file2markdown is an MCP server published by ai.file2markdown, hosted at mcp.file2markdown.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 5 tools, including convert_url, convert_base64, convert_batch, list_supported_formats, usage_status.
Convert docs and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scans, URLs. Batch of 10.
12 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Fetch a URL (web page, PDF, Office doc, and more) and convert it to Markdown. Works on publicly accessible URLs. Web pages are converted from their served HTML; JavaScript-rendered content may be incomplete. Optional filename_hint (e.g. "report.pdf") helps format detection when the URL has no file extension. The result carries a `quality` object (output-health check of the returned Markdown: status review / no_issues_detected / not_evaluated, coverage and a list of issues with line locations). quality_check="basic" (default) runs only local deterministic checks. quality_check="ai" additionally sends selected excerpts of the CONVERTED text to TypeSafe for narrow yes/no judgments (garbled text, hard-wrapped prose, broken tables); it is off unless requested. No check compares against the source document.
| Parameter | Type | Description |
|---|---|---|
| url * | string | |
| filename_hint | any | |
| quality_check | string |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "convert_url",
"description": "Fetch a URL (web page, PDF, Office doc, and more) and convert it to Markdown.\n\n Works on publicly accessible URLs. Web pages are converted from their\n served HTML; JavaScript-rendered content may be incomplete. Optional\n filename_hint (e.g. \"report.pdf\") helps format detection when the URL\n has no file extension.\n\n The result carries a `quality` object (output-health check of the returned\n Markdown: status review / no_issues_detected / not_evaluated, coverage and\n a list of issues with line locations). quality_check=\"basic\" (default)\n runs only local deterministic checks. quality_check=\"ai\" additionally\n sends selected excerpts of the CONVERTED text to TypeSafe for narrow\n yes/no judgments (garbled text, hard-wrapped prose, broken tables); it is\n off unless requested. No check compares against the source document.\n ",
"inputSchema": {
"type": "object",
"title": "convert_urlArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
},
"filename_hint": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Filename Hint",
"default": null
},
"quality_check": {
"type": "string",
"title": "Quality Check",
"default": "basic"
}
}
}
}Convert base64-encoded file contents to Markdown. filename is required and drives format detection (e.g. "report.docx"). Intended for programmatic MCP clients; for anything with a URL, prefer convert_url. quality_check: "basic" (default) attaches local output-health checks in the `quality` field; "ai" additionally sends selected excerpts of the converted text to TypeSafe for narrow yes/no judgments. See convert_url.
| Parameter | Type | Description |
|---|---|---|
| filename * | string | |
| quality_check | string | |
| content_base64 * | string |
{
"name": "convert_base64",
"description": "Convert base64-encoded file contents to Markdown.\n\n filename is required and drives format detection (e.g. \"report.docx\").\n Intended for programmatic MCP clients; for anything with a URL, prefer\n convert_url.\n\n quality_check: \"basic\" (default) attaches local output-health checks in\n the `quality` field; \"ai\" additionally sends selected excerpts of the\n converted text to TypeSafe for narrow yes/no judgments. See convert_url.\n ",
"inputSchema": {
"type": "object",
"title": "convert_base64Arguments",
"required": [
"content_base64",
"filename"
],
"properties": {
"filename": {
"type": "string",
"title": "Filename"
},
"quality_check": {
"type": "string",
"title": "Quality Check",
"default": "basic"
},
"content_base64": {
"type": "string",
"title": "Content Base64"
}
}
}
}Convert 2-10 documents to Markdown in one call (Pro API key required). Each item is either {"url": ..., "filename_hint"?: ...} or {"content_base64": ..., "filename": ...}; types may be mixed. Items are converted in parallel and isolated: one bad URL or file never fails the batch — its slot returns ok:false with the error. The combined markdown shares one output budget, split evenly across items (per-item `truncated` flags apply). Set include_markdown=false to get only metadata + quality per item (health-check a folder without flooding your context). Anonymous callers: use convert_url / convert_base64 individually.
| Parameter | Type | Description |
|---|---|---|
| items * | array | |
| quality_check | string | |
| include_markdown | boolean |
{
"name": "convert_batch",
"description": "Convert 2-10 documents to Markdown in one call (Pro API key required).\n\n Each item is either {\"url\": ..., \"filename_hint\"?: ...} or\n {\"content_base64\": ..., \"filename\": ...}; types may be mixed. Items are\n converted in parallel and isolated: one bad URL or file never fails the\n batch — its slot returns ok:false with the error. The combined markdown\n shares one output budget, split evenly across items (per-item `truncated`\n flags apply). Set include_markdown=false to get only metadata + quality\n per item (health-check a folder without flooding your context).\n\n Anonymous callers: use convert_url / convert_base64 individually.\n ",
"inputSchema": {
"type": "object",
"title": "convert_batchArguments",
"required": [
"items"
],
"properties": {
"items": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Items"
},
"quality_check": {
"type": "string",
"title": "Quality Check",
"default": "basic"
},
"include_markdown": {
"type": "boolean",
"title": "Include Markdown",
"default": true
}
}
}
}List supported input formats, per-tier limits, and which features need Pro. Single source of truth — do not claim capabilities beyond what this returns.
No parameters.
{
"name": "list_supported_formats",
"description": "List supported input formats, per-tier limits, and which features need Pro.\n\n Single source of truth — do not claim capabilities beyond what this\n returns.\n ",
"inputSchema": {
"type": "object",
"title": "list_supported_formatsArguments",
"properties": {}
}
}Check your tier and remaining conversions before burning a call.
No parameters.
{
"name": "usage_status",
"description": "Check your tier and remaining conversions before burning a call.",
"inputSchema": {
"type": "object",
"title": "usage_statusArguments",
"properties": {}
}
}Convert documents and web pages to clean Markdown. Use convert_url for anything reachable by URL (web pages, PDFs, Office files); convert_base64 for local file contents. Anonymous callers get 5 conversions/day per network; a Pro API key removes the limit, enables OCR for scanned PDFs and images, and unlocks convert_batch (2-10 documents in one call). Keys: https://www.file2markdown.ai/account
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.