Search / dev.pdfmd/pdf-to-markdown
protogridR0· no sign-inConvert public PDF links into Markdown with page counts and explicit excerpt limits.
v1.0.1 · active · website · descriptor JSON · versions
{
"mcpServers": {
"pdf-to-markdown": {
"type": "http",
"url": "https://pdfmd.dev/mcp"
}
}
}claude mcp add --transport http pdf-to-markdown https://pdfmd.dev/mcp[mcp_servers.pdf-to-markdown]
url = "https://pdfmd.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"pdf-to-markdown": {
"type": "remote",
"url": "https://pdfmd.dev/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"pdf-to-markdown": {
"type": "http",
"url": "https://pdfmd.dev/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=pdf-to-markdown&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vcGRmbWQuZGV2L21jcCJ9"
}{
"servers": {
"pdf-to-markdown": {
"type": "http",
"url": "https://pdfmd.dev/mcp"
}
}
}{
"mcpServers": {
"pdf-to-markdown": {
"httpUrl": "https://pdfmd.dev/mcp"
}
}
}extensions:
"pdf-to-markdown":
enabled: true
name: "pdf-to-markdown"
type: streamable_http
uri: "https://pdfmd.dev/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_lengthdescriptions are concisetools.schemasevery tool has an object input schematools.annotations1 of 1 tools declare readOnlyHint or destructiveHinttools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHinttools.token_costabout 228 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes5 tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI packageconvert_pdf_urlchangeddescription, input schema, output schemaUse when someone asks to read, quote or summarize a PDF that sits at a public web link, or wants it as Markdown for research or a coding project. Returns extracted text, page and table counts, and whether scanned pages were found. It does not OCR scanned pages and it cannot open private links or local files. The reply holds at most 20,000 Markdown characters and marks a longer result as an excerpt; the whole PDF counts toward the API page allowance.
Use when someone asks to read, quote or summarize a PDF that sits at a public web link, or wants it as Markdown or HTML for research or a coding project. Returns extracted text, page and table counts, and whether scanned pages were found. It does not OCR scanned pages and it cannot open private links or local files. The reply holds at most 20,000 Markdown characters and marks a longer result as an excerpt; the whole PDF counts toward the API page allowance.
convert_pdf_urlchangeddescription, annotationsConvert a PDF available at a public HTTP or HTTPS link into Markdown for reading, research or a coding project. Returns extracted text, page and table counts, and whether scanned pages were found. No OCR, private links or local files. The reply is limited to 20,000 Markdown characters and marks longer results as excerpts; the whole PDF uses the API page allowance.
Use when someone asks to read, quote or summarize a PDF that sits at a public web link, or wants it as Markdown for research or a coding project. Returns extracted text, page and table counts, and whether scanned pages were found. It does not OCR scanned pages and it cannot open private links or local files. The reply holds at most 20,000 Markdown characters and marks a longer result as an excerpt; the whole PDF counts toward the API page allowance.
convert_pdf_urlchangedoutput schemaconvert_pdf_urlchangedoutput schemaconvert_pdf_urlchangedannotationsFull history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+dns-namespace +website +reachable +uptime-100% +updated-9d-ago -no-repository
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://pdfmd.dev/mcp streamable-http | none | yes | 100% | 425 ms | 2025-11-25 | 2026-10-20 |
convert_pdf_urlread-only | Use when someone asks to read, quote or summarize a PDF that sits at a public web link, or wants it as Markdown or HTML for research or a coding project. Returns extracted text, page and table counts, and whether scanned pages were found. It does not OCR scanned pages and it cannot open private links or local files. The reply holds at most 20,000 Markdown characters and marks a longer result as an excerpt; the whole PDF counts toward the API page allowance. |
Schemas: list_tools.
{
"name": "dev.pdfmd/pdf-to-markdown",
"icons": [
{
"src": "https://pdfmd.dev/brand/icon-512x512.png",
"sizes": [
"512x512"
],
"mimeType": "image/png"
}
],
"title": "PDF to Markdown",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://pdfmd.dev/mcp",
"type": "streamable-http"
}
],
"version": "1.0.1",
"websiteUrl": "https://pdfmd.dev/docs?utm_source=mcp&utm_medium=registry#agents",
"description": "Convert public PDF links into Markdown with page counts and explicit excerpt limits."
}