Hystersis MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HYSTERSIS_API_KEY | No | Optional API key for authentication | |
| HYSTERSIS_API_URL | No | The URL of the Hystersis API server | http://localhost:8080 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| add_memoryA | Add a new persistent memory or fact to Hystersis. Use this when the user shares a preference, fact, or instruction that should be remembered across sessions. |
| search_memoriesC | Search for existing memories in Hystersis using semantic or graph spreading activation. |
| get_contextA | Retrieve aggregated agent context from Hystersis including relevant memories for the current state. |
| create_entityC | Create a named entity in the Hystersis knowledge graph. |
| create_relationB | Create a relationship between two entities in the Hystersis knowledge graph. |
| compression_statsA | Retrieve compression metrics and token savings from the Hystersis ProMem engine. |
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 6 tools
Each tool has a distinct purpose: adding memories, searching, retrieving context, creating entities/relations, and getting stats. No overlap.
All tool names follow a consistent verb_noun snake_case pattern (e.g., add_memory, create_entity, get_context).
With 6 tools, the server is well-scoped, covering core memory and knowledge graph operations without being overly sparse or bloated.
Missing update/delete operations for memories and entities, and no read entity/relation tools, creating gaps in lifecycle coverage.