HUMMBL MCP Server
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": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_modelA | Retrieve detailed information about a specific HUMMBL mental model using its code (e.g., P1, IN3, CO5). |
| list_all_modelsB | Retrieve complete list of all 120 HUMMBL mental models with basic information. |
| search_modelsA | Search HUMMBL mental models by keyword across codes, names, and definitions. |
| get_transformationA | Retrieve information about a specific transformation type and all its models (P, IN, CO, DE, RE, SY). |
| search_problem_patternsB | Find pre-defined problem patterns with recommended transformations and top models based on a search query. |
| recommend_modelsC | Get recommended mental models based on a natural language problem description using HUMMBL REST API. |
| get_related_modelsC | Get all models related to a specific model with relationship details |
| add_relationshipC | Add a relationship between two mental models with evidence. |
| get_recommendation_historyA | Fetch the caller's past recommendation calls (problems submitted and the model codes that were returned), newest first. Useful for 'what did we explore last time?' and for avoiding re-recommending the same models. |
| get_methodologyA | Retrieve the canonical Self-Dialectical AI Systems methodology with HUMMBL Base120 mappings. |
| audit_model_referencesB | Audit a list of HUMMBL model references for existence, transformation alignment, and duplicates. |
| list_workflowsA | Get all available guided workflows for problem-solving with Base120 mental models. |
| start_workflowB | Begin a guided multi-turn workflow for systematic problem-solving using Base120 mental models. |
| continue_workflowA | Proceed to the next step of your guided workflow after completing the current step. |
| find_workflow_for_problemB | Discover which workflow best fits your problem type or situation. |
| export_modelsA | Export a curated subset of Base120 mental models as Markdown, JSON, or PDF. Pass |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| root_cause_analysis | Systematically investigate problems to find root causes, not just symptoms. Uses Perspective, Inversion, and Decomposition transformations. (~20-30 minutes) |
| strategy_design | Design comprehensive strategies by framing the problem, combining elements creatively, and understanding system dynamics. (~30-45 minutes) |
| decision_making | Make high-quality decisions by framing clearly, stress-testing with inversion, and planning reversible vs. irreversible choices. (~15-25 minutes) |
| analyze_with_models | Open-ended analysis: surface the most relevant Base120 mental models for a problem and synthesise them into concrete guidance. |
| apply_model | Apply one specific HUMMBL mental model (by code, e.g. P1, IN3, CO5) to a problem. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| all-models | Complete Base120 framework with all 120 mental models. |
| self-dialectical-methodology | Canonical Self-Dialectical AI Systems methodology with HUMMBL Base120 mappings. |
| self-dialectical-methodology-markdown | Human-readable markdown overview of the Self-Dialectical AI Systems methodology, derived from the canonical structured definition. |
TDQS
Scored across 16 tools
Each tool targets a distinct action or query (e.g., get vs search vs recommend, add vs audit). Even closely related tools like get_model and get_related_models have clearly different purposes. No overlapping functionality.
All tools follow a verb_noun snake_case pattern (e.g., add_relationship, export_models, start_workflow). Verbs are descriptive and consistently used. No mixed conventions or ambiguous names.
With 16 tools covering models, relationships, workflows, recommendations, search, and export, the count is well-scoped. Each tool has a clear role, and the set is neither bloated nor sparse for a methodology server.
The tool set covers core CRUD-like operations (retrieve, list, search, add, export) and workflow management. Minor gaps exist, such as no tools for updating or deleting relationships, but the domain's static nature makes these non-critical.