Pdfkb Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Pdfkb Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A powerful Model Context Protocol (MCP) server that transforms your PDF and Markdown document collection into an intelligent, searchable knowledge base. Built for seamless integration with Claude Desktop, VS Code, Continue, and other MCP-enabled AI assistants.
pdfkb-mcp processes your documents using advanced PDF parsing, creates semantic embeddings, and provides sophisticated search capabilities through the Model Context Protocol. Whether you're managing research papers, technical documentation, or business reports, pdfkb-mcp makes your document collection instantly searchable and accessible to your AI assistant.
I built pdfkb-mcp because I needed a way to efficiently index and search through hundreds of semiconductor datasheets and technical documents. Traditional file search wasn't sufficient—I needed semantic understanding, context preservation, and the ability to ask complex questions about technical specifications across multiple documents. This tool has transformed how I work with technical documentation, and I'm sharing it so others can benefit from intelligent document search in their workflows.
Once your setup is complete, you'll have access to a modern web interface for document management and search:
PDF Knowledgebase Web Interface
The web interface provides document upload, real-time processing status, semantic search, and comprehensive document management capabilities.
Key Features:
Get up and running in minutes using Docker/Podman with DeepInfra as your AI provider.
# Download configuration and create directories
curl -o docker-compose.yml https://raw.githubusercontent.com/juanqui/pdfkb-mcp/main/docker-compose.sample.yml
mkdir -p ./documents ./cache ./logs
# Edit docker-compose.yml and update:
# 1. Volume path: "/path/to/your/documents:/app/documents:rw"
# 2. API key: PDFKB_OPENAI_API_KEY: "your-deepinfra-api-key-here"# Using Podman (recommended)
podman-compose up -d
# Or using Docker
docker compose up -dAccess Points:
Claude Desktop - Add to claude_desktop_config.json:
{
"mcpServers": {
"pdfkb": {
"transport": "http",
"url": "http://localhost:8000/mcp/"
}
}
}VS Code with Continue - Add to .continue/config.json:
{
"mcpServers": {
"pdfkb": {
"transport": "http",
"url": "http://localhost:8000/mcp/"
}
}
}Ask your AI assistant to search your documents:
The setup includes:
For complete documentation, configuration options, and advanced features:
👉 [View the Complete User Guide](docs/userguide/index.md)
The user guide includes:
This project is licensed under the MIT License - see the LICENSE file for details.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.