Elite Reasoning 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
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 |
|---|---|
| elite_prepareB | Start a non-trivial task. Retain run_id and obey the returned continuation after each later Elite call. Not the answer. |
| elite_verifyC | Run one check, persist evidence by run_id, then follow the returned continuation before answering. |
| elite_memoryC | Search, record, or explicitly approve scoped memory items. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| goal | Anchor a durable goal and continuous verification lifecycle. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct phase: elite_memory handles memory persistence/retrieval, elite_prepare initiates a task run, and elite_verify checks and records evidence. There is no meaningful overlap or ambiguity about which tool to select.
All tools share the elite_ prefix and use snake_case, creating a recognizble namespace. The only minor inconsistency is that elite_prepare and elite_verify are verbs while elite_memory is a noun, so the verb/noun pattern is not perfectly uniform.
Three tools is a tightly scoped set for a specialized reasoning workflow: memory, task preparation, and verification. Each tool provides a clear capability without bloat and is within the ideal range.
The set covers the core reasoning lifecycle: starting a task, using scoped memory, and verifying evidence before answering. Some explicit run management like status, retry, or finalization is delegated to returned continuations, making it slightly indirect but still workable.