KFabric
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_queryC | Create a new KFabric documentary query. |
| discover_documentsC | Launch discovery for an existing KFabric query. |
| list_candidatesC | List candidate documents for a query. |
| collect_candidateC | Collect a candidate document and persist the raw payload. |
| analyze_documentC | Parse, score and decide on a collected document. |
| accept_documentC | Force a manual accept decision for a parsed document. |
| reject_documentC | Force a manual reject decision for a parsed document. |
| list_salvaged_fragmentsC | List salvaged fragments optionally filtered by query. |
| consolidate_fragmentsC | Cluster salvaged fragments for a query. |
| generate_fragment_synthesisC | Create a synthesis from salvaged fragments. |
| build_corpusC | Build the final corpus for a query. |
| prepare_indexC | Prepare an indexable artifact for a corpus. |
| get_corpus_statusC | Read the latest corpus status for a query or corpus id. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| summarize_document | Construit un prompt de resume prudent pour un document normalise. |
| synthesize_fragments | Construit un prompt de synthese pour des fragments recuperes. |
| review_corpus | Construit un prompt de revue qualitative du corpus final. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Each tool targets a distinct step in the document processing pipeline, from query creation to corpus building. There is minimal overlap between tools like analyze_document and accept_document, which serve different stages.
All tool names follow a consistent verb_noun pattern (e.g., create_query, discover_documents). The style is uniform with no mixing of conventions.
The 13 tools are well-scoped for a document collection and analysis pipeline. Each tool earns its place, covering discovery, collection, analysis, decision, and corpus assembly.
The core workflow is fully covered, but missing tools for listing queries or deleting candidates/corpora are minor gaps. Overall, the surface is nearly complete for the stated purpose.