conved.com file converter

com.conved/mcpVersion 1.4.0

Convert files between hundreds of formats: documents, images, audio, e-books, fonts, GPS and more.

Status

Responds215 msNov 14, 2026, 13:52 UTCAnswered our handshake without sign-in.

Registry data may be out of date

We could not refresh it, so this page shows the last copy.

Last checked: Nov 14, 2026, 13:52 UTC
Latency: 215 ms
Remotes responding: 1 of 1
Sign-in: No sign-in
Hosting: EU hosting detected (detected, not a legal statement)
Registry data as of: Nov 14, 2026, 21:12 UTC

Data from the official MCP Registry, checked by run.zero. How we check

Connect

Streamable HTTP

https://www.conved.com/mcpResponds215 msNov 14, 2026, 13:52 UTC

No sign-in

Claude Code

claude mcp add --transport http conved https://www.conved.com/mcp

Claude Desktop and claude.ai

1
2
3

Settings > Connectors > Add custom connector
Name: conved
Remote MCP server URL: https://www.conved.com/mcp

Cursor

{
  "mcpServers": {
    "conved": {
      "url": "https://www.conved.com/mcp"
    }
  }
}

VS Code

code --add-mcp '{"name":"conved","type":"http","url":"https://www.conved.com/mcp"}'

Built your own server? run.zero hosts MCP servers on European infrastructure.

