Knowledge MCP Server
by congtuuit
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the MCP server. | 3900 |
| DB_PATH | No | Path to the SQLite database file. | ./db/knowledge.db |
| VAULT_DIR | No | Directory containing Markdown knowledge files. | ./data/raw |
| CHAT_MODEL | No | Model name for the chat endpoint (optional). | |
| CHAT_API_KEY | No | API key for the chat endpoint (optional). | |
| CHAT_BASE_URL | No | Base URL for the LLM chat endpoint used for contextual retrieval (optional). | |
| EMBEDDING_DIM | No | Dimension of the embedding vectors. | 768 |
| MCP_AUTH_TOKEN | No | Bearer token for authenticating MCP requests (optional for remote deployments). | |
| EMBEDDING_MODEL | No | Embedding model name. | nomic-embed-text |
| EMBEDDING_API_KEY | No | API key for the embedding endpoint. | ollama |
| EMBEDDING_BASE_URL | No | Base URL for the embedding endpoint (Ollama or 9router OpenAI-compatible). | http://localhost:11434/v1 |
| CONTEXTUAL_RETRIEVAL_ENABLED | No | Whether to enable Anthropic Contextual Retrieval (true/false). | false |
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues