Docling-rs MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --http | No | Serve the MCP server over Streamable HTTP instead of stdio. | false |
| --root | No | Directory under which local file reads are restricted. | |
| --allow-url-fetch | No | Allow fetching documents from URLs. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| convertB | Convert a document (URI or path, as convert_to_markdown) to Markdown, docling JSON, HTML, plain text, LaTeX, RAG chunks, WebVTT or Pandoc JSON, with docling.rs's conversion options (page ranges, OCR language and mode, text-layer-only PDFs, passwords, picture OCR, …). |
| convert_to_markdownB | Convert a resource described by an http:, https:, file: or data: URI (or a local path) to Markdown — PDFs with layout analysis, table structure and OCR; Word, PowerPoint, Excel, HTML, EPUB, e-mail, images, audio and more. MarkItDown's tool of the same name. |
| list_input_formatsA | The input file extensions this server converts, one per line, and whether URL inputs are enabled. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
convert_to_markdown is essentially a subset of convert, which already lists Markdown among its output formats. An agent must guess whether to use the general tool or the specialized one, and the descriptions don't clarify when to prefer each.
Names mix conventions: list_input_formats follows verb_noun, convert is a bare verb, and convert_to_markdown uses verb_to_target. They are readable but do not form a predictable pattern.
Three tools is reasonable for a focused document-conversion server, covering format discovery and conversion without bloat. It is on the lean side but each tool has a plausible role.
Input format discovery plus flexible conversion covers the core domain well. Minor gaps exist (no output-format enumeration or batch/validation helpers), but agents can work around them.