MCP PDF to PGVector

┌────────────────────────────────────────────────────────────┐
│  Agent (OpenCode, Claude Desktop, etc.)                    │
│  calls index_pdfs_for_rag(pdf_directory, collection_name)  │
└─────────────────────┬──────────────────────────────────────┘
                      │ JSON-RPC (stdio)
┌─────────────────────▼──────────────────────────────────────┐
│  server.py — MCP Server (FastMCP v1)                       │
│                                                             │
│  1. Scan PDF directory (recursive glob)                     │
│  2. Compute SHA-256 hash of each file                       │
│  3. Extract text (PyMuPDF)                                  │
│  4. Recursive character chunking (1000/200 default)         │
│  5. Batch embed (nomic-embed-text-v2-moe, 768-dim)          │
│  6. Batch insert into pgvector (ON CONFLICT DO NOTHING)     │
│  7. Create HNSW index on completion                         │
└─────────────────────┬──────────────────────────────────────┘
                      │ asyncpg
┌─────────────────────▼──────────────────────────────────────┐
│  PostgreSQL + pgvector                                      │
│                                                             │
│  documents (                                                │
│    collection_name TEXT,     ← namespace for multi-tenant   │
│    file_hash TEXT,           ← SHA-256 for resume/dedup     │
│    file_path TEXT,           ← original source              │
│    chunk_index INT,          ← position within file         │
│    content TEXT,             ← chunk text                   │
│    embedding vector(768),    ← nomic embedding              │
│    metadata JSONB,           ← extensible                   │
│    UNIQUE(collection_name, file_hash, chunk_index)          │
│  )                                                          │
└────────────────────────────────────────────────────────────┘

{
  "mcp": {
    "mcp-pdf-to-pgvector": {
      "type": "local",
      "command": ["/path/to/mcp-pdf-to-pgvector/.venv/bin/python", "server.py"],
      "enabled": true
    }
  }
}

index_pdfs_for_rag(
  pdf_directory="/path/to/pdfs",
  collection_name="company-policies"
)

check_indexing_progress(task_id="...")

# Clone and enter
git clone <url>
cd mcp-pdf-to-pgvector

# Create virtual environment and install dependencies
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Configure pgvector connection
cp .env.example .env
# Edit .env with your pgvector credentials

# Start the server (listens on stdio)
python server.py

source .venv/bin/activate
mcp dev server.py

CREATE TABLE documents (
    id BIGSERIAL PRIMARY KEY,
    collection_name TEXT NOT NULL,
    file_hash TEXT NOT NULL,
    file_path TEXT NOT NULL,
    chunk_index INT NOT NULL,
    content TEXT NOT NULL,
    embedding vector(768),
    metadata JSONB DEFAULT '{}'::jsonb,
    created_at TIMESTAMPTZ DEFAULT NOW(),
    UNIQUE(collection_name, file_hash, chunk_index)
);

CREATE INDEX idx_documents_collection ON documents (collection_name);

-- Auto-created after ingestion:
CREATE INDEX ON documents USING hnsw (embedding vector_cosine_ops)
    WITH (m = 16, ef_construction = 200)
    WHERE collection_name = ?;