Narrative Graph MCP
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rtm_create_narrative_treeC | Create a Random Tree Model encoding of a narrative text |
| rtm_generate_ensembleC | Generate a statistical ensemble of Random Trees to model population-level recall |
| rtm_traverse_narrativeC | Traverse a narrative tree at different depths to get summaries at varying abstraction levels |
| rtm_find_optimal_depthC | Find the optimal traversal depth to achieve a target recall length |
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 4 tools
Each tool has a clearly distinct purpose within the Random Tree Model (RTM) workflow: creation, depth optimization, ensemble generation, and traversal. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent 'rtm_verb_noun' naming pattern with snake_case, using descriptive verbs like 'create', 'find', 'generate', and 'traverse'. This predictability enhances readability and usability.
Four tools are well-scoped for the narrative graph modeling domain, covering core operations from tree creation to analysis. It is slightly lean but reasonable, as it focuses on essential RTM functions without unnecessary bloat.
The toolset covers key aspects of narrative tree modeling: creation, optimization, ensemble analysis, and traversal. Minor gaps may exist, such as tools for editing or deleting trees, but the core workflow is well-supported for statistical recall modeling.