Host your own MCP server on run.zero

Tools

6 tools

Tools of conved.com file converter
	Description		Read-only	Idempotent	Open world
`convert`Convert one file to another format (one file in, one file out). Input – exactly one of: "url" (a public http(s) link), "text" + "filename" (source as text, e.g. Markdown, HTML, CSV, SVG; max 1 MB), "data_base64" + "filename" (a small binary file). For a file on the user's computer use create_upload (an upload page for the user, or curl if you can run commands). The source format comes from the extension of filename or of the URL path; pass "from" when there is none. For archiving or authorities use "to": "pdfa" (PDF/A-2b, scans get a text layer by OCR; the file is a .pdf and the done job carries "validation" – the result of an independent conformance check). There are no conversion options (quality, resolution, page range…) – defaults are used. A multi-page document converted to an image format gives the first page only (use "cbz" for all pages as images in a ZIP). To SEE a result you cannot read (PDF, DOCX, PPTX…), call convert again with its download_url as "url", "to": "png" and "return": "content" – you get an image of the first page. Returns the job: "done" with download_url (served by our conversion server hosting2.synetix.cz, valid until expires_at, 14 days), "waiting" (call get_job) or "error". Errors come back with isError and a code: invalid_arguments (fix the call), limit_reached (see get_account; wait, do not retry in a loop), file_too_large, unsupported_format (unknown source – pass "from" if the name has no extension), unsupported_target (call list_formats with "from"), download_failed (the URL is not publicly reachable), busy (too many downloads from URLs at once – retry in a few seconds), node_unavailable (retry later), not_found.	Convert one file to another format (one file in, one file out). Input – exactly one of: "url" (a public http(s) link), "text" + "filename" (source as text, e.g. Markdown, HTML, CSV, SVG; max 1 MB), "data_base64" + "filename" (a small binary file). For a file on the user's computer use create_upload (an upload page for the user, or curl if you can run commands). The source format comes from the extension of filename or of the URL path; pass "from" when there is none. For archiving or authorities use "to": "pdfa" (PDF/A-2b, scans get a text layer by OCR; the file is a .pdf and the done job carries "validation" – the result of an independent conformance check). There are no conversion options (quality, resolution, page range…) – defaults are used. A multi-page document converted to an image format gives the first page only (use "cbz" for all pages as images in a ZIP). To SEE a result you cannot read (PDF, DOCX, PPTX…), call convert again with its download_url as "url", "to": "png" and "return": "content" – you get an image of the first page. Returns the job: "done" with download_url (served by our conversion server hosting2.synetix.cz, valid until expires_at, 14 days), "waiting" (call get_job) or "error". Errors come back with isError and a code: invalid_arguments (fix the call), limit_reached (see get_account; wait, do not retry in a loop), file_too_large, unsupported_format (unknown source – pass "from" if the name has no extension), unsupported_target (call list_formats with "from"), download_failed (the URL is not publicly reachable), busy (too many downloads from URLs at once – retry in a few seconds), node_unavailable (retry later), not_found.	No	No	No	Yes
`create_upload`Get a file that is not at a public URL into a conversion to "to". Returns a one-time link (1 hour, one file, counts toward the limits like convert) in two forms: (1) upload_page – a web page where the USER picks the file in the browser; use it when the file is on the user's computer and you cannot run commands there (e.g. in a chat app): give the user the link, then call get_job with upload_id (wait_seconds up to 25, repeat while "waiting_for_upload"; a rejected file – wrong format, too large – is reported as last_error and the link stays valid for another file). (2) command – a curl command for when YOU have the file and can run shell commands (e.g. Claude Code): replace FILE with the path and run it; the shell must be able to reach https://www.conved.com (sandboxes often block outgoing connections). It prints the job as JSON. If the connection fails, fall back to data_base64 for a file of tens of kB, or to a public link. Use only one of the two forms – the link works once.	Get a file that is not at a public URL into a conversion to "to". Returns a one-time link (1 hour, one file, counts toward the limits like convert) in two forms: (1) upload_page – a web page where the USER picks the file in the browser; use it when the file is on the user's computer and you cannot run commands there (e.g. in a chat app): give the user the link, then call get_job with upload_id (wait_seconds up to 25, repeat while "waiting_for_upload"; a rejected file – wrong format, too large – is reported as last_error and the link stays valid for another file). (2) command – a curl command for when YOU have the file and can run shell commands (e.g. Claude Code): replace FILE with the path and run it; the shell must be able to reach https://www.conved.com (sandboxes often block outgoing connections). It prints the job as JSON. If the connection fails, fall back to data_base64 for a file of tens of kB, or to a public link. Use only one of the two forms – the link works once.	No	No	No	No
`get_account`The account e-mail and limits. plan: "free" (limit per hour) or "custom" (limit per 24 hours). hourLimit / usedHour count conversions in the last 60 minutes, dailyLimit / usedToday in the last 24 hours (rolling windows, not calendar days); maxFileMb is the maximum file size. 0 in any limit means no limit. Every conversion the server accepts counts, also one that fails later; rejected requests and the other tools do not.	The account e-mail and limits. plan: "free" (limit per hour) or "custom" (limit per 24 hours). hourLimit / usedHour count conversions in the last 60 minutes, dailyLimit / usedToday in the last 24 hours (rolling windows, not calendar days); maxFileMb is the maximum file size. 0 in any limit means no limit. Every conversion the server accepts counts, also one that fails later; rejected requests and the other tools do not.	No	Yes	Yes	No
`get_job`Status of a conversion: "waiting", "done" (with download_url and expires_at; for "to": "pdfa" also "validation" – the PDF/A-2b conformance check by an independent validator: compliant, failed_rules, issues) or "error" (with an error code, e.g. timeout, killed, tool_error, empty_output, unsupported, source_unavailable, no_audio, signed_pdf / encrypted_pdf (to pdfa: a signed or password-protected PDF – tell the user why), password_protected (the source cannot be opened without its password), expired, not_found). Pass "id" from convert, or "upload_id" from create_upload – before the file is uploaded the status is "waiting_for_upload" (with wait_seconds it waits for the upload too). Does not count toward limits.	Status of a conversion: "waiting", "done" (with download_url and expires_at; for "to": "pdfa" also "validation" – the PDF/A-2b conformance check by an independent validator: compliant, failed_rules, issues) or "error" (with an error code, e.g. timeout, killed, tool_error, empty_output, unsupported, source_unavailable, no_audio, signed_pdf / encrypted_pdf (to pdfa: a signed or password-protected PDF – tell the user why), password_protected (the source cannot be opened without its password), expired, not_found). Pass "id" from convert, or "upload_id" from create_upload – before the file is uploaded the status is "waiting_for_upload" (with wait_seconds it waits for the upload too). Does not count toward limits.	No	Yes	Yes	No
`list_formats`Which formats conved.com converts. Prefer "from" (a format id or file extension, e.g. "docx", "heic"): the target formats for that source. Without arguments: the categories and their number of formats; with "category": the formats of that category (id → name). There are hundreds of formats, so avoid listing everything.	Which formats conved.com converts. Prefer "from" (a format id or file extension, e.g. "docx", "heic"): the target formats for that source. Without arguments: the categories and their number of formats; with "category": the formats of that category (id → name). There are hundreds of formats, so avoid listing everything.	No	Yes	Yes	No
`list_jobs`Recent conversions, newest first (id, file name, formats, status, time): those made through this connection (with a personal API token: all API conversions of the account). Use get_job for the download link.	Recent conversions, newest first (id, file name, formats, status, time): those made through this connection (with a personal API token: all API conversions of the account). Use get_job for the download link.	No	Yes	Yes	No

Details

Registry status: Active
Published: Oct 12, 2026
Updated: Oct 12, 2026
Website: https://www.conved.com/ai⁠ (opens in a new tab)
Repository: Not given
Categories (suggested): Design and mediaSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared

Are you the operator? Claim this listing