neurodivergent-memory
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEURODIVERGENT_MEMORY_DIR | No | Directory that contains the memories.json snapshot file. Defaults to ~/.neurodivergent-memory. | |
| NEURODIVERGENT_MEMORY_MAX | No | Maximum number of memories before eviction. Integer. Default: unlimited. | |
| NEURODIVERGENT_MEMORY_FILE | No | Explicit path to the snapshot file. Overrides NEURODIVERGENT_MEMORY_DIR. | |
| NEURODIVERGENT_MEMORY_EVICTION | No | Eviction policy when max is reached. One of: lru, access_frequency, district_priority. Default: lru. | |
| NEURODIVERGENT_MEMORY_WIP_LIMIT | No | Maximum in-progress practical execution tasks per agent_id. Integer. Set 0 to disable. Default: 1. | |
| NEURODIVERGENT_MEMORY_LOOP_WINDOW | No | Number of recent operations for loop detection. Integer. Default: 20. | |
| NEURODIVERGENT_MEMORY_QUEUE_DEPTH | No | Maximum pending write operations in the queue. Integer. Default: 50. | |
| NEURODIVERGENT_MEMORY_REPEAT_THRESHOLD | No | Token-overlap score threshold for detecting repeated content. Float between 0 and 1. Default: 0.85. | |
| NEURODIVERGENT_MEMORY_PING_PONG_THRESHOLD | No | Number of read/write ping-pong transitions before activating cooldown. Integer. Default: 3. | |
| NEURODIVERGENT_MEMORY_DISTILL_SUGGEST_THRESHOLD | No | Number of repeated logical_analysis reads of emotional_processing memories before suggesting distillation. Integer. Default: 3. | |
| NEURODIVERGENT_MEMORY_CROSS_DISTRICT_COOLDOWN_MS | No | Duration in milliseconds for temporary cross-district write cooldown. Integer. Default: 0 (disabled). | |
| NEURODIVERGENT_MEMORY_IMPORT_ALLOW_EXTERNAL_FILE | No | If 'true', allows import_memories to read snapshot files outside the persistence directory. Default: false. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| store_memoryB | Store a new memory in a specific district of the neurodivergent mind |
| retrieve_memoryB | Retrieve a specific memory by ID |
| update_memoryB | Update an existing memory's content, tags, district, emotional_valence, intensity, or epistemic_status |
| delete_memoryA | Permanently delete a memory and remove all its connections |
| connect_memoriesB | Create connections between memories (like neural pathways) |
| search_memoriesA | Search memories using BM25 semantic ranking with optional goal-context blending, recency bias, and filters. Returns results sorted by relevance score (0-1). |
| traverse_fromB | Walk the memory graph from a starting node up to N hops deep, returning all reachable memories |
| related_toA | Find memories related to a given memory ID, ranked by graph proximity + BM25 semantic score with optional goal-context blending. |
| list_memoriesA | List stored memories with optional pagination and filters |
| memory_statsA | Return aggregate statistics: total count, per-district counts, connection count, most-accessed nodes, and orphan nodes |
| storage_diagnosticsA | Show the resolved snapshot path, WAL path, and the effective environment/config source used for persistence. |
| server_handshakeA | Return runtime server identity and version details so clients can confirm the active build. |
| import_memoriesA | Bulk-import memories from inline entries or from a snapshot file. Supports dry-run validation, dedupe policies, and explicit snapshot migration flags. |
| distill_memoryA | Translate an emotional_processing memory into a structured logical artifact (signals, triggers, constraints, next_actions, risk_flags). Creates a distilled memory in logical_analysis district with reduced intensity and neutral valence for efficient consumption by planning agents. Only operates on emotional_processing memories. |
| prepare_memory_city_contextA | Return the same exploration context exposed by the explore_memory_city prompt, packaged as a tool result for clients that support tools but not MCP prompts. |
| prepare_synthesis_contextB | Return the same context exposed by the synthesize_memories prompt, packaged as a tool result for prompt-limited clients. |
| prepare_packetized_synthesis_contextB | Return the same context exposed by the synthesize_memory_packets prompt, packaged as a tool result for prompt-limited or attachment-constrained clients. |
| register_districtA | Register a custom district with LUCA ancestry validation. Custom districts must declare a valid parent that traces back to one of the 5 canonical districts (logical_analysis, emotional_processing, practical_execution, vigilant_monitoring, creative_synthesis). The custom district inherits its archetype from the canonical ancestor. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| explore_memory_city | Explore the neurodivergent memory city and its districts |
| synthesize_memories | Create new insights by connecting existing memories |
| synthesize_memory_packets | Create new insights from packetized memory slices for attachment-constrained clients |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Logical Analysis District | Structured thinking, problem solving, and analytical processes |
| Emotional Processing District | Feelings, emotional responses, and affective states |
| Practical Execution District | Action-oriented thoughts, tasks, and implementation |
| Vigilant Monitoring District | Awareness, safety concerns, and protective thinking |
| Creative Synthesis District | Novel connections, creative insights, and innovative thinking |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jmeyer1980/neurodivergent-memory'
If you have feedback or need assistance with the MCP directory API, please join our Discord server