keywordgraph-mcp-server 1.9.1 → 1.9.5

package/llms-full.infranodus.txt

@@ -50,13 +50,15 @@ Get API key at: https://infranodus.com/api-access
 
 **Entity detection** (`modifyAnalyzedText` parameter):
 - `none` (default): Word co-occurrence graph
-- `detectEntities`: Mix entities and words
-- `extractEntitiesOnly`: Entity-only graph, best for ontologies and knowledge graphs
+- `detectEntities`: An algorithm marks names as entities, mixed with the words
+- `extractEntitiesOnly`: An algorithm finds names and only they become nodes. For plain text without `[[wikilinks]]`; for text already written as `[[entity]]` statements use `wikilinksMode: wikilinksOnly`
+- `aiKnowledgeGraph` (`generate_knowledge_graph`, `create_knowledge_graph`): An AI model writes `[[entity]]` statements about a topic or a text, and only those entities become nodes. Slower, uses AI credits; optional `instructions` and `modelToUse`
 
 **AI models** (`modelToUse` parameter, no additional API keys needed):
-- `gpt-4o`, `gpt-4o-mini`, `gpt-5.4`, `gpt-5.4-mini`
-- `claude-sonnet-4.6`, `claude-opus-4.6`
-- `gemini-2.5-flash`, `gemini-2.5-flash-lite`
+- `claude-opus-5-5` (default of the graph-generating tools), `claude-sonnet-5-5`, `claude-fable-5-1`
+- `gpt-6.1-terra` (default of the text-writing tools), `gpt-6.1-sol`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-4o`, `gpt-4o-mini`
+- `gemini-4-argon`, `gemini-3.8-flash`, `gemini-3.5-flash-lite`
+- `grok-4.7`, `grok-4.20-0309-non-reasoning`
 
 **Response types** (`responseType` parameter):
 - `response`: Default analytical response
@@ -85,7 +87,8 @@ Generates a knowledge graph from text using network analysis. Shows main concept
 - `includeGraph` (boolean): Include full graph structure with cluster details
 - `includeStatements` (boolean): Include original statements
 - `addNodesAndEdges` (boolean): Include raw nodes and edges
-- `modifyAnalyzedText`: Entity detection mode
+- `modifyAnalyzedText`: Entity detection mode; `aiKnowledgeGraph` builds an AI knowledge graph of a topic or text
+- `modelToUse`, `instructions`: Only with `aiKnowledgeGraph` — the AI model, and the user's own instructions (which entities, scope); they cannot change the output format
 
 **Returns**: statistics (modularity, diversity_stats), contentGaps, mainTopicalClusters, mainConcepts, conceptualGateways, topRelations, topInfluentialNodes, knowledgeGraphByCluster.
 
@@ -124,23 +127,24 @@ Identifies content gaps — missing connections between topical clusters that re
 
 **Parameters**: `text` / `url` / `graphName`
 
-**Returns**: `contentGaps` array. Format: "Gap N: ClusterA (keywords) -> ClusterB (keywords)"
+**Returns**: `contentGaps` array. Format: "Gap N: ClusterA (keywords) -> ClusterB (keywords)". Also `insightClusters`: the 1–3 clusters the AI bridges by default, one line per gap depth, each cluster tagged `gap`, `bridge` or `influence`. Format: "Insight clusters N (state): [gap] ClusterA (keywords) + [bridge] ClusterB (keywords)". Every tool that returns `contentGaps` returns `insightClusters` beside it.
 
 ---
 
 ### generate_research_questions
 
-Generates research questions that bridge content gaps identified in text.
+Generates research questions that bridge the topical clusters of a text. By default the questions bridge the insight clusters.
 
 **Use for**: Generating prompts for LLM workflows, research ideation, bridging knowledge gaps.
 
 **Parameters**:
 - `text` / `url` / `graphName`: Input source
+- `optimize`: which clusters the questions are generated from. `optimize` (default) uses the insight clusters, picked from the structure of the graph to move it toward a balanced shape; `gap` the widest content gap; `develop` all the main topics; `latent` the under-developed ones
 - `useSeveralGaps` (boolean): Generate questions for multiple gaps (more diverse)
-- `gapDepth` (number): Explore less prominent gaps (0 = top gap)
+- `gapDepth` (number): Explore less prominent gaps or insight clusters (0 = the first)
 - `modelToUse` (string): AI model to use
 
-**Returns**: `questions` array of research question strings.
+**Returns**: `questions` array of research question strings, and `insightClusters`.
 
