Enhanced Architecture 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 |
|---|---|
| query_local_aiC | Query local AI model via Ollama for reasoning assistance |
| reasoning_assistC | Structured reasoning assistance for complex problems |
| model_listB | List available local AI models |
| hybrid_analysisC | Hybrid local+cloud analysis for complex data |
| token_efficient_reasoningB | Delegate heavy reasoning to local AI to conserve cloud tokens |
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 5 tools
Multiple tools have overlapping purposes that could cause confusion. 'query_local_ai' and 'reasoning_assist' both involve reasoning assistance with local AI, while 'hybrid_analysis' and 'token_efficient_reasoning' both address complex problem-solving with efficiency considerations. The descriptions don't clearly differentiate when to use one over the other.
The naming conventions are mixed but still readable. 'model_list' and 'query_local_ai' follow a verb_noun pattern, while 'hybrid_analysis', 'reasoning_assist', and 'token_efficient_reasoning' use descriptive phrases without clear verbs. This inconsistency makes the set less predictable but not chaotic.
With 5 tools, the count is reasonable for a server focused on AI and analysis tasks. It's slightly lean but covers core functionalities like listing models, querying AI, and analysis. A few more tools might enhance coverage, but this is within an appropriate range.
The toolset covers basic AI interaction and analysis but has notable gaps. There's no tool for managing or configuring models (e.g., load/unload), updating analysis parameters, or handling errors. The domain suggests more lifecycle operations, but agents can work around this with the provided tools.