docling-rs-mcp 2.22.0__tar.gz

docling_rs_mcp-2.22.0/.gitignore

@@ -0,0 +1,51 @@
+/target
+
+# Stray CLI conversion outputs (`docling-rs --to dclx <file>` writes next to CWD)
+/*.dclx
+
+# ONNX Runtime profiler output (written to CWD when session profiling is on)
+onnxruntime_profile_*.json
+
+# wasm-bindgen output for the docling-wasm demo (built from source, see its README)
+crates/docling-wasm/www/pkg/
+# ML models the scan demo fetches same-origin (download_dependencies.sh, run in www/)
+crates/docling-wasm/www/models/
+crates/docling-wasm/www/.models/
+
+# Secrets — never commit (holds CARGO_REGISTRY_TOKEN)
+.env
+.env.*
+# …but the documented template for docling-rag config is committed.
+!.env.example
+
+# Local RAG vector store (default RAG_DATABASE_URL=sqlite://data/rag.db)
+/data/
+
+# Python virtual environments (venv) — not committed, but can be created from requirements.txt
+/.venv*
+
+# Downloaded native libs / models (not committed)
+.pdfium/
+*.onnx
+.models/
+
+# Python bytecode cache from the comparison scripts
+__pycache__/
+*.pyc
+
+# Local docling scratch dir for this migration work
+/scratch-gt/
+
+# Benchmarks for GPU (not committed, large and reproducible)
+/bench-gpu/
+
+# docling-py is a standalone crate (own workspace) — its build dirs
+crates/docling-py/target/
+crates/docling-py/.venv/
+crates/docling-py/python/docling_rs/*.so
+
+# docling's .dclx loader extracts each archive it reads next to the file
+tests/data/**/*_artifacts/
+tests/data/**/groundtruth_dclx/tests/
+# docling-parse renderer plugin (#478, scripts/install/build_docling_parse_render.sh)
+.docling-parse/

