Agents read Markdown far better than they read PDFs, slide decks or spreadsheets. Getting a document into that shape usually means leaving the conversation, opening a converter, downloading the result and pasting it back. The MCP server removes those four steps: the agent calls a tool and receives the converted file on disk.
What it exposes
Two tools, and deliberately only two.
list_conversionsanswers what a given format can become, read from the same table the website serves.convert_fileconverts one local file and returns the path it wrote.
Both run on the same credit balance as the website. A conversion started by an agent and one started in a browser cost the same and draw from the same account.
Try one local HTML file
Sign up or sign in to your dashboard, create an API key, and save it when it is shown. Configure your MCP client with the example below, then restart the client. Node.js 20 or later is required.
Create field-notes.html on the machine running the server,
with a heading, a short reading and two action items. Ask your agent to
call list_conversions with extension: "html",
confirm md is listed, then call convert_file with
the absolute file path and target: "md". The server reports
the output path. Open that file and check the heading, reading and both
action items before using it.
In the verified example, a fresh ordinary Free account started with 50 credits. HTML to Markdown cost 0.5 credit through the MCP server, the same as the identical conversion with an ordinary website session. The two outputs matched: a 151-byte Markdown file preserving the heading, 42-centimetre reading and both list items. Listing supported targets did not debit credits. This is one small HTML example, not a quality guarantee for every document.
Without output_path, the result goes beside the input with
the new extension. If that name exists, a numbered name is used. An
explicit output_path overwrites an existing file at that path.
Choose a destination you are ready to replace.
What it does not do
This list matters more than the one above, because the opposite claim is easy to make by accident. There is no batch mode, no webhooks, no job polling, no queue, no streaming, and no URL input. It converts one local file per call and waits for the answer. There is no public HTTP API and no command-line tool either: the server speaks stdio to a local agent, which is a different thing.
Where your key lives
The API key is read from the server environment. It is never a tool argument, and the server does not write it to an output file. Keep the client configuration private and revoke a key in your dashboard if it is exposed. The plaintext key is shown once when you create it; only its hash is stored, so nobody can recover it for you, us included.
What it can convert
162 input formats and 3,649 conversions, each one proven by running it and reading the output back rather than by trusting a compatibility table. Documents, images, audio, video, ebooks, subtitles, archives, fonts, data files and bibliographies. File limits depend on your account plan and the conversion family. The server's local ceiling is 150 MB; this is not an allowance for every format or plan. Free accounts have a 10 MB file limit, and document conversions have a 25 MB family limit. Larger eligible inputs use the storage upload path above 4 MB.