 ---
 
@@ -150,12 +154,14 @@ Generates ideas that develop the text further based on content gaps. By default
 
 **Parameters**:
 - `text` / `url` / `graphName`: Input source
+- `optimize`: which clusters the ideas are generated from. `optimize` (default) uses the insight clusters, picked from the structure of the graph to move it toward a balanced shape; `gap` the widest content gap; `develop` all the main topics; `latent` the under-developed ones
 - `useSeveralGaps` (boolean): Ideas for multiple gaps
+- `gapDepth` (number): Explore less prominent gaps or insight clusters (0 = the first)
 - `shouldTranscend` (boolean): Connect to broader discourse
 - `responseType`: 'response' (analytical) or 'idea' (business-oriented)
 - `modelToUse` (string): AI model to use
 
-**Returns**: `responses` array of idea strings.
+**Returns**: `responses` array of idea strings (`ideas` with `responseType: 'idea'`), and `insightClusters`.
 
 ---
 

package/llms-full.keywordgraph.txt

@@ -50,13 +50,15 @@ Get API key at: https://keywordgraph.com/api-access
 
 **Entity detection** (`modifyAnalyzedText` parameter):
 - `none` (default): Word co-occurrence graph
-- `detectEntities`: Mix entities and words
-- `extractEntitiesOnly`: Entity-only graph, best for ontologies and knowledge graphs
+- `detectEntities`: An algorithm marks names as entities, mixed with the words
+- `extractEntitiesOnly`: An algorithm finds names and only they become nodes. For plain text without `[[wikilinks]]`; for text already written as `[[entity]]` statements use `wikilinksMode: wikilinksOnly`
+- `aiKnowledgeGraph` (`generate_knowledge_graph`, `create_knowledge_graph`): An AI model writes `[[entity]]` statements about a topic or a text, and only those entities become nodes. Slower, uses AI credits; optional `instructions` and `modelToUse`
 
 **AI models** (`modelToUse` parameter, no additional API keys needed):
-- `gpt-4o`, `gpt-4o-mini`, `gpt-5.4`, `gpt-5.4-mini`
-- `claude-sonnet-4.6`, `claude-opus-4.6`
-- `gemini-2.5-flash`, `gemini-2.5-flash-lite`
+- `claude-opus-5-5` (default of the graph-generating tools), `claude-sonnet-5-5`, `claude-fable-5-1`
+- `gpt-6.1-terra` (default of the text-writing tools), `gpt-6.1-sol`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-4o`, `gpt-4o-mini`
+- `gemini-4-argon`, `gemini-3.8-flash`, `gemini-3.5-flash-lite`
+- `grok-4.7`, `grok-4.20-0309-non-reasoning`
 
 **Response types** (`responseType` parameter):
 - `response`: Default analytical response
@@ -85,7 +87,8 @@ Generates a knowledge graph from text using network analysis. Shows main concept
 - `includeGraph` (boolean): Include full graph structure with cluster details
 - `includeStatements` (boolean): Include original statements
 - `addNodesAndEdges` (boolean): Include raw nodes and edges
-- `modifyAnalyzedText`: Entity detection mode
+- `modifyAnalyzedText`: Entity detection mode; `aiKnowledgeGraph` builds an AI knowledge graph of a topic or text
+- `modelToUse`, `instructions`: Only with `aiKnowledgeGraph` — the AI model, and the user's own instructions (which entities, scope); they cannot change the output format
 
 **Returns**: statistics (modularity, diversity_stats), contentGaps, mainTopicalClusters, mainConcepts, conceptualGateways, topRelations, topInfluentialNodes, knowledgeGraphByCluster.
 

package/llms-full.txt

@@ -50,13 +50,15 @@ Get API key at: https://infranodus.com/api-access
 
 **Entity detection** (`modifyAnalyzedText` parameter):
 - `none` (default): Word co-occurrence graph
-- `detectEntities`: Mix entities and words
-- `extractEntitiesOnly`: Entity-only graph, best for ontologies and knowledge graphs
+- `detectEntities`: An algorithm marks names as entities, mixed with the words
+- `extractEntitiesOnly`: An algorithm finds names and only they become nodes. For plain text without `[[wikilinks]]`; for text already written as `[[entity]]` statements use `wikilinksMode: wikilinksOnly`
+- `aiKnowledgeGraph` (`generate_knowledge_graph`, `create_knowledge_graph`): An AI model writes `[[entity]]` statements about a topic or a text, and only those entities become nodes. Slower, uses AI credits; optional `instructions` and `modelToUse`
 
