mcp-csv-server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-csv-server calculate total sales by region in orders.csv"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-csv-server
An MCP server that lets an AI assistant preview, query, aggregate, and convert CSV/TSV data — safely, with no API key.
Give Claude (or any MCP client) the ability to actually work with spreadsheets: filter rows, sum/average/group columns, and turn CSV into JSON — instead of eyeballing a pasted table and guessing. Pure TypeScript, dependency-light, and runnable with zero credentials, so a reviewer can try it in one command.
日本語の概要
AIアシスタント(Claude等)に「CSV/業務データを正しく扱う力」を与えるMCPサーバです。表をそのまま 読ませて推測させるのではなく、行の絞り込み・列の集計(合計/平均/最大最小)・グループ集計・JSON変換を ツールとして提供します。APIキー不要で動くので、その場で試せます。
壊れにくいCSVパーサ:引用符・エスケープ(
"")・引用符内のカンマ/改行に対応(素朴なsplit(',')が壊れる実データを正しく処理)。型付きエラー+対処ヒント:
[UNKNOWN_COLUMN] Unknown column "x". Hint: Available columns: ...のように、AIにも人にも原因と対処が分かる。責務分離:
csv/(パース・クエリの純粋ロジック)/tools/(MCPツール定義)/server.ts(薄い配線)。テスト:パーサ・クエリ・ツールを19本のユニットテストで検証(全エラー経路含む)。CI緑。
Related MCP server: mcp-excel
Tools
Tool | What it does | Key inputs |
| Columns, total row count, and a sample |
|
| Filter / select / aggregate / group / limit |
|
| Convert CSV/TSV to JSON records |
|
aggregate supports count, sum, avg, min, max; where ops are
eq, ne, gt, gte, lt, lte, contains (ANDed together). Numbers tolerate
thousands separators ("2,000" → 2000).
Install & run
git clone https://github.com/takuyahoritacromtech/mcp-csv-server.git
cd mcp-csv-server
npm install
npm run buildUse with Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"csv": {
"command": "node",
"args": ["/absolute/path/to/mcp-csv-server/dist/index.js"]
}
}
}Restart the client; the csv_preview, csv_query, and csv_to_json tools appear.
Quick smoke test (no client needed)
printf '%s\n' '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke","version":"0"}}}' \
| node dist/index.js
# → {"result":{...,"serverInfo":{"name":"mcp-csv-server",...}},"jsonrpc":"2.0","id":1}Example: "total sales by region"
Given a csv_query call with:
{ "csv": "region,amount\nEast,1000\nWest,2000\nEast,500",
"groupBy": "region",
"aggregate": { "fn": "sum", "column": "amount" } }the tool returns:
{ "columns": ["region", "sum_amount"],
"rows": [{ "region": "East", "sum_amount": 1500 }, { "region": "West", "sum_amount": 2000 }],
"rowCount": 2 }Design notes (the "why")
A real CSV parser, not
split(',')— a small RFC 4180 state machine handles quoting, escaped quotes, and embedded delimiters/newlines. This is where naive tools silently corrupt data.Pure core, thin MCP shell — all logic lives in
csv/andtools/as pure functions, so it is unit-tested without the protocol.server.tsonly maps tools to the SDK and convertsCsvErrorinto clean tool errors.Typed errors with hints — every failure (
UNKNOWN_COLUMN,NON_NUMERIC_COLUMN,CSV_PARSE_ERROR, …) is actionable from the message alone.Validated inputs — every tool input is a Zod schema, so malformed calls are rejected before any work happens.
Testing
npm run check # typecheck + lint + test19 unit tests cover CSV parsing (quoting, TSV, CRLF, ragged rows, empty, unterminated quotes), the query engine (filter/select/aggregate/group/limit + every error code), and the three tools.
License
MIT © Takuya Horita
Available Tools
3 toolscsv_previewPreview CSVA
Parse CSV/TSV text and return its columns, total row count, and a few sample rows.
Inputs: csv (required), delimiter, limit.
csv_queryQuery CSVA
Filter, select, aggregate (count/sum/avg/min/max), group, and limit CSV/TSV rows declaratively.
Inputs: csv (required), delimiter, select, where, +3 more.
csv_to_jsonCSV to JSONB
Convert CSV/TSV text into an array of JSON records.
Inputs: csv (required), delimiter, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a distinct purpose: preview shows structure, query filters/aggregates, to_json converts format. No overlap or ambiguity.
All tools follow the consistent pattern 'csv_' + verb: csv_preview, csv_query, csv_to_json. Naming is uniform and predictable.
Three tools cover the essential CSV operations (preview, query, convert) without being too sparse or excessive. Well-scoped for the domain.
Covers core operations but lacks write/update or other format conversions (e.g., to JSON is included, but to other formats like XML is missing). Minor gaps exist.
Maintenance
Related MCP Connectors
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Ask questions about a CSV in plain English and get answers, charts and cleaned data back.
Dedupe, compare, merge, split and profile CSV or TSV files that are too big to paste into a chat.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with local CSV and Parquet data files through natural language queries, facilitating tasks like summarizing datasets or retrieving specific information.4-
- AlicenseNot gradedqualityDmaintenanceEnables querying Excel and CSV files using SQL via natural language, allowing AI assistants to analyze data without manual SQL writing.23 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceTransforms AI assistants into data analysts by enabling CSV and Google Sheets import, SQL querying, and instant insights through natural language.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to analyze large CSV files locally by importing them into SQLite, profiling columns, and running read-only SQL queries without data leaving the machine.MIT