kb-mcp-server
by Doy369
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the Web console (used by run_demo.py/app.py). Falls back to KB_WEB_PORT then 8000. | 8000 |
| KB_API_MOCK | No | Set to '1' to use mock data for external APIs (orders/inventory); set to '0' to use real HTTP endpoints configured via KB_ORDER_API_URL and KB_INVENTORY_API_URL. | 1 |
| KB_LOG_FILE | No | Path to a log file for structured logging. | |
| KB_WEB_PORT | No | Alternative port for the Web console (used by run_demo.py/app.py). | 8000 |
| KB_API_TOKEN | No | Bearer token for optional authentication to the server's Web/HTTP endpoints. | |
| KB_LLM_MODEL | No | Model name for the local LLM (e.g., 'llama3'). Used if KB_LLM_ENABLED=1. | |
| KB_AGENT_MODE | No | Multi-agent orchestration mode: 'deterministic' (fixed pipeline, zero LLM dependency) or 'llm' (uses local LLM to decide pipeline steps; falls back to deterministic on error). | deterministic |
| KB_GRAPH_NAME | No | Graph name in AGE mode (when KB_GRAPH_BACKEND=age). | kb_graph |
| KB_RATE_LIMIT | No | Rate limit per IP (e.g., '100/minute') for the Web console's HTTP interface. | |
| KB_LLM_ENABLED | No | Set to '1' to enable local LLM for synthesis, graph triple extraction, and agent routing. Falls back to template/rules if LLM unavailable. | 0 |
| KB_DATABASE_URL | No | PostgreSQL connection string (e.g., postgresql://user:pass@host:5432/kb). Required for pgvector storage and/or AGE graph backend. | |
| KB_LLM_BASE_URL | No | Base URL for an OpenAI-compatible local LLM (e.g., http://localhost:11434/v1 for Ollama). Required if KB_LLM_ENABLED=1. | |
| KB_GRAPH_BACKEND | No | Graph backend: 'memory' (offline pure Python) or 'age' (Postgres + Apache AGE, same DB as pgvector). | memory |
| KB_GRAPH_ENABLED | No | Total switch for automatic triple extraction into the knowledge graph during ingestion. Set to '0' to disable. | 1 |
| KB_ORDER_API_URL | No | URL for the order status API. Only used if KB_API_MOCK=0. | |
| KB_STORAGE_BACKEND | No | Storage backend: 'memory' (offline) or 'pgvector' (production with Postgres + vector index). | memory |
| KB_EMBEDDING_BACKEND | No | Embedding backend: 'dev' (zero-dependency, for development/demo) or 'bge' (local model, e.g., BAAI/bge-large-zh-v1.5). | dev |
| KB_INVENTORY_API_URL | No | URL for the inventory API. Only used if KB_API_MOCK=0. |
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/Doy369/kb-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server