Agentoom Knowledge
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APP_ENV | No | production | |
| APP_KEY | Yes | ||
| DB_HOST | No | ||
| DB_PORT | No | 5432 | |
| APP_DEBUG | No | false | |
| REDIS_HOST | No | ||
| REDIS_PORT | No | 6379 | |
| CACHE_STORE | No | array | |
| DB_DATABASE | No | :memory: | |
| DB_PASSWORD | No | ||
| DB_USERNAME | No | ||
| SCOUT_DRIVER | No | null | |
| DB_CONNECTION | No | sqlite | |
| TIKA_ENDPOINT | No | ||
| RUN_MIGRATIONS | No | false | |
| TYPESENSE_HOST | No | ||
| TYPESENSE_PORT | No | 8108 | |
| QUEUE_CONNECTION | No | sync | |
| TYPESENSE_API_KEY | No | ||
| TYPESENSE_PROTOCOL | No | http |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search-knowledgeA | Unified search across all knowledge sources. The server determines the best retrieval strategy internally. Use |
| list-sourcesA | List all available knowledge sources with their capabilities. Optionally filter by namespace. |
| get-source-schemaA | Get the schema and capabilities for a specific knowledge source identified by its namespace or class name. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| knowledge-search-guide | Guidance on how to effectively use the Agentoom Knowledge server for retrieving enterprise knowledge. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: search across sources, list sources, and get a source's schema. No ambiguity between them.
All tool names follow a consistent 'verb-noun' pattern with hyphens (search-knowledge, list-sources, get-source-schema), making them predictable.
With only 3 tools, the server feels minimal for a knowledge management system, though it may suffice for read-only queries. Slightly thin.
The set lacks essential operations like adding, updating, or deleting knowledge sources or items, leaving significant gaps for standard CRUD workflows.