mcpField
C
csv-tools-mcp

csv-tools-mcp

Local
github.com/MukundaKattaDeveloper Tools0Updated 20w ago
Repository

About csv-tools-mcp

csv-tools-mcp is an MCP server for parsing, generating, and selecting data from CSV files. Its parser handles quoted fields, embedded delimiters, line endings, and leading BOMs.

Key features

  1. 01Parse CSV into headers and rows
  2. 02Generate CSV with correct quoting
  3. 03Select named columns
  4. 04Handle BOMs and line endings

Use cases

  1. 01Parse CSV with quoted commas
  2. 02Convert row data to CSV
  3. 03Reduce parsed data to selected columns

MCP support

Exposes CSV parsing, generation, and column-selection tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "mukundakatta-csv-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@mukundakatta/csv-tools-mcp"
      ]
    }
  }
}
Run commandnpx -y @mukundakatta/csv-tools-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@mukundakatta/csv-tools-mcp0.1.0

Tools

3

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
textstringYesRaw CSV text.
delimiterstringNoSingle-char delimiter.
has_headerbooleanNo

Details

From the project README

@mukundakatta/csv-tools-mcp

MCP server for reliable CSV parsing and generation. Three tools:

  • parse_csv(text, has_header?, delimiter?) — RFC 4180 parsing with proper handling of quoted fields, embedded commas, escaped double quotes (""), CRLF/LF, and a leading BOM. Returns headers + objects (or raw arrays).
  • to_csv(rows, headers?, delimiter?) — serialize arrays-of-arrays or arrays-of-objects with correct quoting.
  • pluck_columns(rows, columns) — reduce parsed rows to just the named columns.

Why this exists

LLMs ask for "the CSV parsed" and silently miss edge cases: a comma inside a quoted field, an escaped quote, a BOM that turns the first column header into name. Routing through this MCP server gives you state-machine-correct parsing instead of best-effort imagination.

Install — Claude Desktop

{
  "mcpServers": {
    "csv-tools": { "command": "npx", "args": ["-y", "@mukundakatta/csv-tools-mcp"] }
  }
}

Same shape for Cursor / Cline / Windsurf / Zed.

License

MIT OR Apache-2.0.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.