Connect doc-convert-mcp and your agent gets 4 tools, among them ocr_image, parse_spreadsheet, pdf_to_markdown. It answers at https://convert.ioconnex.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 26 September 2026; the last check, on 9 November 2026, succeeded.
Document conversion and OCR for AI agents: PDF, Office docs, images to text.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ocr_image | Run OCR on an image (base64-encoded bytes) and return recognized text. Inputs: image_base64, lang |
parse_spreadsheet | Parse a CSV or XLSX file (base64-encoded bytes) into Markdown tables. Inputs: file_base64, filename |
pdf_to_markdown | Convert a PDF (base64-encoded bytes) to Markdown, one section per page. Inputs: pdf_base64, max_pages |
url_to_clean_text | Fetch a public http(s) URL and return its main text content as plain text. Inputs: url |
Every block below points at https://convert.ioconnex.dev/mcp. Pick your client and copy.
claude mcp add --transport http doc-convert-mcp https://convert.ioconnex.dev/mcp
{
"mcpServers": {
"doc-convert-mcp": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://convert.ioconnex.dev/mcp"]
}
}
}{
"mcpServers": {
"doc-convert-mcp": {
"url": "https://convert.ioconnex.dev/mcp"
}
}
}{
"servers": {
"doc-convert-mcp": {
"type": "http",
"url": "https://convert.ioconnex.dev/mcp"
}
}
}{
"context_servers": {
"doc-convert-mcp": {
"url": "https://convert.ioconnex.dev/mcp"
}
}
}{
"mcpServers": {
"doc-convert-mcp": {
"serverUrl": "https://convert.ioconnex.dev/mcp"
}
}
}{
"mcpServers": {
"doc-convert-mcp": {
"url": "https://convert.ioconnex.dev/mcp"
}
}
}name: doc-convert-mcp
version: 0.0.1
schema: v1
mcpServers:
- name: doc-convert-mcp
type: streamable-http
url: https://convert.ioconnex.dev/mcp{
"mcpServers": {
"doc-convert-mcp": {
"httpUrl": "https://convert.ioconnex.dev/mcp"
}
}
}{
"mcpServers": {
"doc-convert-mcp": {
"type": "http",
"url": "https://convert.ioconnex.dev/mcp"
}
}
}{
"mcpServers": {
"doc-convert-mcp": {
"url": "https://convert.ioconnex.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fconvert.ioconnex.dev%2Fmcp&type=streamable_http&id=doc-convert-mcp&name=doc-convert-mcp
It answered our last check on 9 November 2026 in 439 ms. Over 4 checks since 26 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by ioconnex.dev and served from convert.ioconnex.dev, the vendor's own domain: https://convert.ioconnex.dev/mcp.
4, as returned by the server's own tools/list on 16 November 2026: ocr_image, parse_spreadsheet, pdf_to_markdown, url_to_clean_text.
It answered our last check on 9 November 2026 in 439 ms. Over 4 checks since 26 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://convert.ioconnex.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.ioconnex. Endpoint host: convert.ioconnex.dev. ARD identifier: urn:air:dev.ioconnex:mcp:doc-convert-mcp.
First indexed 25 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.