docling_rs_mcp-2.22.0/PKG-INFO

@@ -0,0 +1,87 @@
+Metadata-Version: 2.5
+Name: docling-rs-mcp
+Version: 2.22.0
+Summary: MCP server that converts documents to Markdown for AI agents: PDF with layout, tables and OCR, DOCX, PPTX, XLSX, HTML, scans. docling in Rust, MarkItDown's convert_to_markdown tool.
+Project-URL: Homepage, https://github.com/docling-project/docling.rs
+Project-URL: Repository, https://github.com/docling-project/docling.rs
+Project-URL: Documentation, https://github.com/docling-project/docling.rs/blob/master/crates/docling-cli/README.md#mcp-server--docling-rs-mcp
+Project-URL: Issues, https://github.com/docling-project/docling.rs/issues
+License: MIT
+Keywords: claude,docling,document-conversion,llm,markitdown,markitdown-mcp,mcp,mcp-server,model-context-protocol,ocr,pdf-to-markdown,rag
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Rust
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Text Processing :: Markup :: Markdown
+Requires-Python: >=3.9
+Requires-Dist: docling-rs==2.22.0
+Description-Content-Type: text/markdown
+
+# docling-rs-mcp
+
+<!-- mcp-name: io.github.docling-project/docling-rs -->
+
+A [Model Context Protocol](https://modelcontextprotocol.io) server that
+converts documents to Markdown for AI agents — PDF with layout analysis,
+table structure and OCR, DOCX, PPTX, XLSX, HTML, EPUB, e-mail, scans and
+40-odd other formats. It is [docling.rs](https://github.com/docling-project/docling.rs),
+a Rust port of IBM's [docling](https://github.com/docling-project/docling),
+and it serves **MarkItDown's `convert_to_markdown(uri)` tool** under the same
+name and contract: a `markitdown-mcp` setup switches by changing the command.
+
+```bash
+uvx docling-rs-mcp --root ~/Documents
+```
+
+Claude Desktop (`claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "docling": { "command": "uvx", "args": ["docling-rs-mcp", "--root", "/Users/me/Documents"] }
+  }
+}
+```
+
+Claude Code: `claude mcp add docling -- uvx docling-rs-mcp --root ~/Documents`.
+
+## Tools
+
+| Tool | Returns |
+|---|---|
+| `convert_to_markdown(uri)` | Markdown of the document behind an `http:`/`https:`/`file:`/`data:` URI or a path |
+| `convert(uri, to?, images?, options?)` | `md`, `json` (docling's `DoclingDocument`), `html`, `text`, `latex`, `chunks`, `vtt` or `pandoc`, with docling.rs's [conversion options](https://github.com/docling-project/docling.rs/blob/master/docs/OPTIONS.md) — `{"pages": "1-5"}`, `{"ocr_lang": "ch"}`, `{"password": "…"}`, … |
+| `list_input_formats()` | the extensions the server converts |
+
+## PDF models
+
+Office, HTML, Markdown and e-mail need no models. PDFs and images use
+ONNX models for layout, tables and OCR (~720 MB). Fetch them once:
+
+```bash
+uvx docling-rs-mcp --download-models
+```
+
+They land in the docling.rs cache (`$DOCLING_RS_CACHE_DIR`, else
+`~/.cache/docling.rs`) and the server finds them from then on;
+`--download-models=all` adds the code/formula enrichment models (~740 MB
+more). Until then PDFs convert from their text layer, as MarkItDown's do.
+
+## What a call may reach
+
+Local paths and `file:` URIs are confined to `--root` (repeatable; the
+working directory by default, except in `/`, where it is required).
+`http(s)` URLs are fetched only with
+`--allow-url-fetch`, and private or loopback addresses stay blocked.
+`--http` serves Streamable HTTP on `127.0.0.1:3001` instead of stdio.
+`--help` lists every flag; the security model is in
+[docs/SECURITY.md](https://github.com/docling-project/docling.rs/blob/master/docs/SECURITY.md#docling-rs-mcp-model-context-protocol-server-669).
+
+The same server ships in the `docling-rs` binary (`docling-rs mcp`) and the
+`ghcr.io/docling-project/docling-rs` image, models included; with the
+`docling-rs` Python package installed it is also `python -m docling_rs.mcp`.
+On NVIDIA GPUs, `uv run --with docling-rs-cuda python -m docling_rs.mcp`.
+
+MIT licensed.

docling_rs_mcp-2.22.0/README.md

@@ -0,0 +1,66 @@
+# docling-rs-mcp
+
+<!-- mcp-name: io.github.docling-project/docling-rs -->
+
+A [Model Context Protocol](https://modelcontextprotocol.io) server that
+converts documents to Markdown for AI agents — PDF with layout analysis,
+table structure and OCR, DOCX, PPTX, XLSX, HTML, EPUB, e-mail, scans and
+40-odd other formats. It is [docling.rs](https://github.com/docling-project/docling.rs),
+a Rust port of IBM's [docling](https://github.com/docling-project/docling),
+and it serves **MarkItDown's `convert_to_markdown(uri)` tool** under the same
+name and contract: a `markitdown-mcp` setup switches by changing the command.
+
+```bash
+uvx docling-rs-mcp --root ~/Documents
+```
+
+Claude Desktop (`claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "docling": { "command": "uvx", "args": ["docling-rs-mcp", "--root", "/Users/me/Documents"] }
+  }
+}
+```
+
+Claude Code: `claude mcp add docling -- uvx docling-rs-mcp --root ~/Documents`.
+
+## Tools
+
+| Tool | Returns |
+|---|---|
+| `convert_to_markdown(uri)` | Markdown of the document behind an `http:`/`https:`/`file:`/`data:` URI or a path |
+| `convert(uri, to?, images?, options?)` | `md`, `json` (docling's `DoclingDocument`), `html`, `text`, `latex`, `chunks`, `vtt` or `pandoc`, with docling.rs's [conversion options](https://github.com/docling-project/docling.rs/blob/master/docs/OPTIONS.md) — `{"pages": "1-5"}`, `{"ocr_lang": "ch"}`, `{"password": "…"}`, … |
+| `list_input_formats()` | the extensions the server converts |
+
+## PDF models
+
+Office, HTML, Markdown and e-mail need no models. PDFs and images use
+ONNX models for layout, tables and OCR (~720 MB). Fetch them once:
+
+```bash
+uvx docling-rs-mcp --download-models
+```
+
+They land in the docling.rs cache (`$DOCLING_RS_CACHE_DIR`, else
+`~/.cache/docling.rs`) and the server finds them from then on;
+`--download-models=all` adds the code/formula enrichment models (~740 MB
+more). Until then PDFs convert from their text layer, as MarkItDown's do.
+
+## What a call may reach
+
+Local paths and `file:` URIs are confined to `--root` (repeatable; the
+working directory by default, except in `/`, where it is required).
+`http(s)` URLs are fetched only with
+`--allow-url-fetch`, and private or loopback addresses stay blocked.
+`--http` serves Streamable HTTP on `127.0.0.1:3001` instead of stdio.
+`--help` lists every flag; the security model is in
+[docs/SECURITY.md](https://github.com/docling-project/docling.rs/blob/master/docs/SECURITY.md#docling-rs-mcp-model-context-protocol-server-669).
+
+The same server ships in the `docling-rs` binary (`docling-rs mcp`) and the
+`ghcr.io/docling-project/docling-rs` image, models included; with the
+`docling-rs` Python package installed it is also `python -m docling_rs.mcp`.
+On NVIDIA GPUs, `uv run --with docling-rs-cuda python -m docling_rs.mcp`.
+
+MIT licensed.

