doc-index-mcp 0.1.0__tar.gz

doc_index_mcp-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,47 @@
+name: Build and Publish
+
+on:
+  push:
+    tags:
+      - "v*"
+
+permissions:
+  id-token: write
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run tests
+        run: uv run pytest src/tests/ -v
+
+      - name: Build package
+        run: uv build
+
+      - name: Upload artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    steps:
+      - name: Download artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

doc_index_mcp-0.1.0/.github/workflows/test.yml

@@ -0,0 +1,23 @@
+name: Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run tests
+        run: uv run pytest src/tests/ -v

doc_index_mcp-0.1.0/.gitignore

@@ -0,0 +1,54 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+.venv/
+venv/
+ENV/
+env/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# Doc index data (user-specific)
+.docindex/
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+
+# Test fixture PDFs (large, downloaded at test time)
+tests/fixtures/*.pdf
+
+# Demo artifacts
+demo/.venv/
+demo/.docindex/
+demo/.claude/
+
+# Misc
+.DS_Store
+*.log

doc_index_mcp-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Mike
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

doc_index_mcp-0.1.0/PKG-INFO

@@ -0,0 +1,264 @@
+Metadata-Version: 2.4
+Name: doc-index-mcp
+Version: 0.1.0
+Summary: MCP server for semantic document search with boundary-aware chunking
+License: MIT License
+        
+        Copyright (c) 2026 Mike
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: fastembed>=0.2.0
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: openpyxl>=3.1.0
+Requires-Dist: pdfplumber>=0.10.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-docx>=0.8.11
+Requires-Dist: python-pptx>=0.6.21
+Requires-Dist: tiktoken>=0.5.0
+Requires-Dist: usearch>=2.0.0
+Provides-Extra: apple
+Requires-Dist: onnxruntime>=1.17.0; extra == 'apple'
+Provides-Extra: cuda
+Requires-Dist: onnxruntime-gpu>=1.17.0; extra == 'cuda'
+Provides-Extra: dev
+Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
+Requires-Dist: pytest>=7.0.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Doc Index MCP
+
+## What is This For?
+
+A local-first semantic search server for your documents. Index PDFs, Word docs, PowerPoints, Excel files, and text/markdown, then search them using natural language via the Model Context Protocol (MCP).
+
+- **Semantic search** - Find relevant content using natural language queries
+- **Boundary-aware chunking** - Respects document structure (chapters, sections, headers)
+- **Table extraction** - Extract tables from documents as CSV
+- **Fully local** - No external APIs, no cloud services, no PyTorch
+- **Lightweight** - ONNX-based embeddings (~50MB vs ~2GB for PyTorch)
+
+## Supported Formats
+
+| Format | Extensions | Notes |
+|--------|------------|-------|
+| Text | `.txt` | Plain text |
+| Markdown | `.md`, `.markdown` | Preserves headers for boundaries |
+| PDF | `.pdf` | Text extraction with page markers |
+| Word | `.docx` | Paragraphs, headings, tables |
+| PowerPoint | `.pptx` | Slides, notes, tables |
+| Excel | `.xlsx`, `.xls` | Sheets as tables |
+
+### Why No External Services?
+
+| Component | Traditional RAG | This Server |
+|-----------|-----------------|-------------|
+| Embeddings | OpenAI API / hosted model | Local ONNX model (fastembed) |
+| Vector DB | Pinecone / Weaviate / Qdrant | Local file (usearch) |
+| Storage | Cloud / managed DB | Local `.docindex/` directory |
+| Dependencies | PyTorch (~2GB) | ONNX Runtime (~50MB) |
+
+## Tools
+
+### `doc_index`
+Index a document for semantic search.
+
+```json
+{
+  "file_path": "docs/manual.pdf",
+  "source_name": "manual"
+}
+```
+
+### `doc_search`
