool inventory
Tools (2)
⚪csv_profile(csvContent)
Return a deterministic profile of CSV text: row count, column count, each column's name, whether it looks numeric or text, and how many blanks it has. Runs locally without an AI model, so it is fast and always available.
Input Schema
{
"type": "object",
"properties": {
"csvContent": {
"type": "string",
"description": "The raw CSV text, including the header row."
}
},
"required": [
"csvContent"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢analyze_csv(csvContent, question)
Ask a question about CSV data in plain English and get a written answer back (totals, trends, outliers, comparisons, a recommended chart). The CSV text is analysed and discarded; nothing is stored.
Input Schema
{
"type": "object",
"properties": {
"csvContent": {
"type": "string",
"description": "The raw CSV text to analyse, including the header row."
},
"question": {
"type": "string",
"description": "The question to answer, in plain English."
}
},
"required": [
"csvContent",
"question"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}Community
Evidence