docling_rs_mcp-2.22.0/pyproject.toml

@@ -0,0 +1,44 @@
+# PyPI distribution `docling-rs-mcp`: what `uvx docling-rs-mcp` installs and
+# runs (#669), like MarkItDown's `markitdown-mcp`. It has no server code of
+# its own — the server is `docling_rs.mcp`, the one `docling-rs mcp` runs,
+# compiled into the docling-rs wheel — so this package only pins that wheel
+# and names the command. pypi-publish.yml writes the release version into
+# `version` and into the docling-rs pin before building; the committed
+# values are placeholders (install locally with `pip install --no-deps`).
+[build-system]
+requires = ["hatchling>=1.24"]
+build-backend = "hatchling.build"
+
+[project]
+name = "docling-rs-mcp"
+version = "2.22.0"
+description = "MCP server that converts documents to Markdown for AI agents: PDF with layout, tables and OCR, DOCX, PPTX, XLSX, HTML, scans. docling in Rust, MarkItDown's convert_to_markdown tool."
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.9"
+keywords = [
+    "mcp", "model-context-protocol", "mcp-server", "markitdown", "markitdown-mcp",
+    "docling", "pdf-to-markdown", "document-conversion", "ocr", "claude", "llm", "rag",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Rust",
+    "Topic :: Text Processing :: Markup :: Markdown",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = ["docling-rs==2.22.0"]
+
+[project.scripts]
+docling-rs-mcp = "docling_rs_mcp:main"
+
+[project.urls]
+Homepage = "https://github.com/docling-project/docling.rs"
+Repository = "https://github.com/docling-project/docling.rs"
+Documentation = "https://github.com/docling-project/docling.rs/blob/master/crates/docling-cli/README.md#mcp-server--docling-rs-mcp"
+Issues = "https://github.com/docling-project/docling.rs/issues"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/docling_rs_mcp"]

docling_rs_mcp-2.22.0/src/docling_rs_mcp/__init__.py

@@ -0,0 +1,6 @@
+"""``uvx docling-rs-mcp``: the docling.rs MCP server. The server itself is
+:mod:`docling_rs.mcp` in the docling-rs package; this one names the command."""
+
+from docling_rs.mcp import main
+
+__all__ = ["main"]

docling_rs_mcp-2.22.0/src/docling_rs_mcp/__main__.py

@@ -0,0 +1,3 @@
+from docling_rs.mcp import main
+
+main()