shared-memory-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MDCG_ROOT | No | Private memory directory for this user. If unset, the startup script uses ~/.shared-memory-mcp/memory. | ~/.shared-memory-mcp/memory |
| MDCG_ACTOR | No | Identifier for the user/actor using the memory service. | |
| MDCG_AUX_ROOT | No | Auxiliary runtime directory. The startup script automatically sets an independent default when MDCG_ROOT is not set. | |
| MDCG_DATA_ROOT | No | Data directory. The startup script automatically sets an independent default when MDCG_ROOT is not set. | |
| MDCG_STATE_ROOT | No | State directory. The startup script automatically sets an independent default when MDCG_ROOT is not set. | |
| MDCG_MCP_SURFACE | No | MCP surface to expose. Recommended to keep as kernel initially, then switch to full if needed. | kernel |
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 |
|---|---|
| cgB | 灵枢认知图唯一入口（38 op：写/读/审/护/演化/元认知/预测/白箱/验证态 status/三元组反查 edges…）。完整 op/参数语义：cg(op="help", query="<op 名 | 参数名 | 工具名>") |
| stgC | 语义时空图 5 op：relation|timeline|anchors|consistency|state_chain。完整 op/参数语义：cg(op="help", query="<op 名 | 参数名 | 工具名>") |
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 2 tools
Both tools are op-dispatch mega-tools whose domains (cognitive graph vs. semantic spatiotemporal graph) overlap in graph/relation/edge concepts, making it hard to know which entry point to use. With 38 hidden ops in cg and 5 in stg, an agent must first call help to disambiguate, which is a poor tool-set boundary.
The two names cg and stg follow a consistent short-lowercase-abbreviation convention with no mixing of styles. They are not self-descriptive verb_noun names, but consistency is strong.
Two tools is thin for a server with this much implied functionality, and cg alone hides 38 operations behind a single tool. The op-dispatch design may be intentional, but at the tool level it feels compressed and forces discovery through a help op.
The descriptions suggest broad coverage: cg spans write/read/audit/protect/evolve/metacognition/predict/validation/edges, and stg covers relation/timeline/anchors/consistency/state_chain. Minor uncertainty remains because actual op semantics are hidden behind cg(op="help"), but the surface appears fairly complete for a shared-memory graph domain.