# truecopy MCP server

> Extracts tables, figures, and dates from PDFs, Word files, CSVs, or text with built-in validation to detect reading errors.

- Repository: https://github.com/truecopydev/truecopy
- Page: https://hostedmcp.org/servers/truecopydev/truecopy
- Transport: stdio
- Stars: 3
- License: MIT
- Latest version: 2.0.24

## Install

### Claude Code

```sh
claude mcp add truecopy -- npx -y truecopy
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "truecopy": {
      "command": "npx",
      "args": [
        "-y",
        "truecopy"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "truecopy": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "truecopy"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"truecopy","type":"stdio","command":"npx","args":["-y","truecopy"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "truecopy": {
      "command": "npx",
      "args": [
        "-y",
        "truecopy"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add truecopy -- npx -y truecopy
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.truecopy]
command = "npx"
args = ["-y", "truecopy"]
```

### Gemini CLI

```sh
gemini mcp add -s user truecopy npx -- -y truecopy
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "truecopy": {
      "command": "npx",
      "args": [
        "-y",
        "truecopy"
      ]
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `TRUECOPY_MCP_ROOT` | no | no | A directory the server may not read outside of, symbolic links resolved. Unset, it reads what the account running it can read. |

## Tools (4)

- `read_table`: Read a PDF, a CSV, a TSV or a saved paste on this machine into rows, and say what the reading cannot vouch for. Returns the cut into columns, what each column holds, the rows numbered for check_citations, and the doubts. An empty list of doubts is NOT a promise that the reading is right: it means nothing looked wrong from the shape of the page. The file is read on this machine and never uploaded. (read-only)
- `find_amounts`: Find every figure written with a given number of decimals in a document on this machine: the value, the characters as printed, and the row and column they sit in, numbered as read_table numbers them. Two decimals is how a page tells a sum of money from a reference number without knowing what money is; ask for 0 decimals to take every number. The answer opens with the verdict of the reading, reliable, doubtful or unreadable, and reliable only means nothing looked wrong. What a figure MEANS - a debit, a balance, a date written as digits - is not read here: that is the reading, and check_citations is how a claim about it is checked. The file is read on this machine and never uploaded. (read-only)
- `find_dates`: Find every cell that starts with a date in a document on this machine: the calendar date, the characters as printed, and the row and column they sit in, numbered as read_table numbers them. The order of day and month is STATED, never guessed: there is no reading of 01/02/2026 that is right everywhere. A row that prints a day and a month without a year is a date only when the year is given, which is how a statement dates its rows. The answer opens with the verdict of the reading, reliable, doubtful or unreadable, and reliable only means nothing looked wrong. The file is read on this machine and never uploaded. (read-only)
- `check_citations`: Verify that every value really appears in the rows it cites. A model turning cells into records fails one visible way, it misses a record, and one invisible way: it returns a plausible value the document never printed - a town deduced from a postcode, a rounded figure, a recomposed date - which reads exactly like a successful extraction. Each value is looked up in the cited rows and NOWHERE else, so nothing can be produced, only pointed at. A JSON number is checked as a figure, a JSON string as its words in order. Cite the row numbers read_table returned, for the same file and the same maximumPages: a different page bound is a different reading, and its rows are numbered differently. Pass back the digest read_table returned, and a file changed since is refused rather than checked against rows it no longer has. (read-only)

## FAQ

### What file formats does truecopy support?

It can read PDF, Word, OpenDocument, CSV, TSV, OCR pages, or even text that has been pasted.

### How does truecopy handle unreliable data extraction?

It provides warnings and findings that identify columns that are mostly empty, pages that disagree on column counts, or other structural anomalies.

### Do I need to install a PDF reader to use it?

No, the PDF engine is an optional peer dependency; if you only process CSVs or pasted text, you don't need to download a PDF reader.

### Can it handle different number and date formats?

Yes, it includes notation utilities to handle various accounting negatives, decimal separators, and date orders.

### Does it require a headless browser?

No, the output is text-based and works in terminals, CI logs, or bug reports without needing a canvas or browser.
