agent-memory MCP server
by aqa03009-ux
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_MEMORY_DB | No | SQLite index | $VAULT/.vectors/memory.db |
| AGENT_MEMORY_DIM | No | MRL truncation dimension | 256 |
| AGENT_MEMORY_BATCH | No | Batch size inside a slice | 8 |
| AGENT_MEMORY_CHUNK | No | Documents per embedding slice | 16 |
| AGENT_MEMORY_MODEL | No | Sentence-transformers model | Qwen/Qwen3-Embedding-0.6B |
| AGENT_MEMORY_VAULT | No | Vault root | ~/memory |
| AGENT_MEMORY_DEVICE | No | A torch device (cpu, cuda:1, mps) or auto | cpu |
| AGENT_MEMORY_MCP_KEEP_WARM | No | 1 keeps the model loaded between MCP tool calls | 0 |
| AGENT_MEMORY_QUERY_INSTRUCT | No | Query-side prefix (applied when the model id contains qwen) | Qwen3 instruction |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues