PDF Knowledgebase MCP Server
by juanqui
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_DPI | No | DPI setting for LLM parser | 150 |
| CACHE_DIR | No | Cache directory for processing | ./.cache |
| LLM_MODEL | No | Model to use with LLM parser | anthropic/claude-3.5-sonnet |
| LOG_LEVEL | No | Logging level | INFO |
| CHUNK_SIZE | No | Target chunk size for LangChain chunker | 1000 |
| PDF_PARSER | No | Parser to use: marker, pymupdf4llm, mineru, docling, llm | marker |
| MINERU_LANG | No | Language setting for MinerU parser | en |
| MINERU_VRAM | No | VRAM setting for MinerU parser | |
| PDF_CHUNKER | No | Chunking strategy to use | unstructured |
| CHUNK_OVERLAP | No | LangChain chunk overlap | 200 |
| MINERU_METHOD | No | Method setting for MinerU parser | auto |
| DOCLING_DO_OCR | No | Enable OCR for Docling parser | false |
| OPENAI_API_KEY | Yes | OpenAI API key for embeddings (required) | |
| EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-large |
| LLM_CONCURRENCY | No | Concurrency setting for LLM parser | 5 |
| VECTOR_SEARCH_K | No | Default search results | 5 |
| DOCLING_TABLE_MODE | No | Table extraction mode for Docling parser | ACCURATE |
| FILE_SCAN_INTERVAL | No | File monitoring interval in seconds | 60 |
| KNOWLEDGEBASE_PATH | No | Directory containing PDF files | ./pdfs |
| OPENROUTER_API_KEY | No | OpenRouter API key, required for LLM parser | |
| EMBEDDING_BATCH_SIZE | No | Embedding batch size | 100 |
| DOCLING_OCR_LANGUAGES | No | Languages for OCR with Docling parser | en |
| DOCLING_DO_TABLE_STRUCTURE | No | Enable table structure extraction for Docling parser | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/juanqui/pdfkb-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server