KB-MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KB_DATA_DIR | No | Directory for storing knowledge base data | ./.kb-data |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ingest_documentC | Ingest a document into the knowledge base. Stores content with embeddings for semantic search. |
| query_knowledgeC | Query the knowledge base using semantic search. |
| list_documentsC | List all documents in the knowledge base. |
| get_documentC | Get a specific document by ID. |
| delete_documentC | Delete a document from the knowledge base. |
| update_documentC | Update an existing document. |
| kb_statsB | Get knowledge base statistics. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Every tool has a clearly distinct purpose with no ambiguity. Each targets a specific action on documents or the knowledge base (e.g., ingest, get, update, delete, list, query, stats), and the descriptions reinforce non-overlapping functions.
All tool names follow a consistent verb_noun pattern (e.g., delete_document, get_document, ingest_document), with no deviations in style or convention, making them predictable and readable.
With 7 tools, the server is well-scoped for a knowledge base management system. Each tool earns its place, covering essential CRUD operations, querying, and statistics without being overly sparse or bloated.
The tool set provides complete CRUD/lifecycle coverage for the knowledge base domain, including ingest, get, update, delete, list, query, and stats. There are no obvious gaps, allowing agents to handle all core workflows without dead ends.