+Search indexed documents using natural language.
+
+```json
+{
+  "query": "how to configure authentication",
+  "top_k": 5,
+  "expand_to_boundary": "section",
+  "max_return_tokens": 4096
+}
+```
+
+Parameters:
+- `query` - Search query
+- `sources` - Filter to specific sources (optional)
+- `top_k` - Number of results (default: 5)
+- `expand_to_boundary` - Expand results to full "section" or "chapter"
+- `max_return_tokens` - Token budget for results (default: 4096)
+- `include_siblings` - Include sibling sections when expanding
+
+### `doc_list`
+List all indexed sources.
+
+### `doc_chunk`
+Retrieve a specific chunk by ID with optional neighbors.
+
+```json
+{
+  "chunk_id": "manual:42",
+  "neighbors": 2
+}
+```
+
+### `read_document`
+Read a document without indexing. Returns formatted text.
+
+```json
+{
+  "file_path": "report.pdf",
+  "max_chars": 100000
+}
+```
+
+### `list_tables`
+List all tables in a document.
+
+```json
+{
+  "file_path": "data.xlsx"
+}
+```
+
+### `extract_table`
+Extract a specific table as CSV.
+
+```json
+{
+  "file_path": "data.xlsx",
+  "table_index": 0,
+  "max_rows": 100
+}
+```
+
+## Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+Or with uv:
+
+```bash
+uv pip install -r requirements.txt
+```
+
+## Configuration
+
+Add to your Claude Desktop or MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "doc-index": {
+      "command": "python",
+      "args": ["/path/to/doc-index-mcp/src/server.py"],
+      "env": {
+        "MCP_WORKING_DIR": "/path/to/your/project",
+        "DOC_INDEX_DIR": "/path/to/store/indices"
+      }
+    }
+  }
+}
+```
+
+### Environment Variables
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `MCP_WORKING_DIR` | Base directory for resolving file paths | Current working directory |
+| `DOC_INDEX_DIR` | Directory for storing vector indices | `.docindex` in working dir |
+
+## Architecture
+
+Everything runs locally - no external APIs, databases, or embedding servers required.
+
+```mermaid
+flowchart TB
+    subgraph Client["MCP Client (Claude Desktop, etc.)"]
+        LLM[LLM]
+    end
+
+    subgraph MCP["Doc Index MCP Server"]
+        Server[server.py]
+
+        subgraph Services["Local Services"]
+            Loader[Document Loader<br/>PDF, DOCX, PPTX, XLSX]
+            Chunker[Boundary-Aware<br/>Chunker]
+            Embedder[Embedder<br/>ONNX Runtime]
+            VectorStore[Vector Store<br/>usearch]
+        end
+    end
+
+    subgraph Storage["Local Filesystem"]
+        Docs[(Source<br/>Documents)]
+        Index[(".docindex/<br/>├── manifest.json<br/>└── vectors/<br/>    ├── index.usearch<br/>    ├── chunks.jsonl<br/>    └── boundaries.json")]
+    end
+
+    subgraph Models["Embedded Model (downloaded once)"]
+        ONNX[BAAI/bge-small-en-v1.5<br/>ONNX format ~50MB]
+    end
+
+    LLM <-->|MCP Protocol| Server
+    Server --> Loader
+    Server --> Chunker
+    Server --> Embedder
+    Server --> VectorStore
+
+    Loader -->|read| Docs
+    VectorStore <-->|read/write| Index
+    Embedder -->|load once| ONNX
+
+    style Client fill:#e1f5fe
+    style Storage fill:#fff3e0
+    style Models fill:#f3e5f5
+    style MCP fill:#e8f5e9
+```
+
+### Data Flow
+
+```mermaid
+flowchart LR
+    subgraph Index["Indexing"]
+        direction TB
+        A[Document] --> B[Load & Extract Text]
+        B --> C[Detect Boundaries]
+        C --> D[Chunk ~256 tokens]
+        D --> E[Generate Embeddings]
+        E --> F[Save to Disk]
+    end
+
+    subgraph Search["Searching"]
+        direction TB
+        G[Query] --> H[Embed Query]
+        H --> I[Vector Similarity Search]
+        I --> J[Expand to Boundaries]
+        J --> K[Return Results]
+    end
+
+    Index -.->|stored in .docindex/| Search
+```
+
+## License
+
+MIT

