mindcore-memory-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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memory_storeB | Store a new memory that should be remembered long-term. |
| memory_recallC | Recall memories relevant to the query. |
| memory_contextA | Build a context window from relevant memories for LLM input. |
| memory_update_confidenceA | Update a memory confidence score after correction. |
| memory_statsB | Get stats: total count, importance distribution, avg confidence. |
| memory_deleteA | Delete a memory by its ID. Irreversible — use with caution. |
| bnd_checkA | Evaluate content through the 3D Boundary balance algorithm (Forward/Reverse Formula). Returns 4D scores (TRJ/EVO/COG/BALANCE) and accept/reject decision. |
| bnd_statsA | Get BND manager stats: acceptance rate, score distributions, anti-chain triggers. |
| deduceB | Run the Deduction engine on stored memories to derive new cognitive insights. Finds patterns across high-quality COG memories. |
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 9 tools
Each tool has a clearly distinct purpose: BND algorithm evaluation, deduction, memory CRUD operations, context building, and stats. No overlapping functionality.
Tools follow a consistent snake_case convention with prefixes like 'bnd_' and 'memory_', though 'deduce' deviates from the verb_noun pattern and 'memory_context' is noun_noun instead of verb_noun.
9 tools is well within the ideal 3-15 range, covering all essential operations for a memory system with cognitive algorithms without being excessive.
Covers core memory operations (store, recall, delete, update confidence, stats, context) and specialized BND/deduction tools. Minor gaps like inability to update other memory fields or list all memories are acceptable.