Innovaas KMS MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_API_KEY | No | MCP-specific authentication key (alternative to BACKGROUND_PROCESS_API_KEY) | |
| KMS_BASE_URL | Yes | KMS API endpoint (required) | |
| BACKGROUND_PROCESS_API_KEY | No | Authentication key (alternative to MCP_API_KEY) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kms_searchC | Semantic search across documents using vector similarity. Searches through text documents, audio transcriptions, and video content with full document content retrieval. |
| kms_intelligent_searchC | Advanced RAG search with intelligent query analysis, routing, and full content access. Uses enhanced middleware for optimal search strategy selection. |
| kms_chatC | 🚀 Primary tool for comprehensive knowledge queries. RAG-powered conversational queries with multi-modal context, intelligent token management, and full document content access. Automatically optimizes for token limits while providing comprehensive responses. |
| kms_multimodal_searchB | Enhanced multi-modal search with full content retrieval. Search across text, audio, video content and video frames with technical content detection (code, diagrams, UI elements). |
| kms_get_documentA | Retrieve detailed information about a specific document by ID, including full content, transcriptions, and metadata. |
| kms_get_statsB | Get comprehensive analytics and statistics about the KMS system including document counts, processing status, and performance metrics. |
| kms_list_documentsB | List recent documents with filtering options. Useful for browsing and discovering content in the knowledge base. |
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
Four search tools (kms_search, kms_intelligent_search, kms_multimodal_search, kms_chat) have overlapping purposes and unclear boundaries. An agent cannot reliably choose among them without deep understanding of the server's internals.
All tool names follow a consistent kms_verb_noun pattern (kms_search, kms_get_document, kms_list_documents). This is predictable and easy to parse.
Seven tools is a reasonable count for a knowledge management server. However, the redundancy among search tools suggests some could be merged or better differentiated.
The server covers search, retrieval, chat, and stats, but lacks any write operations (create, update, delete documents). This is a notable gap for a KMS, though read-only functionality might be intentional.