doc_index_mcp-0.1.0/README.md

@@ -0,0 +1,218 @@
+# Doc Index MCP
+
+## What is This For?
+
+A local-first semantic search server for your documents. Index PDFs, Word docs, PowerPoints, Excel files, and text/markdown, then search them using natural language via the Model Context Protocol (MCP).
+
+- **Semantic search** - Find relevant content using natural language queries
+- **Boundary-aware chunking** - Respects document structure (chapters, sections, headers)
+- **Table extraction** - Extract tables from documents as CSV
+- **Fully local** - No external APIs, no cloud services, no PyTorch
+- **Lightweight** - ONNX-based embeddings (~50MB vs ~2GB for PyTorch)
+
+## Supported Formats
+
+| Format | Extensions | Notes |
+|--------|------------|-------|
+| Text | `.txt` | Plain text |
+| Markdown | `.md`, `.markdown` | Preserves headers for boundaries |
+| PDF | `.pdf` | Text extraction with page markers |
+| Word | `.docx` | Paragraphs, headings, tables |
+| PowerPoint | `.pptx` | Slides, notes, tables |
+| Excel | `.xlsx`, `.xls` | Sheets as tables |
+
+### Why No External Services?
+
+| Component | Traditional RAG | This Server |
+|-----------|-----------------|-------------|
+| Embeddings | OpenAI API / hosted model | Local ONNX model (fastembed) |
+| Vector DB | Pinecone / Weaviate / Qdrant | Local file (usearch) |
+| Storage | Cloud / managed DB | Local `.docindex/` directory |
+| Dependencies | PyTorch (~2GB) | ONNX Runtime (~50MB) |
+
+## Tools
+
+### `doc_index`
+Index a document for semantic search.
+
+```json
+{
+  "file_path": "docs/manual.pdf",
+  "source_name": "manual"
+}
+```
+
+### `doc_search`
+Search indexed documents using natural language.
+
+```json
+{
+  "query": "how to configure authentication",
+  "top_k": 5,
+  "expand_to_boundary": "section",
+  "max_return_tokens": 4096
+}
+```
+
+Parameters:
+- `query` - Search query
+- `sources` - Filter to specific sources (optional)
+- `top_k` - Number of results (default: 5)
+- `expand_to_boundary` - Expand results to full "section" or "chapter"
+- `max_return_tokens` - Token budget for results (default: 4096)
+- `include_siblings` - Include sibling sections when expanding
+
+### `doc_list`
+List all indexed sources.
+
+### `doc_chunk`
+Retrieve a specific chunk by ID with optional neighbors.
+
+```json
+{
+  "chunk_id": "manual:42",
+  "neighbors": 2
+}
+```
+
+### `read_document`
+Read a document without indexing. Returns formatted text.
+
+```json
+{
+  "file_path": "report.pdf",
+  "max_chars": 100000
+}
+```
+
+### `list_tables`
+List all tables in a document.
+
+```json
+{
+  "file_path": "data.xlsx"
+}
+```
+
+### `extract_table`
+Extract a specific table as CSV.
+
+```json
+{
+  "file_path": "data.xlsx",
+  "table_index": 0,
+  "max_rows": 100
+}
+```
+
+## Installation
+
+```bash
+pip install -r requirements.txt
+```
+
+Or with uv:
+
+```bash
+uv pip install -r requirements.txt
+```
+
+## Configuration
+
+Add to your Claude Desktop or MCP client config:
+
+```json
+{
+  "mcpServers": {
+    "doc-index": {
+      "command": "python",
+      "args": ["/path/to/doc-index-mcp/src/server.py"],
+      "env": {
+        "MCP_WORKING_DIR": "/path/to/your/project",
+        "DOC_INDEX_DIR": "/path/to/store/indices"
+      }
+    }
+  }
+}
+```
+
+### Environment Variables
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `MCP_WORKING_DIR` | Base directory for resolving file paths | Current working directory |
+| `DOC_INDEX_DIR` | Directory for storing vector indices | `.docindex` in working dir |
+
+## Architecture
+
+Everything runs locally - no external APIs, databases, or embedding servers required.
+
+```mermaid
+flowchart TB
+    subgraph Client["MCP Client (Claude Desktop, etc.)"]
+        LLM[LLM]
+    end
+
+    subgraph MCP["Doc Index MCP Server"]
+        Server[server.py]
+
+        subgraph Services["Local Services"]
+            Loader[Document Loader<br/>PDF, DOCX, PPTX, XLSX]
+            Chunker[Boundary-Aware<br/>Chunker]
+            Embedder[Embedder<br/>ONNX Runtime]
+            VectorStore[Vector Store<br/>usearch]
+        end
+    end
+
+    subgraph Storage["Local Filesystem"]
+        Docs[(Source<br/>Documents)]
+        Index[(".docindex/<br/>├── manifest.json<br/>└── vectors/<br/>    ├── index.usearch<br/>    ├── chunks.jsonl<br/>    └── boundaries.json")]
+    end
+
+    subgraph Models["Embedded Model (downloaded once)"]
+        ONNX[BAAI/bge-small-en-v1.5<br/>ONNX format ~50MB]
+    end
+
+    LLM <-->|MCP Protocol| Server
+    Server --> Loader
+    Server --> Chunker
+    Server --> Embedder
+    Server --> VectorStore
+
+    Loader -->|read| Docs
+    VectorStore <-->|read/write| Index
+    Embedder -->|load once| ONNX
+
+    style Client fill:#e1f5fe
+    style Storage fill:#fff3e0
+    style Models fill:#f3e5f5
+    style MCP fill:#e8f5e9
+```
+
+### Data Flow
+
+```mermaid
+flowchart LR
+    subgraph Index["Indexing"]
+        direction TB
+        A[Document] --> B[Load & Extract Text]
+        B --> C[Detect Boundaries]
+        C --> D[Chunk ~256 tokens]
+        D --> E[Generate Embeddings]
+        E --> F[Save to Disk]
+    end
+
+    subgraph Search["Searching"]
+        direction TB
+        G[Query] --> H[Embed Query]
+        H --> I[Vector Similarity Search]
+        I --> J[Expand to Boundaries]
+        J --> K[Return Results]
+    end
+
+    Index -.->|stored in .docindex/| Search
+```
+
+## License
+
+MIT

