com.filetypeconverters/converter

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Convert files between 44 formats: documents, spreadsheets, images, ebooks, email and subtitles.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "converter": {
      "url": "https://filetypeconverters.com/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (5)

• list_formats

  List every file format this converter reads or writes (id, name, extensions, family). Use the id values as `from`/`to` in other tools.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• check_conversion

  Check whether one format can be converted to another before sending a file. Returns the engine, whether AI Deep Read is needed, the options it accepts, and alternatives when the pair is not supported. Formats accept ids (docx), extensions (jpeg) or common names (word, excel).

  Parameters:

  • from (required) — string — Source format, e.g. pdf
  • to (required) — string — Target format, e.g. docx

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_conversions

  List supported target formats for a source format (or every source that can produce a target). Returns compact {from,to,slug,engine,mode} rows.

  Parameters:

  • to — string
  • from — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• convert_file

  Convert a file. Provide the content as base64 OR a public https URL. `from` is optional when the filename/URL has an extension. Text outputs (Markdown, CSV, JSON, HTML…) up to 200 KB are returned inline as `text`; other outputs are returned as `base64` plus a `downloadUrl` that accepts the same bearer token. Max 10 MB per file. Set `deepRead: true` to read scans, photos and handwriting with AI Deep Read (1 credit per page).

  Parameters:

  • to (required) — string — Target format id, e.g. md, docx, xlsx, png
  • url — string — Public https URL of the file (alternative to base64)
  • from — string — Source format id; detected from the filename when omitted
  • base64 — string — File bytes, base64-encoded
  • options — object — Engine options from check_conversion (delimiter, sheet, quality, …)
  • deepRead — boolean — Use AI Deep Read (OCR + layout understanding) for PDFs and images
  • filename — string — Original filename with extension, e.g. report.pdf

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_conversion

  Fetch a previous conversion by id: status, warnings, and the output (inline text or base64) if it is still retained.

  Parameters:

  • id (required) — string

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.