KnowledgeMCP
by maxzrff
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWLEDGE_OCR__ENABLED | No | Whether to enable OCR for scanned documents. Default is true. | true |
| KNOWLEDGE_OCR__LANGUAGE | No | OCR language code (e.g., 'eng', 'fra'). Default is eng. | eng |
| KNOWLEDGE_LOGGING__LEVEL | No | Logging verbosity level (DEBUG, INFO, etc.). Default is INFO. | INFO |
| KNOWLEDGE_OCR__FORCE_OCR | No | Whether to force OCR on all documents regardless of text extraction quality. Default is false. | false |
| KNOWLEDGE_LOGGING__FORMAT | No | The format for log messages ('text'). Default is text. | text |
| KNOWLEDGE_EMBEDDING__DEVICE | No | Computation device for embeddings (e.g., 'cpu' or 'cuda'). Default is cpu. | cpu |
| KNOWLEDGE_SEARCH__MAX_TOP_K | No | Maximum number of search results allowed. Default is 50. | 50 |
| KNOWLEDGE_CHUNKING__STRATEGY | No | The strategy used for chunking (e.g., 'sentence'). Default is sentence. | sentence |
| KNOWLEDGE_CHUNKING__CHUNK_SIZE | No | The number of characters per document chunk. Default is 500. | 500 |
| KNOWLEDGE_EMBEDDING__BATCH_SIZE | No | Number of embeddings to process per batch. Default is 32. | 32 |
| KNOWLEDGE_EMBEDDING__MODEL_NAME | No | The Sentence Transformers model name to use for embeddings. Default is sentence-transformers/all-MiniLM-L6-v2. | sentence-transformers/all-MiniLM-L6-v2 |
| KNOWLEDGE_SEARCH__DEFAULT_TOP_K | No | Default number of search results to return. Default is 10. | 10 |
| KNOWLEDGE_CHUNKING__CHUNK_OVERLAP | No | The number of overlapping characters between chunks. Default is 50. | 50 |
| KNOWLEDGE_STORAGE__DOCUMENTS_PATH | No | The directory path where documents are stored. Default is ./data/documents. | ./data/documents |
| KNOWLEDGE_STORAGE__VECTOR_DB_PATH | No | The directory path for the ChromaDB vector database. Default is ./data/chromadb. | ./data/chromadb |
| KNOWLEDGE_OCR__CONFIDENCE_THRESHOLD | No | OCR confidence threshold. Default is 0.0. | 0.0 |
| KNOWLEDGE_PROCESSING__MAX_FILE_SIZE_MB | No | Maximum allowed file size in MB for processing. Default is 100. | 100 |
| KNOWLEDGE_PROCESSING__MAX_CONCURRENT_TASKS | No | Maximum number of background indexing tasks to run concurrently. Default is 3. | 3 |
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/maxzrff/KnowledgeMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server