doc_index_mcp-0.1.0/demo/.mcp-local.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "doc-index": {
+      "command": "uv",
+      "args": ["--directory", "..", "run", "doc-index-mcp"],
+      "env": {
+        "MCP_WORKING_DIR": "${workspaceFolder}"
+      }
+    }
+  }
+}

doc_index_mcp-0.1.0/demo/.mcp.json

@@ -0,0 +1,11 @@
+{
+  "mcpServers": {
+    "doc-index": {
+      "command": "uvx",
+      "args": ["doc-index-mcp"],
+      "env": {
+        "MCP_WORKING_DIR": "${workspaceFolder}"
+      }
+    }
+  }
+}

doc_index_mcp-0.1.0/pyproject.toml

@@ -0,0 +1,51 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "doc-index-mcp"
+version = "0.1.0"
+description = "MCP server for semantic document search with boundary-aware chunking"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { file = "LICENSE" }
+dependencies = [
+    "mcp>=1.0.0",
+    "pydantic>=2.0.0",
+    "numpy>=1.24.0",
+    # Embedding - ONNX-based, lightweight (~50x smaller than PyTorch)
+    "fastembed>=0.2.0",
+    # Vector search - pre-built wheels, no C++ compilation
+    "usearch>=2.0.0",
+    # Token counting
+    "tiktoken>=0.5.0",
+    # Document loading
+    "pdfplumber>=0.10.0",
+    "python-docx>=0.8.11",
+    "python-pptx>=0.6.21",
+    "openpyxl>=3.1.0",
+]
+
+[project.optional-dependencies]
+cuda = [
+    "onnxruntime-gpu>=1.17.0",
+]
+apple = [
+    "onnxruntime>=1.17.0",
+]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.21.0",
+]
+
+[project.scripts]
+doc-index-mcp = "src.server:main"
+doc-index-install-skill = "src.install_skill:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src"]
+artifacts = ["src/skills/**/*.md"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["src/tests", "tests"]