# PDF to Markdown

> Convert public PDF links into Markdown with page counts and explicit excerpt limits.

- name: dev.pdfmd/pdf-to-markdown
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/dev.pdfmd%2Fpdf-to-markdown
- tools: https://api.protogrid.dev/v1/servers/dev.pdfmd%2Fpdf-to-markdown/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "pdf-to-markdown": {
      "type": "http",
      "url": "https://pdfmd.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +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.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 1 of 1 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 228 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 1, about 228 tokens to load them all
- tool set hash: 75061879ceaed6fa15e5d094e1ac34a4
- tools last changed: 2026-10-15T07:51:04.693Z
- badge: [![protogrid quality](https://protogrid.dev/badge/dev.pdfmd/pdf-to-markdown.svg)](https://protogrid.dev/servers/dev.pdfmd/pdf-to-markdown)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-15 `convert_pdf_url` changed (description, inputSchema, outputSchema)
  - before: 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.
  - after: 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.
- 2026-10-08 `convert_pdf_url` changed (description, annotations)
  - before: Convert 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.
  - after: 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.
- 2026-10-07 `convert_pdf_url` changed (outputSchema)
- 2026-10-07 `convert_pdf_url` changed (outputSchema)
- 2026-10-06 `convert_pdf_url` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/dev.pdfmd%2Fpdf-to-markdown/changes

## Remotes

- https://pdfmd.dev/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (1)

- `convert_pdf_url`: 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.