 **AI models** (`modelToUse` parameter, no additional API keys needed):
-- `gpt-4o`, `gpt-4o-mini`, `gpt-5.4`, `gpt-5.4-mini`
-- `claude-sonnet-4.6`, `claude-opus-4.6`
-- `gemini-2.5-flash`, `gemini-2.5-flash-lite`
+- `claude-opus-5-5` (default of the graph-generating tools), `claude-sonnet-5-5`, `claude-fable-5-1`
+- `gpt-6.1-terra` (default of the text-writing tools), `gpt-6.1-sol`, `gpt-5.6-terra`, `gpt-5.6-sol`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-4o`, `gpt-4o-mini`
+- `gemini-4-argon`, `gemini-3.8-flash`, `gemini-3.5-flash-lite`
+- `grok-4.7`, `grok-4.20-0309-non-reasoning`
 
 **Response types** (`responseType` parameter):
 - `response`: Default analytical response
@@ -85,7 +87,8 @@ Generates a knowledge graph from text using network analysis. Shows main concept
 - `includeGraph` (boolean): Include full graph structure with cluster details
 - `includeStatements` (boolean): Include original statements
 - `addNodesAndEdges` (boolean): Include raw nodes and edges
-- `modifyAnalyzedText`: Entity detection mode
+- `modifyAnalyzedText`: Entity detection mode; `aiKnowledgeGraph` builds an AI knowledge graph of a topic or text
+- `modelToUse`, `instructions`: Only with `aiKnowledgeGraph` — the AI model, and the user's own instructions (which entities, scope); they cannot change the output format
 
 **Returns**: statistics (modularity, diversity_stats), contentGaps, mainTopicalClusters, mainConcepts, conceptualGateways, topRelations, topInfluentialNodes, knowledgeGraphByCluster.
 
@@ -124,23 +127,24 @@ Identifies content gaps — missing connections between topical clusters that re
 
 **Parameters**: `text` / `url` / `graphName`
 
-**Returns**: `contentGaps` array. Format: "Gap N: ClusterA (keywords) -> ClusterB (keywords)"
+**Returns**: `contentGaps` array. Format: "Gap N: ClusterA (keywords) -> ClusterB (keywords)". Also `insightClusters`: the 1–3 clusters the AI bridges by default, one line per gap depth, each cluster tagged `gap`, `bridge` or `influence`. Format: "Insight clusters N (state): [gap] ClusterA (keywords) + [bridge] ClusterB (keywords)". Every tool that returns `contentGaps` returns `insightClusters` beside it.
 
 ---
 
 ### generate_research_questions
 
-Generates research questions that bridge content gaps identified in text.
+Generates research questions that bridge the topical clusters of a text. By default the questions bridge the insight clusters.
 
 **Use for**: Generating prompts for LLM workflows, research ideation, bridging knowledge gaps.
 
 **Parameters**:
 - `text` / `url` / `graphName`: Input source
+- `optimize`: which clusters the questions are generated from. `optimize` (default) uses the insight clusters, picked from the structure of the graph to move it toward a balanced shape; `gap` the widest content gap; `develop` all the main topics; `latent` the under-developed ones
 - `useSeveralGaps` (boolean): Generate questions for multiple gaps (more diverse)
-- `gapDepth` (number): Explore less prominent gaps (0 = top gap)
+- `gapDepth` (number): Explore less prominent gaps or insight clusters (0 = the first)
 - `modelToUse` (string): AI model to use
 
-**Returns**: `questions` array of research question strings.
+**Returns**: `questions` array of research question strings, and `insightClusters`.
 
 ---
 
@@ -150,12 +154,14 @@ Generates ideas that develop the text further based on content gaps. By default
 
 **Parameters**:
 - `text` / `url` / `graphName`: Input source
+- `optimize`: which clusters the ideas are generated from. `optimize` (default) uses the insight clusters, picked from the structure of the graph to move it toward a balanced shape; `gap` the widest content gap; `develop` all the main topics; `latent` the under-developed ones
 - `useSeveralGaps` (boolean): Ideas for multiple gaps
+- `gapDepth` (number): Explore less prominent gaps or insight clusters (0 = the first)
 - `shouldTranscend` (boolean): Connect to broader discourse
 - `responseType`: 'response' (analytical) or 'idea' (business-oriented)
 - `modelToUse` (string): AI model to use
 
-**Returns**: `responses` array of idea strings.
+**Returns**: `responses` array of idea strings (`ideas` with `responseType: 'idea'`), and `insightClusters`.
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "keywordgraph-mcp-server",
-	"version": "1.9.1",
+	"version": "1.9.5",
 	"description": "KeywordGraph MCP server - A Model Context Protocol server for network thinking and graph analysis",
 	"type": "module",
 	"module": "src/index.ts",