Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@PDFDashboardWithMCP search my documents for project deadlines"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Upload PDFs, extract text with PyMuPDF or GLM-OCR (Ollama), and ask questions against the document with a local Ollama model. No API keys.
PDF extraction: PyMuPDF for text layers; GLM-OCR when the PDF is scanned or image-only
Per-document RAG: each upload gets its own Chroma collection
Local chat: LangChain agent with inline citations; choose any installed Ollama model from the dropdown
Markdown viewer: read extracted text, preview chunks, download markdown
Related MCP server: MyDocsMCP
1. Clone the repository
git clone https://github.com/dakshp26/PDFDashboardWithMCP.git
cd PDFDashboardWithMCP2. Install dependencies
uv sync3. Pull Ollama models
ollama pull qwen2.5:3b # chat (or another chat model)
ollama pull nomic-embed-text # embeddings
ollama pull glm-ocr # OCR for scanned PDFs4. Run the app
uv run streamlit run app/main.pyOpen http://localhost:8501 in your browser.
Upload PDF: open Upload PDF, select a file, wait for extraction to finish
Chat: open Chat, pick the PDF and an Ollama model, ask questions
app/
├── main.py # Entry point, page navigation
├── app_pages/
│ ├── landing.py # Home page
│ ├── process_pdf_upload.py # Upload + pipeline UI
│ ├── pdf_library.py # Browse uploaded PDFs (read-only viewer)
│ └── process_pdf.py # Viewer + chat UI
└── process_pdf/
├── extract.py # PDF → Markdown (pymupdf4llm + GLM-OCR)
├── pipeline.py # Extraction pipeline with live progress
├── rag.py # Chunking, embeddings, Chroma persistence
└── agent.py # LangChain agent with retriever tool
mcp_server/
└── server.py # MCP server (list_documents, get_document)
data/ # Runtime data (gitignored)
├── process_pdf/ # Saved PDFs and extracted markdown
└── process_chroma/ # Chroma vector collections (one per PDF)File-by-file breakdown, execution order, and data flow:APP_STRUCTURE.md.
Page | What it does |
Home | Links and setup summary |
Upload PDF | Run extraction (text layer, OCR fallback, chunking, embedding); download markdown |
PDF Library | Open past uploads; view markdown and chunk previews without re-running extraction |
Chat | Query an indexed PDF with citations |
Extraction progress shows in an st.status block. After processing, the Chroma collection lives in data/process_chroma/ and loads on the next run without re-extracting.
Two tools for MCP clients (Claude Desktop, Cursor, Claude Code):
list_documents: indexed document collections
get_document(document, query): semantic search over a collection
Add to claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json) or use .mcp.json in the project root:
{
"mcpServers": {
"PDFDashboardWithMCP": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/PDFDashboardWithMCP", "mcp_server/server.py"]
}
}
}Add to .cursor/mcp.json in the project root or global ~/.cursor/mcp.json:
{
"mcpServers": {
"PDFDashboardWithMCP": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/PDFDashboardWithMCP", "mcp_server/server.py"]
}
}
}Project-scoped .mcp.json in the repo root keeps the server tied to this repo:
{
"mcpServers": {
"PDFDashboardWithMCP": {
"command": "uv",
"args": ["run", "--directory", "/absolute/path/to/PDFDashboardWithMCP", "mcp_server/server.py"]
}
}
}Claude Code reads .mcp.json when you open the project.
Replace /absolute/path/to/PDFDashboardWithMCP with your clone path.
Ollama must be running with
nomic-embed-textpulled before the MCP server can load collections.
Component | Library |
UI | Streamlit |
PDF extraction | langchain-pymupdf4llm, PyMuPDF |
OCR fallback | Ollama glm-ocr |
Embeddings | Ollama nomic-embed-text |
Vector store | Chroma (langchain-chroma) |
LLM / agent | Ollama chat model (e.g. qwen2.5:3b), LangChain |
Package manager | uv |
MCP server | mcp[cli] |
Search a document collection for chunks relevant to a query.
Args: document: Collection name as returned by list_documents. query: Natural-language question or search string.
Inputs: query (required), document (required). Returns: result
List all document collections available in the vector store.
Inputs: no named parameters. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: list_documents enumerates collections, while get_document searches within a specified collection. There is no ambiguity about which to use for a given task.
Both tools follow the verb_noun pattern, but list_documents uses plural while get_document uses singular. This minor inconsistency does not hinder readability or predictability.
With only two tools, the server feels thin for a PDF dashboard. While it covers listing and searching, the small number may not justify a dedicated server for many use cases.
The domain appears to be document retrieval, but the surface lacks essential operations like uploading, deleting, or retrieving full documents. The get_document tool only returns chunks, leaving significant gaps for common workflows.
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
Agentic search over your Dewey document collections from any MCP-compatible client.
Document processing over MCP: merge, split and compress PDFs, run OCR, extract document text.
